diff --git a/ChangeLog.md b/ChangeLog.md
new file mode 100644
--- /dev/null
+++ b/ChangeLog.md
@@ -0,0 +1,10 @@
+
+# Table of Contents
+
+1. [Changelog for ELynx](#org9916021)
+
+
+
+
+# Changelog for ELynx
+
diff --git a/LICENSE b/LICENSE
new file mode 100644
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,674 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc.
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+ The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works. By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users. We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors. You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+ To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights. Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received. You must make sure that they, too, receive
+or can get the source code. And you must show them these terms so they
+know their rights.
+
+ Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+ For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software. For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+ Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so. This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software. The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable. Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products. If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+ Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary. To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ TERMS AND CONDITIONS
+
+ 0. Definitions.
+
+ "This License" refers to version 3 of the GNU General Public License.
+
+ "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+ "The Program" refers to any copyrightable work licensed under this
+License. Each licensee is addressed as "you". "Licensees" and
+"recipients" may be individuals or organizations.
+
+ To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy. The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+ A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+ To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy. Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+ To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies. Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+ An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License. If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+ 1. Source Code.
+
+ The "source code" for a work means the preferred form of the work
+for making modifications to it. "Object code" means any non-source
+form of a work.
+
+ A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+ The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form. A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+ The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities. However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work. For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+ The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+ The Corresponding Source for a work in source code form is that
+same work.
+
+ 2. Basic Permissions.
+
+ All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met. This License explicitly affirms your unlimited
+permission to run the unmodified Program. The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work. This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+ You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force. You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright. Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+ Conveying under any other circumstances is permitted solely under
+the conditions stated below. Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+ 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+ No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+ When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+ 4. Conveying Verbatim Copies.
+
+ You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+ You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+ 5. Conveying Modified Source Versions.
+
+ You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+ a) The work must carry prominent notices stating that you modified
+ it, and giving a relevant date.
+
+ b) The work must carry prominent notices stating that it is
+ released under this License and any conditions added under section
+ 7. This requirement modifies the requirement in section 4 to
+ "keep intact all notices".
+
+ c) You must license the entire work, as a whole, under this
+ License to anyone who comes into possession of a copy. This
+ License will therefore apply, along with any applicable section 7
+ additional terms, to the whole of the work, and all its parts,
+ regardless of how they are packaged. This License gives no
+ permission to license the work in any other way, but it does not
+ invalidate such permission if you have separately received it.
+
+ d) If the work has interactive user interfaces, each must display
+ Appropriate Legal Notices; however, if the Program has interactive
+ interfaces that do not display Appropriate Legal Notices, your
+ work need not make them do so.
+
+ A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit. Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+ 6. Conveying Non-Source Forms.
+
+ You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+ a) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by the
+ Corresponding Source fixed on a durable physical medium
+ customarily used for software interchange.
+
+ b) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by a
+ written offer, valid for at least three years and valid for as
+ long as you offer spare parts or customer support for that product
+ model, to give anyone who possesses the object code either (1) a
+ copy of the Corresponding Source for all the software in the
+ product that is covered by this License, on a durable physical
+ medium customarily used for software interchange, for a price no
+ more than your reasonable cost of physically performing this
+ conveying of source, or (2) access to copy the
+ Corresponding Source from a network server at no charge.
+
+ c) Convey individual copies of the object code with a copy of the
+ written offer to provide the Corresponding Source. This
+ alternative is allowed only occasionally and noncommercially, and
+ only if you received the object code with such an offer, in accord
+ with subsection 6b.
+
+ d) Convey the object code by offering access from a designated
+ place (gratis or for a charge), and offer equivalent access to the
+ Corresponding Source in the same way through the same place at no
+ further charge. You need not require recipients to copy the
+ Corresponding Source along with the object code. If the place to
+ copy the object code is a network server, the Corresponding Source
+ may be on a different server (operated by you or a third party)
+ that supports equivalent copying facilities, provided you maintain
+ clear directions next to the object code saying where to find the
+ Corresponding Source. Regardless of what server hosts the
+ Corresponding Source, you remain obligated to ensure that it is
+ available for as long as needed to satisfy these requirements.
+
+ e) Convey the object code using peer-to-peer transmission, provided
+ you inform other peers where the object code and Corresponding
+ Source of the work are being offered to the general public at no
+ charge under subsection 6d.
+
+ A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+ A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling. In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage. For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product. A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+ "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source. The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+ If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information. But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+ The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed. Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+ Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+ 7. Additional Terms.
+
+ "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law. If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+ When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it. (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.) You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+ Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+ a) Disclaiming warranty or limiting liability differently from the
+ terms of sections 15 and 16 of this License; or
+
+ b) Requiring preservation of specified reasonable legal notices or
+ author attributions in that material or in the Appropriate Legal
+ Notices displayed by works containing it; or
+
+ c) Prohibiting misrepresentation of the origin of that material, or
+ requiring that modified versions of such material be marked in
+ reasonable ways as different from the original version; or
+
+ d) Limiting the use for publicity purposes of names of licensors or
+ authors of the material; or
+
+ e) Declining to grant rights under trademark law for use of some
+ trade names, trademarks, or service marks; or
+
+ f) Requiring indemnification of licensors and authors of that
+ material by anyone who conveys the material (or modified versions of
+ it) with contractual assumptions of liability to the recipient, for
+ any liability that these contractual assumptions directly impose on
+ those licensors and authors.
+
+ All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10. If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term. If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+ If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+ Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+ 8. Termination.
+
+ You may not propagate or modify a covered work except as expressly
+provided under this License. Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+ However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+ Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+ Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License. If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+ 9. Acceptance Not Required for Having Copies.
+
+ You are not required to accept this License in order to receive or
+run a copy of the Program. Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance. However,
+nothing other than this License grants you permission to propagate or
+modify any covered work. These actions infringe copyright if you do
+not accept this License. Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+ 10. Automatic Licensing of Downstream Recipients.
+
+ Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License. You are not responsible
+for enforcing compliance by third parties with this License.
+
+ An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations. If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+ You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License. For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+ 11. Patents.
+
+ A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based. The
+work thus licensed is called the contributor's "contributor version".
+
+ A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version. For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+ Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+ In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement). To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+ If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients. "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+ If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+ A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License. You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+ Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+ 12. No Surrender of Others' Freedom.
+
+ If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all. For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+ 13. Use with the GNU Affero General Public License.
+
+ Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work. The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+ 14. Revised Versions of this License.
+
+ The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+ Each version is given a distinguishing version number. If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation. If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+ If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+ Later license versions may give you additional or different
+permissions. However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+ 15. Disclaimer of Warranty.
+
+ THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+ 16. Limitation of Liability.
+
+ IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+ 17. Interpretation of Sections 15 and 16.
+
+ If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+
+ Copyright (C)
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see .
+
+Also add information on how to contact you by electronic and paper mail.
+
+ If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+ Copyright (C)
+ This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+ You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+.
+
+ The GNU General Public License does not permit incorporating your program
+into proprietary programs. If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library. If this is what you want to do, use the GNU Lesser General
+Public License instead of this License. But first, please read
+.
diff --git a/README.md b/README.md
new file mode 100644
--- /dev/null
+++ b/README.md
@@ -0,0 +1,417 @@
+
+
+# The ELynx Suite
+
+Version: 0.0.1.
+Reproducible evolution made easy.
+
+The ELynx Suite is a Haskell library and a tool set for computational biology.
+The goal of the ELynx Suite is reproducible research. Evolutionary sequences and
+phylogenetic trees can be read, viewed, modified and simulated. Exact
+specification of all options is necessary, and nothing is assumed about the data
+(e.g., the type of code). The command line with all arguments is consistently,
+and automatically logged. The work overhead in the beginning usually pays off in
+the end.
+
+The Elynx Suite consists of three library packages and two executables providing
+a range of sub commands.
+
+The library packages are:
+
+- **elynx-seq:** Handle evolutionary sequences and multi sequence alignments;
+- **elynx-tree:** Handle phylogenetic trees;
+- **elynx-tools:** Tools for the provided executables;
+
+The executables are:
+
+- **SLynx:** Analyze, modify, and simulate evolutionary sequences (FASTA format);
+- **TLynx:** Analyze, modify, and simulate phylogenetic trees (Newick format).
+
+**ELynx is still under development. We happily receive comments, ideas, feature
+requests, or pull requests!**
+
+
+# Installation
+
+ELynx is written in [Haskell](https://www.haskell.org/) and can be installed with [Stack](https://docs.haskellstack.org/en/stable/README/).
+
+1. Install Stack with your package manager, or directly from the web
+ page.
+
+ curl -sSL https://get.haskellstack.org/ | sh
+
+2. Clone the ELynx repository.
+
+ git clone clone https://github.com/dschrempf/elynx
+
+3. Navigate to the newly created `elynx` folder and build the binaries.
+ This will take a while.
+
+ stack build
+
+4. Run a binary from within the project directory. For example,
+
+ stack exec tlynx -- --help
+
+5. If needed, install the binaries.
+
+ stack install
+
+ The binaries are installed into `~/.local/bin/` which has to be added [PATH](https://en.wikipedia.org/wiki/PATH_(variable)).
+ Then, they can be used directly.
+
+
+# SLynx
+
+Handle evolutionary sequences.
+
+ slynx --help
+
+ ELynx Suite version 0.5.1. Developed by Dominik Schrempf. Compiled on September
+ 9, 2019, at 10:48 am, UTC.
+
+ Usage: slynx [-v|--verbosity VALUE] [-o|--output-file-basename NAME] COMMAND
+ Analyze, and simulate multi sequence alignments.
+
+ Available options:
+ -h,--help Show this help text
+ -V,--version Show version
+ -v,--verbosity VALUE Be verbose; one of: Quiet Warning Info
+ Debug (default: Info)
+ -o,--output-file-basename NAME
+ Specify base name of output file
+
+ Available commands:
+ concatenate
+ examine If data is a multi sequence alignment, additionally
+ analyze columns.
+ filter-rows
+ filter-columns
+ simulate
+ sub-sample Create a given number of multi sequence alignments,
+ each of which containing a given number of random
+ sites drawn from the original multi sequence
+ alignment.
+ translate
+
+ File formats:
+ - FASTA
+
+ Alphabet types:
+ - DNA (nucleotides)
+ - DNAX (nucleotides; including gaps)
+ - DNAI (nucleotides; including gaps, and IUPAC codes)
+ - Protein (amino acids)
+ - ProteinX (amino acids; including gaps)
+ - ProteinS (amino acids; including gaps, and translation stops)
+ - ProteinI (amino acids; including gaps, translation stops, and IUPAC codes)
+
+ The ELynx Suite.
+ A Haskell library and a tool set for computational biology. The goal of the
+ ELynx Suite is reproducible research. Evolutionary sequences and phylogenetic
+ trees can be read, viewed, modified and simulated. Exact specification of all
+ options is necessary, and nothing is assumed about the data (e.g., the type of
+ code). The command line with all arguments is consistently, and automatically
+ logged. The work overhead in the beginning usually pays off in the end.
+ slynx Analyze, modify, and simulate evolutionary sequences.
+ tlynx Analyze, modify, and simulate phylogenetic trees.
+
+
+## Concatenate
+
+Concatenate multi sequence alignments.
+
+ slynx concatenate --help
+
+ Concatenate sequences found in input files.
+
+ Usage: slynx concatenate (-a|--alphabet NAME) INPUT-FILE
+
+ Available options:
+ -a,--alphabet NAME Specify alphabet type NAME
+ INPUT-FILE Read sequences from INPUT-FILE
+ -h,--help Show this help text
+
+
+## Examine
+
+Examine sequence with `slynx examine`.
+
+ slynx examine --help
+
+ Examine sequences.
+
+ Usage: slynx examine (-a|--alphabet NAME) [INPUT-FILE] [--per-site]
+ If data is a multi sequence alignment, additionally analyze columns.
+
+ Available options:
+ -a,--alphabet NAME Specify alphabet type NAME
+ INPUT-FILE Read sequences from INPUT-FILE
+ --per-site Report per site summary statistics
+ -h,--help Show this help text
+
+
+## Filter
+
+Filter sequences with `filer-rows`.
+
+ slynx filter-rows --help
+
+ Filter rows (or sequences) found in input files.
+
+ Usage: slynx filter-rows (-a|--alphabet NAME) [INPUT-FILE]
+ [--longer-than LENGTH] [--shorter-than LENGTH]
+
+ Available options:
+ -a,--alphabet NAME Specify alphabet type NAME
+ INPUT-FILE Read sequences from INPUT-FILE
+ --longer-than LENGTH Only keep sequences longer than LENGTH
+ --shorter-than LENGTH Only keep sequences shorter than LENGTH
+ -h,--help Show this help text
+
+Filter columns of multi sequence alignments with `filter-columns`.
+
+ slynx filter-columns --help
+
+ Filter columns of multi-sequence alignments.
+
+ Usage: slynx filter-columns (-a|--alphabet NAME) [INPUT-FILE]
+ [--standard-chars DOUBLE]
+
+ Available options:
+ -a,--alphabet NAME Specify alphabet type NAME
+ INPUT-FILE Read sequences from INPUT-FILE
+ --standard-chars DOUBLE Keep columns with a proportion standard (non-IUPAC)
+ characters larger than DOUBLE in [0,1]
+ -h,--help Show this help text
+
+
+## Simulate
+
+Simulate sequences with `slynx simulate`.
+
+ slynx simulate --help
+
+ Simulate multi sequence alignments.
+
+ Usage: slynx simulate (-t|--tree-file Name) [-s|--substitution-model MODEL]
+ [-m|--mixture-model MODEL] [-e|--edm-file NAME]
+ [-w|--mixture-model-weights "[DOUBLE,DOUBLE,...]"]
+ [-g|--gamma-rate-heterogeneity "(NCAT,SHAPE)"]
+ (-l|--length NUMBER) [-S|--seed [INT]]
+
+ Available options:
+ -t,--tree-file Name Read trees from file NAME
+ -s,--substitution-model MODEL
+ Set the phylogenetic substitution model; available
+ models are shown below (mutually exclusive with -m
+ option)
+ -m,--mixture-model MODEL Set the phylogenetic mixture model; available models
+ are shown below (mutually exclusive with -s option)
+ -e,--edm-file NAME Empirical distribution model file NAME in Phylobayes
+ format
+ -w,--mixture-model-weights "[DOUBLE,DOUBLE,...]"
+ Weights of mixture model components
+ -g,--gamma-rate-heterogeneity "(NCAT,SHAPE)"
+ Number of gamma rate categories and shape parameter
+ -l,--length NUMBER Set alignment length to NUMBER
+ -S,--seed [INT] Seed for random number generator; list of 32 bit
+ integers with up to 256 elements (default: random)
+ -h,--help Show this help text
+
+ Substitution models:
+ -s "MODEL[PARAMETER,PARAMETER,...]{STATIONARY_DISTRIBUTION}"
+ Supported DNA models: JC, HKY.
+ For example,
+ -s HKY[KAPPA]{DOUBLE,DOUBLE,DOUBLE,DOUBLE}
+ Supported Protein models: Poisson, Poisson-Custom, LG, LG-Custom, WAG, WAG-Custom.
+ MODEL-Custom means that only the exchangeabilities of MODEL are used,
+ and a custom stationary distribution is provided.
+ For example,
+ -s LG-Custom{...}
+
+ Mixture models:
+ -m "MIXTURE(SUBSTITUTION_MODEL_1,SUBSTITUTION_MODEL_2)"
+ For example,
+ -m "MIXTURE(JC,HKY[6.0]{0.3,0.2,0.2,0.3})"
+ Mixture weights have to be provided with the -w option.
+
+ Special mixture models:
+ -m CXX
+ where XX is 10, 20, 30, 40, 50, or 60; CXX models, Quang et al., 2008.
+ -m "EDM(EXCHANGEABILITIES)"
+ Arbitrary empirical distribution mixture (EDM) models.
+ Stationary distributions have to be provided with the -e option.
+ For example,
+ LG exchangeabilities with stationary distributions given in FILE.
+ -m "EDM(LG-Custom)" -e FILE
+ For special mixture models, mixture weights are optional.
+
+
+## Sub-sample
+
+Sub-sample columns from multi sequence alignments.
+
+ slynx sub-sample --help
+
+ Usage: slynx sub-sample (-a|--alphabet NAME) [INPUT-FILE]
+ (-n|--number-of-sites INT)
+ (-m|--number-of-alignments INT) [-S|--seed [INT]]
+ Create a given number of multi sequence alignments, each of which containing a
+ given number of random sites drawn from the original multi sequence alignment.
+
+ Available options:
+ -a,--alphabet NAME Specify alphabet type NAME
+ INPUT-FILE Read sequences from INPUT-FILE
+ -n,--number-of-sites INT Number of sites randomly drawn with replacement
+ -m,--number-of-alignments INT
+ Number of multi sequence alignments to be created
+ -S,--seed [INT] Seed for random number generator; list of 32 bit
+ integers with up to 256 elements (default: random)
+ -h,--help Show this help text
+
+
+## Translate
+
+Translate sequences.
+
+ slynx translate --help
+
+ Translate from DNA to Protein or DNAX to ProteinX.
+
+ Usage: slynx translate (-a|--alphabet NAME) [INPUT-FILE]
+ (-r|--reading-frame INT) (-u|--universal-code CODE)
+
+ Available options:
+ -a,--alphabet NAME Specify alphabet type NAME
+ INPUT-FILE Read sequences from INPUT-FILE
+ -r,--reading-frame INT Reading frame [0|1|2].
+ -u,--universal-code CODE universal code; one of: Standard,
+ VertebrateMitochondrial.
+ -h,--help Show this help text
+
+
+# TLynx
+
+Handle phylogenetic trees in Newick format.
+
+ tlynx --help
+
+ ELynx Suite version 0.5.1. Developed by Dominik Schrempf. Compiled on September
+ 9, 2019, at 10:48 am, UTC.
+
+ Usage: tlynx [-v|--verbosity VALUE] [-o|--output-file-basename NAME] COMMAND
+ Compare, examine, and simulate phylogenetic trees.
+
+ Available options:
+ -h,--help Show this help text
+ -V,--version Show version
+ -v,--verbosity VALUE Be verbose; one of: Quiet Warning Info
+ Debug (default: Info)
+ -o,--output-file-basename NAME
+ Specify base name of output file
+
+ Available commands:
+ compare
+ examine
+ simulate Simulate reconstructed trees using the point process.
+ See Gernhard, T. (2008). The conditioned
+ reconstructed process. Journal of Theoretical
+ Biology, 253(4), 769–778.
+ http://doi.org/10.1016/j.jtbi.2008.04.005
+
+ File formats:
+ - Newick
+
+ The ELynx Suite.
+ A Haskell library and a tool set for computational biology. The goal of the
+ ELynx Suite is reproducible research. Evolutionary sequences and phylogenetic
+ trees can be read, viewed, modified and simulated. Exact specification of all
+ options is necessary, and nothing is assumed about the data (e.g., the type of
+ code). The command line with all arguments is consistently, and automatically
+ logged. The work overhead in the beginning usually pays off in the end.
+ slynx Analyze, modify, and simulate evolutionary sequences.
+ tlynx Analyze, modify, and simulate phylogenetic trees.
+
+
+## Compare
+
+Compute distances between phylogenetic trees.
+
+ tlynx compare --help
+
+ Compute distances between phylogenetic trees.
+
+ Usage: tlynx compare (-d|--distance MEASURE) [-s|--summary-statistics]
+ [INPUT-FILES]
+
+ Available options:
+ -d,--distance MEASURE Type of distance to calculate (available distance
+ measures are listed below)
+ -s,--summary-statistics Report summary statistics only
+ INPUT-FILES Read tree(s) from INPUT-FILES; if more files are
+ given, one tree is expected per file
+ -h,--help Show this help text
+
+ Available distance measures:
+ Symmetric distance: -d symmetric
+ Incompatible split distance: -d incompatible-split[VAL]
+ Collapse branches with support less than VAL before distance calculation;
+ in this way, only well supported difference contribute to the distance measure.
+
+
+## Examine
+
+Compute summary statistics of phylogenetic trees.
+
+ tlynx examine --help
+
+ Compute summary statistics of phylogenetic trees.
+
+ Usage: tlynx examine [INPUT-FILE]
+
+ Available options:
+ INPUT-FILE Read trees from INPUT-FILE
+ -h,--help Show this help text
+
+
+## Simulate
+
+Simulate phylogenetic trees using birth and death processes.
+
+ tlynx simulate --help
+
+ Simulate phylogenetic trees using birth and death processes.
+
+ Usage: tlynx simulate [-t|--nTrees INT] [-n|--nLeaves INT] [-H|--height DOUBLE]
+ [-M|--condition-on-mrca] [-l|--lambda DOUBLE]
+ [-m|--mu DOUBLE] [-r|--rho DOUBLE] [-u|--sub-sample]
+ [-s|--summary-statistics] [-S|--seed [INT]]
+ Simulate reconstructed trees using the point process. See Gernhard, T. (2008).
+ The conditioned reconstructed process. Journal of Theoretical Biology, 253(4),
+ 769–778. http://doi.org/10.1016/j.jtbi.2008.04.005
+
+ Available options:
+ -t,--nTrees INT Number of trees (default: 10)
+ -n,--nLeaves INT Number of leaves per tree (default: 5)
+ -H,--height DOUBLE Fix tree height (no default)
+ -M,--condition-on-mrca Do not condition on height of origin but on height of
+ MRCA
+ -l,--lambda DOUBLE Birth rate lambda (default: 1.0)
+ -m,--mu DOUBLE Death rate mu (default: 0.9)
+ -r,--rho DOUBLE Sampling probability rho (default: 1.0)
+ -u,--sub-sample Perform sub-sampling; see below.
+ -s,--summary-statistics Only output number of children for each branch
+ -S,--seed [INT] Seed for random number generator; list of 32 bit
+ integers with up to 256 elements (default: random)
+ -h,--help Show this help text
+
+ Height of Trees: if no tree height is given, the heights will be randomly drawn from the expected distribution given the number of leaves, the birth and the death rate.
+ Summary statistics only: only print (NumberOfExtantChildren BranchLength) pairs for each branch of each tree. The trees are separated by a newline character.
+ Sub-sampling: simulate one big tree with n'=round(n/rho), n'>=n, leaves, and randomly sample sub-trees with n leaves. Hence, with rho=1.0, the same tree is reported over and over again.
+
+
+# ELynx
+
+Documentation of the library can be found on Hackage.
+
diff --git a/elynx-tree.cabal b/elynx-tree.cabal
new file mode 100644
--- /dev/null
+++ b/elynx-tree.cabal
@@ -0,0 +1,102 @@
+cabal-version: 1.12
+name: elynx-tree
+version: 0.0.1
+license: GPL-3
+license-file: LICENSE
+copyright: Dominik Schrempf (2019)
+maintainer: dominik.schrempf@gmail.com
+author: Dominik Schrempf
+homepage: https://github.com/dschrempf/elynx#readme
+bug-reports: https://github.com/dschrempf/elynx/issues
+synopsis: Handle phylogenetic trees
+description:
+ Examine, compare, and simulate phylogenetic trees in a reproducible way. Please see the README on GitHub at .
+category: Bioinformatics
+build-type: Simple
+extra-source-files:
+ README.md
+ ChangeLog.md
+
+source-repository head
+ type: git
+ location: https://github.com/dschrempf/elynx
+
+library
+ exposed-modules:
+ ELynx.Data.Tree.Bipartition
+ ELynx.Data.Tree.BranchSupportTree
+ ELynx.Data.Tree.Distance
+ ELynx.Data.Tree.EvoTree
+ ELynx.Data.Tree.MeasurableTree
+ ELynx.Data.Tree.NamedTree
+ ELynx.Data.Tree.PhyloTree
+ ELynx.Data.Tree.SumStat
+ ELynx.Data.Tree.Tree
+ ELynx.Distribution.BirthDeath
+ ELynx.Distribution.BirthDeathCritical
+ ELynx.Distribution.BirthDeathCriticalNoTime
+ ELynx.Distribution.BirthDeathNearlyCritical
+ ELynx.Distribution.CoalescentContinuous
+ ELynx.Distribution.TimeOfOrigin
+ ELynx.Distribution.TimeOfOriginNearCritical
+ ELynx.Distribution.Types
+ ELynx.Export.Tree.Newick
+ ELynx.Import.Tree.Newick
+ ELynx.Simulate.Coalescent
+ ELynx.Simulate.PointProcess
+ hs-source-dirs: src
+ other-modules:
+ Paths_elynx_tree
+ default-language: Haskell2010
+ ghc-options: -Wall
+ build-depends:
+ QuickCheck >=2.13.2 && <2.14,
+ base >=4.12.0.0 && <4.13,
+ bytestring >=0.10.8.2 && <0.11,
+ containers >=0.6.0.1 && <0.7,
+ elynx-tools >=0.0.1 && <0.1,
+ lifted-async >=0.10.0.4 && <0.11,
+ math-functions >=0.3.1.0 && <0.4,
+ megaparsec >=7.0.5 && <7.1,
+ mwc-random >=0.14.0.0 && <0.15,
+ optparse-applicative >=0.14.3.0 && <0.15,
+ parallel >=3.2.2.0 && <3.3,
+ primitive >=0.6.4.0 && <0.7,
+ quickcheck-instances >=0.3.22 && <0.4,
+ statistics >=0.15.0.0 && <0.16,
+ transformers >=0.5.6.2 && <0.6,
+ vector >=0.12.0.3 && <0.13
+
+test-suite tree-test
+ type: exitcode-stdio-1.0
+ main-is: Spec.hs
+ hs-source-dirs: test
+ other-modules:
+ ELynx.Data.Tree.BipartitionSpec
+ ELynx.Data.Tree.DistanceSpec
+ ELynx.Data.Tree.TreeSpec
+ ELynx.Export.Tree.NewickSpec
+ ELynx.Import.Tree.NewickSpec
+ Paths_elynx_tree
+ default-language: Haskell2010
+ ghc-options: -Wall -eventlog -threaded -rtsopts -with-rtsopts=-N
+ build-depends:
+ QuickCheck >=2.13.2 && <2.14,
+ base >=4.12.0.0 && <4.13,
+ bytestring >=0.10.8.2 && <0.11,
+ containers >=0.6.0.1 && <0.7,
+ elynx-tools >=0.0.1 && <0.1,
+ elynx-tree -any,
+ hspec >=2.7.1 && <2.8,
+ hspec-megaparsec >=2.0.1 && <2.1,
+ lifted-async >=0.10.0.4 && <0.11,
+ math-functions >=0.3.1.0 && <0.4,
+ megaparsec >=7.0.5 && <7.1,
+ mwc-random >=0.14.0.0 && <0.15,
+ optparse-applicative >=0.14.3.0 && <0.15,
+ parallel >=3.2.2.0 && <3.3,
+ primitive >=0.6.4.0 && <0.7,
+ quickcheck-instances >=0.3.22 && <0.4,
+ statistics >=0.15.0.0 && <0.16,
+ transformers >=0.5.6.2 && <0.6,
+ vector >=0.12.0.3 && <0.13
diff --git a/src/ELynx/Data/Tree/Bipartition.hs b/src/ELynx/Data/Tree/Bipartition.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Data/Tree/Bipartition.hs
@@ -0,0 +1,231 @@
+{- |
+Module : ELynx.Data.Tree.Bipartition
+Description : Bipartitions on trees
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Aug 30 15:28:17 2019.
+
+'Bipartition's are weird in that
+> Bipartition x y == Bipartition y x
+is True.
+
+Also,
+> Bipartition x y > Bipartition y x
+is False, even when @x > y@.
+
+That's why we have to make sure that for
+> Bipartition x y
+we always have @x >= y@.
+
+-}
+
+module ELynx.Data.Tree.Bipartition
+ ( -- * The 'Bipartition' data type.
+ Bipartition ()
+ , bp
+ , bpmap
+ -- * Working with 'Bipartition's.
+ , bipartitions
+ , bipartitionToBranch
+ , bipartitionsCombined
+ ) where
+
+-- import Data.List
+import qualified Data.Map as M
+import Data.Maybe
+import qualified Data.Set as S
+import Data.Tree
+
+import ELynx.Data.Tree.Tree
+
+-- | Bipartitions with 'S.Set's, since order of elements within the leaf sets
+-- is not important. Also the order of the two leaf sets of the bipartition is
+-- not important (see 'Eq' instance definition).
+newtype Bipartition a = Bipartition (S.Set a, S.Set a)
+ deriving (Show, Read)
+
+-- instance Show a => Show (Bipartition a) where
+-- show (Bipartition (x, y)) = "(" ++ showSet x ++ "|" ++ showSet y ++ ")"
+-- where showSet s = intercalate "," $ map show $ S.toList s
+
+-- | Create a bipartition from two 'S.Set's.
+bp :: Ord a => S.Set a -> S.Set a -> Bipartition a
+bp x y = if x >= y
+ then Bipartition (x, y)
+ else Bipartition (y, x)
+
+-- | Create a bipartition from two 'S.Set's.
+bpWith :: (Ord a, Ord b) => (a -> b) -> S.Set a -> S.Set a -> Bipartition b
+bpWith f x y = bpmap f $ bp x y
+
+instance (Eq a) => Eq (Bipartition a) where
+ Bipartition x == Bipartition y = x == y
+
+instance (Ord a) => Ord (Bipartition a) where
+ Bipartition x `compare` Bipartition y = x `compare` y
+
+-- | Map a function over all elements in the 'Bipartition's.
+bpmap :: (Ord a, Ord b) => (a -> b) -> Bipartition a -> Bipartition b
+bpmap f (Bipartition (x, y)) = bp (S.map f x) (S.map f y)
+
+-- | Each node of a tree is root of a subtree. Get the leaves of the subtree of
+-- each node.
+leavesTree :: (Ord a) => Tree a -> Tree (S.Set a)
+leavesTree (Node l []) = Node (S.singleton l) []
+leavesTree (Node _ xs) = Node (S.unions $ map rootLabel xs') xs'
+ where xs' = map leavesTree xs
+
+-- | Loop through each tree in a forest to report the complementary leaf sets.
+subForestGetLeafSets :: (Ord a)
+ => S.Set a -- ^ Complementary leaf set at the stem
+ -> Tree (S.Set a) -- ^ Tree with leaf set nodes
+ -> [S.Set a]
+subForestGetLeafSets lvsS t = lvsOthers
+ where
+ xs = subForest t
+ nChildren = length xs
+ lvsChildren = map rootLabel xs
+ lvsOtherChildren = [ S.unions $ lvsS
+ : take i lvsChildren ++ drop (i+1) lvsChildren
+ | i <- [0 .. (nChildren - 1)] ]
+ lvsOthers = map (S.union lvsS) lvsOtherChildren
+
+
+-- | Get all bipartitions.
+bipartitions :: Ord a => Tree a -> S.Set (Bipartition a)
+bipartitions t = if S.size (S.fromList lvs) == length lvs
+ then bipartitionsUnsafe t
+ else error "bipartitions: The tree contains duplicate leaves."
+ where lvs = leaves t
+
+-- | See 'bipartitions', but do not check if leaves are unique.
+bipartitionsUnsafe :: Ord a => Tree a -> S.Set (Bipartition a)
+bipartitionsUnsafe (Node _ [] ) = S.empty
+-- If the root stem is split by degree two nodes, just go on since the root stem
+-- does not induce any bipartitions.
+bipartitionsUnsafe (Node _ [x]) = bipartitionsUnsafe x
+-- We have rose trees, so we need to through the list of children and combine
+-- each of them with the rest.
+bipartitionsUnsafe t =
+ S.unions [ bipartitions' lvs x
+ | (lvs, x) <- zip lvsOthers (subForest lvsTree) ]
+ where
+ lvsTree = leavesTree t
+ lvsOthers = subForestGetLeafSets S.empty lvsTree
+
+bipartitions' :: Ord a => S.Set a -> Tree (S.Set a) -> S.Set (Bipartition a)
+bipartitions' lvsStem t@(Node lvs xs)
+ | S.null lvsStem = error "bipartitions': no complementing leaf set."
+ -- Leaf; return a singleton map; bipartition with the leaf and the rest of the tree.
+ | null xs = S.singleton $ bp lvsStem lvs
+ -- For degree two nodes, pass the creation of the set on.
+ | length xs == 1 = bipartitions' lvsStem (head xs)
+ -- We have rose trees, so we need to through the list of children and combine
+ -- each of them with the rest. Also, we use up the possible branch information
+ -- 'br' and start afresh with 'mempty'.
+ | otherwise = S.unions $ S.singleton (bp lvsStem lvs) : zipWith bipartitions' lvsOthers xs
+ where
+ lvsOthers = subForestGetLeafSets lvsStem t
+
+-- | Each branch on a 'Tree' defines a unique 'Bipartition' of leaves. Convert a
+-- tree into a 'M.Map' from each 'Bipartition' to the branch inducing the
+-- respective 'Bipartition'. The information about the branch is extracted from
+-- the nodes with a given function. If the tree has degree two nodes, the branch
+-- values are combined; a unity element is required, and so we need the 'Monoid'
+-- type class constraint. Checks if leaves are unique.
+bipartitionToBranch :: (Ord a, Ord b, Monoid c)
+ => (a -> b) -- ^ Value to compare on
+ -> (a -> c) -- ^ Convert node to branch length
+ -> Tree a -- ^ Tree to dissect
+ -> M.Map (Bipartition b) c
+bipartitionToBranch f g t = if S.size (S.fromList lvs) == length lvs
+ then bipartitionToBranchUnsafe f g t
+ else error "bipartitionToBranch: The tree contains duplicate leaves."
+ where lvs = leaves t
+
+-- | See 'bipartitionToBranch', but does not check if leaves are unique.
+bipartitionToBranchUnsafe :: (Ord a, Ord b, Monoid c)
+ => (a -> b) -- ^ Value to compare on
+ -> (a -> c) -- ^ Convert node to branch length
+ -> Tree a -- ^ Tree to dissect
+ -> M.Map (Bipartition b) c
+bipartitionToBranchUnsafe _ _ (Node _ [] ) = M.empty
+-- If the root stem is split by degree two nodes, just go on and ignore the
+-- branch information, because the stem does not induce any bipartition
+-- anyways..
+bipartitionToBranchUnsafe f g (Node _ [x]) = bipartitionToBranchUnsafe f g x
+-- We have rose trees, so we need to through the list of children and combine
+-- each of them with the rest.
+bipartitionToBranchUnsafe f g t =
+ M.unionsWith (<>) [ bipartitionToBranch' lvs mempty f g x
+ | (lvs, x) <- zip lvsOthers (subForest nodeAndLeavesTrees) ]
+ where
+ lvsTree = leavesTree t
+ nodeAndLeavesTrees = fromJust $ merge t lvsTree
+ lvsOthers = subForestGetLeafSets S.empty lvsTree
+
+-- We need information about the nodes, and also about the leaves of the induced
+-- sub trees. Hence, we need a somewhat complicated node type @(a, S.Set a)@.
+bipartitionToBranch' :: (Ord a, Ord b, Monoid c)
+ => S.Set a -- ^ Complementary set of leaves
+ -- towards the stem
+ -> c -- ^ Maybe we have to pass along some
+ -- information from above (degree two
+ -- nodes)
+ -> (a -> b) -- ^ Extract value to compare on
+ -> (a -> c) -- ^ Extract information about branch
+ -- from node
+ -> Tree (a, S.Set a) -- ^ Tree containing nodes and sub
+ -- tree leaf sets
+ -> M.Map (Bipartition b) c
+bipartitionToBranch' lvsStem br f g t@(Node l xs )
+ | S.null lvsStem = error "bipartitionToBranch': no complementing leaf set."
+ -- Leaf; return a singleton map; bipartition with the leaf and the rest of the tree.
+ | null xs = M.singleton (bpWith f lvsStem lvsThisNode) (br <> g label)
+ -- Pass the creation of the map entry on, but extend the branch.
+ | length xs == 1 = bipartitionToBranch' lvsStem (br <> g label) f g (head xs)
+ -- We have rose trees, so we need to through the list of children and combine
+ -- each of them with the rest. Also, we use up the possible branch information
+ -- 'br' and start afresh with 'mempty'.
+ | otherwise = M.insert (bpWith f lvsStem lvsThisNode) (br <> g label)
+ $ M.unions [ bipartitionToBranch' lvs mempty f g x
+ | (lvs, x) <- zip lvsOthers xs ]
+ where
+ label = fst l
+ lvsThisNode = snd l
+ lvsOthers = subForestGetLeafSets lvsStem $ fmap snd t
+
+-- | Get all bipartitions, but combine leaves from multifurcations. This is
+-- useful to find incompatible splits. See
+-- 'ELynx.Data.Tree.Distance.incompatibleSplitsDistance'. Assume that a root
+-- node with three children is actually not a multifurcation (because then we
+-- would have no induced bypartitions), but rather corresponds to an unrooted
+-- tree.
+bipartitionsCombined :: (Ord a, Show a) => Tree a -> S.Set (Bipartition a)
+bipartitionsCombined t@(Node _ xs)
+ | null xs = S.empty
+ | length xs == 1 = bipartitionsCombined (head xs)
+ -- One big multifurcation does not induce any bipartitions.
+ | length xs > 3 = S.empty
+ | otherwise = res
+ where
+ res = S.unions [ bipartitionsCombined' lvs x
+ | (lvs, x) <- zip lvsOthers (subForest lvsTree) ]
+ lvsTree = leavesTree t
+ lvsOthers = subForestGetLeafSets S.empty lvsTree
+
+bipartitionsCombined' :: Ord a => S.Set a -> Tree (S.Set a) -> S.Set (Bipartition a)
+bipartitionsCombined' lvsStem t@(Node lvs xs)
+ | S.null lvsStem = error "bipartitionsCombined': no complementing leaf set."
+ | null xs = S.singleton $ bp lvsStem lvs
+ | length xs == 1 = bipartitionsCombined' lvsStem (head xs)
+ | length xs == 2 = S.unions $
+ S.singleton (bp lvsStem lvs) : zipWith bipartitionsCombined' lvsOthers xs
+ | otherwise = S.singleton $ bp lvsStem lvs
+ where
+ lvsOthers = subForestGetLeafSets lvsStem t
diff --git a/src/ELynx/Data/Tree/BranchSupportTree.hs b/src/ELynx/Data/Tree/BranchSupportTree.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Data/Tree/BranchSupportTree.hs
@@ -0,0 +1,64 @@
+{- |
+Module : ELynx.Data.Tree.BranchSupportTree
+Description : Node label with branch support
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Jun 13 14:06:45 2019.
+
+-}
+
+module ELynx.Data.Tree.BranchSupportTree
+ ( BranchSupport
+ , BranchSupportLabel (..)
+ , normalize
+ , collapse
+ ) where
+
+import Data.List
+import Data.Maybe
+import Data.Tree
+
+-- XXX : This is probably the preferred way.
+-- data BranchSupport =
+-- BSNothing
+-- | BSInt Int
+-- | BSDouble Double
+-- deriving (Num)
+
+-- | At the moment, just use 'Double'. It would be preferable to use a wrapper
+-- data type that can handle 'Int' or 'Double'.
+type BranchSupport = Maybe Double
+
+-- | A label that supports branch support values.
+class BranchSupportLabel a where
+ -- | For now, branch support is a Double, but one could also think about
+ -- bootstrap values, which are integers.
+ getBranchSupport :: a -> BranchSupport
+ setBranchSupport :: BranchSupport -> a -> a
+
+apply :: BranchSupportLabel a => (Double -> Double) -> a -> a
+apply f l = setBranchSupport (f <$> s) l
+ where s = getBranchSupport l
+
+-- | Normalize branch support values. The maximum branch support value will be
+-- set to 1.0.
+normalize :: BranchSupportLabel a => Tree a -> Tree a
+normalize t = if isNothing m then t else fmap (apply (/ fromJust m)) t
+ where m = maximum $ fmap getBranchSupport t
+
+accept :: Double -> Maybe Double -> Bool
+accept _ Nothing = True
+accept thresh (Just s) = s > thresh
+
+-- | Collapse branches with support lower than given value. Note, branch length
+-- is ignored at the moment.
+collapse :: BranchSupportLabel a => Double -> Tree a -> Tree a
+collapse _ n@(Node _ []) = n
+collapse thresh (Node l xs) = Node l $ map (collapse thresh) (highS ++ lowSubForest)
+ where (highS, lowS) = partition (accept thresh . getBranchSupport . rootLabel) xs
+ lowSubForest = concatMap subForest lowS
diff --git a/src/ELynx/Data/Tree/Distance.hs b/src/ELynx/Data/Tree/Distance.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Data/Tree/Distance.hs
@@ -0,0 +1,124 @@
+{- |
+Module : ELynx.Data.Tree.Distance
+Description : Compute distances between trees
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Jun 13 17:15:54 2019.
+
+Various distance functions for phylogenetic trees (and binary trees in general).
+All trees are assumed to be UNROOTED.
+
+-}
+
+module ELynx.Data.Tree.Distance
+ ( symmetricDistance
+ , symmetricDistanceWith
+ , incompatibleSplitsDistance
+ , incompatibleSplitsDistanceWith
+ , computePairwiseDistances
+ , computeAdjacentDistances
+ , branchScoreDistance
+ , branchScoreDistanceWith
+ ) where
+
+import Data.List
+import qualified Data.Map as M
+import Data.Monoid
+import qualified Data.Set as S
+import Data.Tree
+
+import ELynx.Data.Tree.Bipartition
+import ELynx.Data.Tree.MeasurableTree
+import ELynx.Data.Tree.NamedTree
+
+-- -- Difference between two 'Set's, see 'Set.difference'. Do not compare elements
+-- -- directly but apply a function beforehand.
+-- differenceWith :: (Ord a, Ord b) => (a -> b) -> Set.Set a -> Set.Set a -> Set.Set a
+-- differenceWith f xs ys = Set.filter (\e -> f e `Set.notMember` ys') xs
+-- where ys' = Set.map f ys
+
+-- -- Symmetric difference between two 'Set's. Do not compare elements directly but
+-- -- apply a function beforehand.
+-- symmetricDifferenceWith :: (Ord a, Ord b) => (a -> b) -> Set.Set a -> Set.Set a -> Set.Set a
+-- symmetricDifferenceWith f xs ys = xsNotInYs `Set.union` ysNotInXs
+-- where
+-- xsNotInYs = differenceWith f xs ys
+-- ysNotInXs = differenceWith f ys xs
+
+-- Symmetric difference between two 'Set's.
+symmetricDifferenceS :: Ord a => S.Set a -> S.Set a -> S.Set a
+symmetricDifferenceS xs ys = S.difference xs ys `S.union` S.difference ys xs
+
+-- -- Symmetric difference between two 'Map's.
+-- symmetricDifferenceM :: Ord k => M.Map k a -> M.Map k a -> M.Map k a
+-- symmetricDifferenceM x y = M.difference x y `M.union` M.difference y x
+
+-- | Symmetric (Robinson-Foulds) distance between two trees. Before comparing
+-- the leaf labels, apply a given function. This is useful, for example, to
+-- compare the labels of 'Named' trees on their names only. The tree is assumed
+-- to be UNROOTED!
+--
+-- XXX: Comparing a list of trees with this function recomputes bipartitions.
+symmetricDistanceWith :: (Ord b) => (a -> b) -> Tree a -> Tree a -> Int
+symmetricDistanceWith f t1 t2 = length $ symmetricDifferenceS (bs t1) (bs t2)
+ where bs t = bipartitions $ fmap f t
+
+-- | See 'symmetricDistanceWith', but with 'id' for comparisons.
+symmetricDistance :: Ord a => Tree a -> Tree a -> Int
+symmetricDistance = symmetricDistanceWith id
+
+-- | Number of incompatible splits. Similar to 'symmetricDistanceWith' but
+-- merges multifurcations.
+--
+-- XXX: Comparing a list of trees with this function recomputes bipartitions.
+incompatibleSplitsDistanceWith :: (Ord b, Show b) => (a -> b) -> Tree a -> Tree a -> Int
+incompatibleSplitsDistanceWith f t1 t2 = length $ symmetricDifferenceS (ms t1) (ms t2)
+ where ms t = bipartitionsCombined $ fmap f t
+
+-- | See 'incompatibleSplitsDistanceWith', use 'id' for comparisons.
+incompatibleSplitsDistance :: (Ord a, Show a) => Tree a -> Tree a -> Int
+incompatibleSplitsDistance = incompatibleSplitsDistanceWith id
+
+-- | Compute branch score distance between two trees. Before comparing the leaf
+-- labels, apply a function. This is useful, for example, to compare the labels
+-- of 'Named' trees on their names only. The branch information which is
+-- compared to compute the distance is extracted from the nodes with a given
+-- function. Assumes that the trees are UNROOTED.
+--
+-- XXX: Comparing a list of trees with this function recomputes bipartitions.
+branchScoreDistanceWith :: (Ord a, Ord b, Floating c)
+ => (a -> b) -- ^ Label to compare on
+ -> (a -> c) -- ^ Branch information (e.g., length)
+ -- associated with a node
+ -> Tree a -> Tree a -> c
+branchScoreDistanceWith f g t1 t2 = sqrt dsSquared
+ where bs = bipartitionToBranch f (Sum . g)
+ dBs = M.map getSum $ M.unionWith (-) (bs t1) (bs t2)
+ dsSquared = foldl' (\acc e -> acc + e*e) 0 dBs
+
+-- | See 'branchScoreDistanceWith', use 'id' for comparisons.
+branchScoreDistance :: (Ord a, Measurable a, Named a) => Tree a -> Tree a -> Double
+branchScoreDistance = branchScoreDistanceWith getName getLen
+
+-- | Compute pairwise distances of a list of input trees. Use given distance
+-- measure. Returns a triple, the first two elements are the indices of the
+-- compared trees, the third is the distance.
+computePairwiseDistances :: (a -> a -> b) -- ^ Distance function
+ -> [a] -- ^ Input trees
+ -> [(Int, Int, b)] -- ^ (index i, index j, distance i j)
+computePairwiseDistances dist trs = [ (i, j, dist x y)
+ | (i:is, x:xs) <- zip (tails [0..]) (tails trs)
+ , (j, y) <- zip is xs ]
+
+-- | Compute distances between adjacent pairs of a list of input trees. Use
+-- given distance measure.
+computeAdjacentDistances :: (Tree a -> Tree a -> b) -- ^ Distance function
+ -> [Tree a] -- ^ Input trees
+ -> [b]
+computeAdjacentDistances dist trs = [ dist x y | (x, y) <- zip trs (tail trs) ]
+
diff --git a/src/ELynx/Data/Tree/EvoTree.hs b/src/ELynx/Data/Tree/EvoTree.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Data/Tree/EvoTree.hs
@@ -0,0 +1,43 @@
+{- |
+Module : ELynx.Data.Tree.EvoTree
+Description : Evolutionary nodes
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Jan 17 14:19:26 2019.
+
+XXX: This module is not used.
+
+-}
+
+module ELynx.Data.Tree.EvoTree
+ ( EvoLabel (..)
+ ) where
+
+-- | An evolutionary label has some information about where the corresponding
+-- node is on the tree, and if the node is 'extant', 'extinct', 'internal', or
+-- 'external'. The latter two could also be determined from the tree. This could
+-- be species, genes or individuals; probably more.
+class EvoLabel n where
+ extant :: n -> Bool
+ extinct :: n -> Bool
+
+ internal :: n -> Bool
+ internal n = not $ extant n || extinct n
+ external :: n -> Bool
+ external = not . internal
+
+-- -- | Glue branches together, so that one new tree emerges. It's root node is
+-- -- new, the sub-forest has to be given (a list of trees).
+-- glue :: (NodeType c)
+-- => PhyloLabel a b c -- ^ New root node.
+-- -> [PhyloTree a b c] -- ^ Sub-forest.
+-- -> PhyloTree a b c
+-- glue s@(PhyloLabel _ _ n) ts
+-- | extant n = error "Root node cannot be of type 'Exant'."
+-- | extinct n = error "Root node cannot be of type 'Extinct'."
+-- | otherwise = Node s ts
diff --git a/src/ELynx/Data/Tree/MeasurableTree.hs b/src/ELynx/Data/Tree/MeasurableTree.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Data/Tree/MeasurableTree.hs
@@ -0,0 +1,98 @@
+{- |
+Module : ELynx.Data.Tree.MeasurableTree
+Description : Functions on trees with branch lengths
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Jan 17 14:16:34 2019.
+
+-}
+
+
+module ELynx.Data.Tree.MeasurableTree
+ ( Measurable (..)
+ , distancesRootLeaves
+ , averageDistanceRootLeaves
+ , height
+ , lengthenRoot
+ , shortenRoot
+ , summarize
+ , totalBranchLength
+ , normalize
+ , prune
+ ) where
+
+import qualified Data.ByteString.Lazy.Char8 as L
+import Data.Foldable
+import Data.Tree
+
+import ELynx.Data.Tree.Tree
+
+-- | A 'Node' label with measurable and modifiable branch length to the parent.
+class Measurable a where
+ -- | Length of attached branch.
+ getLen :: a -> Double
+ -- | Set attached branch length.
+ setLen :: Double -> a -> a
+
+ -- | Elongate branch length.
+ lengthen :: Double -> a -> a
+ lengthen dl l = setLen (dl + getLen l) l
+
+ -- | Shorten branch length.
+ shorten :: Double -> a -> a
+ shorten dl = lengthen (-dl)
+
+-- | Distances from the root of a tree to its leaves.
+distancesRootLeaves :: (Measurable a) => Tree a -> [Double]
+distancesRootLeaves (Node l []) = [getLen l]
+distancesRootLeaves (Node l f ) = concatMap (map (+ getLen l) . distancesRootLeaves) f
+
+-- | Average distance from the root of a tree to its leaves.
+averageDistanceRootLeaves :: (Measurable a) => Tree a -> Double
+averageDistanceRootLeaves tr = sum ds / fromIntegral n
+ where ds = distancesRootLeaves tr
+ n = length ds
+
+-- | Height of a tree. Returns 0 if the tree is empty.
+height :: (Measurable a) => Tree a -> Double
+height = maximum . distancesRootLeaves
+
+-- | Lengthen the distance between root and origin.
+lengthenRoot :: (Measurable a) => Double -> Tree a -> Tree a
+lengthenRoot dl (Node lbl chs) = Node (lengthen dl lbl) chs
+
+-- | Lengthen the distance between root and origin.
+shortenRoot :: (Measurable a) => Double -> Tree a -> Tree a
+shortenRoot dl = lengthenRoot (-dl)
+
+-- | Summarize a tree with measureable branch lengths.
+summarize :: (Measurable a) => Tree a -> L.ByteString
+summarize t = L.unlines $ map L.pack
+ [ "Leaves: " ++ show n ++ "."
+ , "Height: " ++ show h ++ "."
+ , "Average distance root to leaves: " ++ show h' ++ "."
+ , "Total branch length: " ++ show b ++ "." ]
+ where n = length . leaves $ t
+ h = height t
+ b = totalBranchLength t
+ h' = sum (distancesRootLeaves t) / fromIntegral n
+
+-- | Total branch length of a tree.
+totalBranchLength :: (Measurable a) => Tree a -> Double
+totalBranchLength = foldl' (\acc n -> acc + getLen n) 0
+
+-- | Normalize tree so that sum of branch lengths is 1.0.
+normalize :: (Measurable a) => Tree a -> Tree a
+normalize t = fmap (\n -> setLen (getLen n / s) n) t
+ where s = totalBranchLength t
+
+-- | Prune degree 2 nodes. Add branch lengths but forget pruned node label. See
+-- 'pruneWith'.
+prune :: (Measurable a) => Tree a -> Tree a
+prune = pruneWith f
+ where f da pa = lengthen (getLen pa) da
diff --git a/src/ELynx/Data/Tree/NamedTree.hs b/src/ELynx/Data/Tree/NamedTree.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Data/Tree/NamedTree.hs
@@ -0,0 +1,23 @@
+{- |
+Module : ELynx.Data.Tree.NamedTree
+Description : Trees with named nodes
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Jan 24 20:09:20 2019.
+
+-}
+
+module ELynx.Data.Tree.NamedTree
+ ( Named (..)
+ ) where
+
+import qualified Data.ByteString.Lazy.Char8 as L
+
+-- | Data types with names.
+class Named a where
+ getName :: a -> L.ByteString
diff --git a/src/ELynx/Data/Tree/PhyloTree.hs b/src/ELynx/Data/Tree/PhyloTree.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Data/Tree/PhyloTree.hs
@@ -0,0 +1,89 @@
+{-# LANGUAGE FlexibleInstances #-}
+
+{- |
+Module : ELynx.Data.Tree.PhyloTree
+Description : Phylogenetic trees
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Jan 17 16:08:54 2019.
+
+Phylogenetic nodes have a branch length and a label.
+
+The easiest label type is 'Int': 'PhyloIntLabel'.
+
+Also, the 'L.ByteString' label is needed often: 'PhyloByteStringLabel'.
+
+XXX: This is all too complicated. Maybe I should just define a standard tree object like
+> data PhyloTree a = Tree (PhyloLabel a)
+and that's it. Forget about type classes like Measurable, Named and so on.
+
+-}
+
+
+module ELynx.Data.Tree.PhyloTree
+ ( PhyloLabel (..)
+ , PhyloIntLabel
+ , PhyloByteStringLabel
+ , removeBrLen
+ ) where
+
+import qualified Data.ByteString.Lazy.Builder as L
+import qualified Data.ByteString.Lazy.Char8 as L
+import Data.Function
+import Data.Tree
+import Test.QuickCheck
+
+import ELynx.Data.Tree.BranchSupportTree
+import ELynx.Data.Tree.MeasurableTree
+import ELynx.Data.Tree.NamedTree
+
+-- | A primitive label type for phylogenetic trees with a name, possibly a
+-- branch support value, and a 'Double' branch length.
+data PhyloLabel a = PhyloLabel { pLabel :: a
+ , pBrSup :: Maybe Double
+ , pBrLen :: Double }
+ deriving (Read, Show, Eq)
+
+instance Ord a => Ord (PhyloLabel a) where
+ compare = compare `on` pLabel
+
+instance Measurable (PhyloLabel a) where
+ getLen = pBrLen
+ setLen l (PhyloLabel lbl s _)
+ | l >= 0 = PhyloLabel lbl s l
+ | otherwise = error "Branch lengths cannot be negative."
+
+instance BranchSupportLabel (PhyloLabel a) where
+ getBranchSupport = pBrSup
+ setBranchSupport Nothing l = l {pBrSup = Nothing}
+ setBranchSupport (Just s) l
+ | s > 0 = l {pBrSup = Just s}
+ | otherwise = error "Branch support cannot be negative."
+
+instance Arbitrary a => Arbitrary (PhyloLabel a) where
+ arbitrary = PhyloLabel
+ <$> arbitrary
+ <*> (Just <$> choose (0, 100))
+ <*> choose (0, 10)
+
+-- | Tree node with 'Int' label.
+type PhyloIntLabel = PhyloLabel Int
+
+instance Named PhyloIntLabel where
+ getName = L.toLazyByteString . L.intDec . pLabel
+
+-- | Tree node with 'L.ByteString' label. Important for parsing
+-- 'ELynx.Import.Tree.Newick' files.
+type PhyloByteStringLabel = PhyloLabel L.ByteString
+
+instance Named PhyloByteStringLabel where
+ getName = pLabel
+
+-- | Remove branch lengths from tree.
+removeBrLen :: Tree (PhyloLabel a) -> Tree a
+removeBrLen = fmap pLabel
diff --git a/src/ELynx/Data/Tree/SumStat.hs b/src/ELynx/Data/Tree/SumStat.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Data/Tree/SumStat.hs
@@ -0,0 +1,57 @@
+{- |
+Module : ELynx.Data.Tree.SumStat
+Description : Summary statistics for phylogenetic trees
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu May 17 14:05:45 2018.
+
+-}
+
+module ELynx.Data.Tree.SumStat
+ ( BrLnNChildren
+ , NChildSumStat
+ , toNChildSumStat
+ , formatNChildSumStat
+ ) where
+
+import qualified Data.ByteString.Builder as L
+import qualified Data.ByteString.Lazy.Char8 as L
+import Data.Monoid ((<>))
+import Data.Tree
+import ELynx.Data.Tree.MeasurableTree
+
+-- This may be too specific, but I only change it if necessary. E.g., use types
+-- a (for node labels) and b (for branch lengths).
+
+-- | Pair of branch length with number of extant children.
+type BrLnNChildren = (Double, Int)
+
+-- | Possible summary statistic of phylogenetic trees. A list of tuples
+-- (BranchLength, NumberOfExtantChildrenBelowThisBranch).
+type NChildSumStat = [BrLnNChildren]
+
+-- | Format the summary statistics in the following form:
+-- @
+-- nLeaves1 branchLength1
+-- nLeaves2 branchLength2
+-- ....
+formatNChildSumStat :: NChildSumStat -> L.ByteString
+formatNChildSumStat s = L.toLazyByteString . mconcat $ map formatNChildSumStatLine s
+
+formatNChildSumStatLine :: BrLnNChildren -> L.Builder
+formatNChildSumStatLine (l, n) = L.intDec n
+ <> L.char8 ' '
+ <> L.doubleDec l
+ <> L.char8 '\n'
+
+-- | Compute NChilSumStat for a phylogenetic tree.
+toNChildSumStat :: Measurable a => Tree a -> NChildSumStat
+toNChildSumStat (Node lbl []) = [(getLen lbl, 1)]
+toNChildSumStat (Node lbl ts) = (getLen lbl, sumCh) : concat nChSS
+ where nChSS = map toNChildSumStat ts
+ sumCh = sum $ map (snd . head) nChSS
diff --git a/src/ELynx/Data/Tree/Tree.hs b/src/ELynx/Data/Tree/Tree.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Data/Tree/Tree.hs
@@ -0,0 +1,143 @@
+{- |
+Module : ELynx.Data.Tree.Tree
+Description : Functions related to phylogenetic trees
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Jan 17 09:57:29 2019.
+
+Comment about nomenclature:
+
+- In "Data.Tree", a 'Tree' is defined as
+
+@
+data Tree a = Node {
+ rootLabel :: a, -- ^ label value
+ subForest :: Forest a -- ^ zero or more child trees
+ }
+@
+
+This means, that the word 'Node' is reserved for the constructor of a tree, and
+that a 'Node' has a label and a children. The terms 'Node' and /label/ are not
+to be confused.
+
+- Branches have /lengths/. For example, a branch length can be a distances or a
+ time.
+
+NOTE: Trees in this library are all rooted. Unrooted trees can be treated with a
+rooted data structure equally well. However, in these cases, some functions have
+no meaning. For example, functions measuring the distance from the root to the
+leaves (the height of a rooted tree).
+
+NOTE: Try fgl or alga. Use functional graph library for unrooted trees see also
+the book /Haskell high performance programming from Thomasson/, p. 344.
+
+-}
+
+
+module ELynx.Data.Tree.Tree
+ ( singleton
+ , degree
+ , leaves
+ , subTree
+ , subSample
+ , nSubSamples
+ , pruneWith
+ , merge
+ , tZipWith
+ ) where
+
+import Control.Monad
+import Control.Monad.Primitive
+import Data.Maybe
+import qualified Data.Sequence as Seq
+import qualified Data.Set as Set
+import Data.Traversable
+import Data.Tree
+import System.Random.MWC
+
+import ELynx.Tools.Random
+
+-- | The simplest tree. Usually an extant leaf.
+singleton :: a -> Tree a
+singleton l = Node l []
+
+-- | The degree of the root node of a tree.
+degree :: Tree a -> Int
+degree = (+ 1) . length . subForest
+
+-- | Get leaves of tree.
+leaves :: Tree a -> [a]
+leaves (Node l []) = [l]
+leaves (Node _ f) = concatMap leaves f
+
+-- -- | Check if ancestor and daughters of first tree are a subset of the ancestor
+-- -- and daughters of the second tree. Useful to test if, e.g., speciations agree.
+-- rootNodesAgreeWith :: (Ord c) => (a -> c) -> Tree a -> (b -> c) -> Tree b -> Bool
+-- rootNodesAgreeWith f s g t =
+-- f (rootLabel s) == g (rootLabel t) &&
+-- S.fromList sDs `S.isSubsetOf` S.fromList tDs
+-- where sDs = map (f . rootLabel) (subForest s)
+-- tDs = map (g . rootLabel) (subForest t)
+
+-- | Get subtree of 'Tree' with nodes satisfying predicate. Return 'Nothing', if
+-- no leaf satisfies predicate. At the moment: recursively, for each child, take
+-- the child if any leaf in the child satisfies the predicate.
+subTree :: (a -> Bool) -> Tree a -> Maybe (Tree a)
+subTree p leaf@(Node lbl [])
+ | p lbl = Just leaf
+ | otherwise = Nothing
+subTree p (Node lbl chs) = if null subTrees
+ then Nothing
+ else Just $ Node lbl subTrees
+ where subTrees = mapMaybe (subTree p) chs
+
+-- XXX: If module gets too big, move the sampling functions into their own
+-- module.
+-- | Extract a random sub tree with N leaves of a tree with M leaves, where M>N
+-- (otherwise error). The complete list of leaves (names are assumed to be
+-- unique) has to be provided as a 'Seq.Seq', and a 'Seq.Set', so that we have
+-- fast sub-sampling as well as lookup and don't have to recompute them when
+-- many sub-samples are requested.
+subSample :: (PrimMonad m, Ord a)
+ => Seq.Seq a -> Int -> Tree a -> Gen (PrimState m) -> m (Maybe (Tree a))
+subSample lvs n tree g
+ | Seq.length lvs < n = error "Given list of leaves is shorter than requested number of leaves."
+ | otherwise = do
+ sampledLs <- sample lvs n g
+ let ls = Set.fromList sampledLs
+ return $ subTree (`Set.member` ls) tree
+
+-- | See 'subSample', but n times.
+nSubSamples :: (PrimMonad m, Ord a)
+ => Int -> Seq.Seq a -> Int -> Tree a -> Gen (PrimState m) -> m [Maybe (Tree a)]
+nSubSamples nS lvs nL tree g = replicateM nS $ subSample lvs nL tree g
+
+-- | Prune degree 2 inner nodes. The information stored in a pruned node can be
+-- used to change the daughter node. To discard this information, use,
+-- @pruneWith const tree@, otherwise @pruneWith (\daughter parent -> combined)
+-- tree@.
+pruneWith :: (a -> a -> a) -> Tree a -> Tree a
+pruneWith _ n@(Node _ []) = n
+pruneWith f (Node paLbl [ch]) = let lbl = f (rootLabel ch) paLbl
+ in pruneWith f $ Node lbl (subForest ch)
+pruneWith f (Node paLbl chs) = Node paLbl (map (pruneWith f) chs)
+
+-- | Merge two trees with the same topology. Returns 'Nothing' if the topologies are different.
+merge :: Tree a -> Tree b -> Maybe (Tree (a, b))
+merge (Node l xs) (Node r ys) =
+ if length xs == length ys
+ -- I am proud of that :)).
+ then zipWithM merge xs ys >>= Just . Node (l, r)
+ else Nothing
+
+-- | Apply a function with different effect on each node to a 'Traversable'.
+-- Based on https://stackoverflow.com/a/41523456.
+tZipWith :: Traversable t => (a -> b -> c) -> [a] -> t b -> Maybe (t c)
+tZipWith f xs = sequenceA . snd . mapAccumL pair xs
+ where pair [] _ = ([], Nothing)
+ pair (y:ys) z = (ys, Just (f y z))
diff --git a/src/ELynx/Distribution/BirthDeath.hs b/src/ELynx/Distribution/BirthDeath.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Distribution/BirthDeath.hs
@@ -0,0 +1,84 @@
+{-# LANGUAGE DeriveDataTypeable #-}
+{-# LANGUAGE DeriveGeneric #-}
+
+{- |
+ Module : ELynx.Distribution.BirthDeath
+ Description : Birth and death distribution
+ Copyright : (c) Dominik Schrempf 2018
+ License : GPL-3
+
+ Maintainer : dominik.schrempf@gmail.com
+ Stability : unstable
+ Portability : portable
+
+Creation date: Tue Feb 13 13:16:18 2018.
+
+See Gernhard, T. (2008). The conditioned reconstructed process. Journal of
+Theoretical Biology, 253(4), 769–778. http://doi.org/10.1016/j.jtbi.2008.04.005.
+
+Distribution of the values of the point process such that it corresponds to
+reconstructed trees under the birth and death process.
+
+-}
+
+module ELynx.Distribution.BirthDeath
+ ( BirthDeathDistribution(..)
+ , cumulative
+ , density
+ , quantile
+ ) where
+
+import Data.Data (Data, Typeable)
+import GHC.Generics (Generic)
+import qualified Statistics.Distribution as D
+
+import ELynx.Distribution.Types
+
+-- | Distribution of the values of the point process such that it corresponds to
+-- a reconstructed tree of the birth and death process.
+data BirthDeathDistribution = BDD
+ { bddTOr :: Time -- ^ Time to origin of the tree.
+ , bddLa :: Rate -- ^ Birth rate.
+ , bddMu :: Rate -- ^ Death rate.
+ } deriving (Eq, Typeable, Data, Generic)
+
+instance D.Distribution BirthDeathDistribution where
+ cumulative = cumulative
+
+-- | Cumulative distribution function Eq. (3).
+cumulative :: BirthDeathDistribution -> Time -> Double
+cumulative (BDD t l m) x
+ | x <= 0 = 0
+ | x > t = 1
+ | otherwise = t1 * t2
+ where d = l - m
+ t1 = (1.0 - exp (-d*x)) / (l - m*exp(-d*x))
+ t2 = (l - m*exp(-d*t)) / (1.0 - exp(-d*t))
+
+instance D.ContDistr BirthDeathDistribution where
+ density = density
+ quantile = quantile
+
+-- | Density function Eq. (2).
+density :: BirthDeathDistribution -> Time -> Double
+density (BDD t l m) x
+ | x < 0 = 0
+ | x > t = 0
+ | otherwise = d**2 * t1 * t2
+ where d = l - m
+ t1 = exp (-d*x) / ((l - m*exp(-d*x))**2)
+ t2 = (l - m*exp(-d*t)) / (1.0 - exp(-d*t))
+
+-- | Inverted cumulative probability distribution 'cumulative'. See also
+-- 'D.ContDistr'.
+quantile :: BirthDeathDistribution -> Double -> Time
+quantile (BDD t l m) p
+ | p >= 0 && p <= 1 = res
+ | otherwise =
+ error $ "PointProcess.quantile: p must be in [0,1] range. Got: " ++ show p ++ "."
+ where d = l - m
+ t2 = (l - m*exp(-d*t)) / (1.0 - exp(-d*t))
+ res = (-1.0/d) * log ((1.0 - p*l/t2)/(1.0 - p*m/t2))
+
+instance D.ContGen BirthDeathDistribution where
+ genContVar = D.genContinuous
diff --git a/src/ELynx/Distribution/BirthDeathCritical.hs b/src/ELynx/Distribution/BirthDeathCritical.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Distribution/BirthDeathCritical.hs
@@ -0,0 +1,76 @@
+{-# LANGUAGE DeriveDataTypeable #-}
+{-# LANGUAGE DeriveGeneric #-}
+
+{- |
+ Module : ELynx.Distribution.BirthDeathCritical
+ Description : Birth and death distribution
+ Copyright : (c) Dominik Schrempf 2018
+ License : GPL-3
+
+ Maintainer : dominik.schrempf@gmail.com
+ Stability : unstable
+ Portability : portable
+
+Creation date: Tue Feb 13 13:16:18 2018.
+
+See Gernhard, T. (2008). The conditioned reconstructed process. Journal of
+Theoretical Biology, 253(4), 769–778. http://doi.org/10.1016/j.jtbi.2008.04.005.
+
+Distribution of the values of the point process such that it corresponds to
+reconstructed trees under the birth and death process; critical birth and death
+process with lambda=mu.
+
+-}
+
+module ELynx.Distribution.BirthDeathCritical
+ ( BirthDeathCriticalDistribution(..)
+ , cumulative
+ , density
+ , quantile
+ ) where
+
+import Data.Data (Data, Typeable)
+import GHC.Generics (Generic)
+import qualified Statistics.Distribution as D
+
+import ELynx.Distribution.Types
+
+-- | Distribution of the values of the point process such that it corresponds to
+-- a reconstructed tree of the birth and death process.
+data BirthDeathCriticalDistribution = BDCD
+ { bdcdTOr :: Time -- ^ Time to origin of the tree.
+ , bdcdLa :: Rate -- ^ Birth and death rate.
+ } deriving (Eq, Typeable, Data, Generic)
+
+instance D.Distribution BirthDeathCriticalDistribution where
+ cumulative = cumulative
+
+-- | Cumulative distribution function section 2.1.2, second formula.
+cumulative :: BirthDeathCriticalDistribution -> Time -> Double
+cumulative (BDCD t l) x
+ | x <= 0 = 0
+ | x > t = 1
+ | otherwise = x / (1.0 + l * x) * (1.0 + l * t) / t
+
+instance D.ContDistr BirthDeathCriticalDistribution where
+ density = density
+ quantile = quantile
+
+-- | Density function section 2.1.2, first formula.
+density :: BirthDeathCriticalDistribution -> Time -> Double
+density (BDCD t l) x
+ | x < 0 = 0
+ | x > t = 0
+ | otherwise = (1.0 + l * t) / (t * (1.0 + l * x)**2)
+
+-- | Inverted cumulative probability distribution 'cumulative'. See also
+-- 'D.ContDistr'.
+quantile :: BirthDeathCriticalDistribution -> Double -> Time
+quantile (BDCD t l) p
+ | p >= 0 && p <= 1 = res
+ | otherwise =
+ error $ "PointProcess.quantile: p must be in [0,1] range. Got: " ++ show p ++ "."
+ where res = p * t / (1 + l*t - l*p*t)
+
+instance D.ContGen BirthDeathCriticalDistribution where
+ genContVar = D.genContinuous
diff --git a/src/ELynx/Distribution/BirthDeathCriticalNoTime.hs b/src/ELynx/Distribution/BirthDeathCriticalNoTime.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Distribution/BirthDeathCriticalNoTime.hs
@@ -0,0 +1,73 @@
+{-# LANGUAGE DeriveDataTypeable #-}
+{-# LANGUAGE DeriveGeneric #-}
+
+{- |
+ Module : ELynx.Distribution.BirthDeathCriticalNoTime
+ Description : Birth and death distribution
+ Copyright : (c) Dominik Schrempf 2018
+ License : GPL-3
+
+ Maintainer : dominik.schrempf@gmail.com
+ Stability : unstable
+ Portability : portable
+
+Creation date: Tue Feb 13 13:16:18 2018.
+
+See Gernhard, T. (2008). The conditioned reconstructed process. Journal of
+Theoretical Biology, 253(4), 769–778. http://doi.org/10.1016/j.jtbi.2008.04.005.
+
+Distribution of the values of the point process such that it corresponds to
+reconstructed trees under the birth and death process; critical birth and death
+process with lambda=mu.
+
+-}
+
+module ELynx.Distribution.BirthDeathCriticalNoTime
+ ( BirthDeathCriticalNoTimeDistribution(..)
+ , cumulative
+ , density
+ , quantile
+ ) where
+
+import Data.Data (Data, Typeable)
+import GHC.Generics (Generic)
+import qualified Statistics.Distribution as D
+
+import ELynx.Distribution.Types
+
+-- | Distribution of the values of the point process such that it corresponds to
+-- a reconstructed tree of the birth and death process.
+newtype BirthDeathCriticalNoTimeDistribution = BDCNTD
+ { bdcntdLa :: Rate -- ^ Birth and death rate.
+ } deriving (Eq, Typeable, Data, Generic)
+
+instance D.Distribution BirthDeathCriticalNoTimeDistribution where
+ cumulative = cumulative
+
+-- | Cumulative distribution function section 2.1.2, second formula.
+cumulative :: BirthDeathCriticalNoTimeDistribution -> Time -> Double
+cumulative (BDCNTD l) x
+ | x <= 0 = 0
+ | otherwise = x * l / (1.0 + x * l)
+
+instance D.ContDistr BirthDeathCriticalNoTimeDistribution where
+ density = density
+ quantile = quantile
+
+-- | Density function section 2.1.2, first formula; t cancels out because it is
+-- expected to be much larger than 1.0; because t \in [0, \infty].
+density :: BirthDeathCriticalNoTimeDistribution -> Time -> Double
+density (BDCNTD l) x
+ | x < 0 = 0
+ | otherwise = l / ((1.0 + x * l)**2)
+
+-- | Inverted cumulative probability distribution 'cumulative'. See also
+-- 'D.ContDistr'.
+quantile :: BirthDeathCriticalNoTimeDistribution -> Double -> Time
+quantile (BDCNTD l) p
+ | p >= 0 && p <= 1 = p / (l - l*p)
+ | otherwise =
+ error $ "PointProcess.quantile: p must be in [0,1]. Got: " ++ show p ++ "."
+
+instance D.ContGen BirthDeathCriticalNoTimeDistribution where
+ genContVar = D.genContinuous
diff --git a/src/ELynx/Distribution/BirthDeathNearlyCritical.hs b/src/ELynx/Distribution/BirthDeathNearlyCritical.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Distribution/BirthDeathNearlyCritical.hs
@@ -0,0 +1,89 @@
+{-# LANGUAGE DeriveDataTypeable #-}
+{-# LANGUAGE DeriveGeneric #-}
+
+{- |
+ Module : ELynx.Distribution.BirthDeathNearlyCritical
+ Description : Birth and death distribution
+ Copyright : (c) Dominik Schrempf 2018
+ License : GPL-3
+
+ Maintainer : dominik.schrempf@gmail.com
+ Stability : unstable
+ Portability : portable
+
+Creation date: Tue Feb 13 13:16:18 2018.
+
+See Gernhard, T. (2008). The conditioned reconstructed process. Journal of
+Theoretical Biology, 253(4), 769–778. http://doi.org/10.1016/j.jtbi.2008.04.005.
+
+Distribution of the values of the point process such that it corresponds to
+reconstructed trees under the birth and death process; nearly critical birth and
+death process with lambda~mu.
+
+Basically, this is a Taylor expansion of Eq. (2) and Eq. (3).
+
+-}
+
+module ELynx.Distribution.BirthDeathNearlyCritical
+ ( BirthDeathNearlyCriticalDistribution(..)
+ , cumulative
+ , density
+ , quantile
+ ) where
+
+import Data.Data (Data, Typeable)
+import GHC.Generics (Generic)
+import qualified Statistics.Distribution as D
+
+import ELynx.Distribution.Types
+
+-- | Distribution of the values of the point process such that it corresponds to
+-- a reconstructed tree of the birth and death process.
+data BirthDeathNearlyCriticalDistribution = BDNCD
+ { bdncdTOr :: Time -- ^ Time to origin of the tree.
+ , bdncdLa :: Rate -- ^ Birth and death rate.
+ , bdncdMu :: Rate -- ^ Birth and death rate.
+ } deriving (Eq, Typeable, Data, Generic)
+
+instance D.Distribution BirthDeathNearlyCriticalDistribution where
+ cumulative = cumulative
+
+-- | Cumulative distribution function section 2.1.2, second formula.
+cumulative :: BirthDeathNearlyCriticalDistribution -> Time -> Double
+cumulative (BDNCD t l m) s
+ | s <= 0 = 0
+ | s > t = 1
+ | otherwise = o0 + o1
+ where o0 = s * (1.0 + t*l) / t / (1.0 + s*l)
+ o1 = (-s*s + s*t) * (m - l) / (2.0*t * (1.0 + s*l)**2)
+
+instance D.ContDistr BirthDeathNearlyCriticalDistribution where
+ density = density
+ quantile = quantile
+
+-- | Density function section 2.1.2, first formula.
+density :: BirthDeathNearlyCriticalDistribution -> Time -> Double
+density (BDNCD t l m) s
+ | s < 0 = 0
+ | s > t = 0
+ | otherwise = o0 + o1
+ where
+ o0 = (1.0 + t*l) / (t * (1.0 + s*l)**2)
+ o1 = (-2.0*s + t - s*t*l) * (m - l) / (2.0*t * (1.0 + s*l)**3)
+
+-- | Inverted cumulative probability distribution 'cumulative'. See also
+-- 'D.ContDistr'.
+quantile :: BirthDeathNearlyCriticalDistribution -> Double -> Time
+quantile (BDNCD t l m) p
+ | p >= 0 && p <= 1 = res
+ | otherwise =
+ error $ "PointProcess.quantile: p must be in [0,1] range. Got: " ++ show p ++ "."
+ where
+ den = l*(-3.0 + 2.0*t*(-1.0+p)*l)+m
+ t1 = (2.0 + t*(l - 4.0*p*l + m)) / den
+ t2Nom = 4.0 + t*(l*(4.0 + t*l + 8.0*p*(1.0 + t*l)) + 2.0*(2.0 + t*l - 4.0*p*(1.0 + t*l))*m + t*m*m)
+ t2 = t2Nom / (den**2)
+ res = 0.5 * (t1 + sqrt t2)
+
+instance D.ContGen BirthDeathNearlyCriticalDistribution where
+ genContVar = D.genContinuous
diff --git a/src/ELynx/Distribution/CoalescentContinuous.hs b/src/ELynx/Distribution/CoalescentContinuous.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Distribution/CoalescentContinuous.hs
@@ -0,0 +1,26 @@
+{- |
+Module : ELynx.Distribution.CoalescentContinuous
+Description : Distribution of coalescent times
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Wed May 16 12:40:45 2018.
+
+-}
+
+module ELynx.Distribution.CoalescentContinuous
+ ( coalescentDistributionCont
+ ) where
+
+import Numeric.SpecFunctions (choose)
+import Statistics.Distribution.Exponential
+
+-- | Distribution of the next coalescent event for a number of samples @n@. The
+-- time is measured in units of effective number of population size.
+coalescentDistributionCont :: Int -- ^ Sample size.
+ -> ExponentialDistribution
+coalescentDistributionCont n = exponential (choose n 2)
diff --git a/src/ELynx/Distribution/TimeOfOrigin.hs b/src/ELynx/Distribution/TimeOfOrigin.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Distribution/TimeOfOrigin.hs
@@ -0,0 +1,84 @@
+{-# LANGUAGE DeriveDataTypeable #-}
+{-# LANGUAGE DeriveGeneric #-}
+
+{- |
+ Module : ELynx.Distribution.TimeOfOrigin
+ Description : Distribution of time of origin for birth and death trees
+ Copyright : (c) Dominik Schrempf 2018
+ License : GPL-3
+
+ Maintainer : dominik.schrempf@gmail.com
+ Stability : unstable
+ Portability : portable
+
+Creation date: Tue Feb 13 13:16:18 2018.
+
+See Gernhard, T. (2008). The conditioned reconstructed process. Journal of
+Theoretical Biology, 253(4), 769–778. http://doi.org/10.1016/j.jtbi.2008.04.005.
+
+Distribution of the time of origin for birth and death trees. See corollary 3.3
+in the paper cited above.
+
+-}
+
+module ELynx.Distribution.TimeOfOrigin
+ ( TimeOfOriginDistribution(..)
+ , cumulative
+ , density
+ , quantile
+ ) where
+
+import Data.Data (Data, Typeable)
+import GHC.Generics (Generic)
+import qualified Statistics.Distribution as D
+
+import ELynx.Distribution.Types
+
+-- | Distribution of the time of origin for a phylogenetic tree evolving under
+-- the birth and death process and conditioned on observing n leaves today.
+data TimeOfOriginDistribution = TOD
+ { todTN :: Int -- ^ Number of leaves of the tree.
+ , todLa :: Rate -- ^ Birth rate.
+ , todMu :: Rate -- ^ Death rate.
+ } deriving (Eq, Typeable, Data, Generic)
+
+instance D.Distribution TimeOfOriginDistribution where
+ cumulative = cumulative
+
+-- | Cumulative distribution function Corollary 3.3.
+cumulative :: TimeOfOriginDistribution -> Time -> Double
+cumulative (TOD n l m) x
+ | x <= 0 = 0
+ | otherwise = te ** fromIntegral n
+ where d = l - m
+ te = l * (1.0 - exp (-d*x)) / (l - m*exp(-d*x))
+
+instance D.ContDistr TimeOfOriginDistribution where
+ density = density
+ quantile = quantile
+
+-- | The density function Eq. (5).
+density :: TimeOfOriginDistribution -> Time -> Double
+density (TOD nn l m) x
+ | x < 0 = 0
+ | otherwise = n * l**n * d**2 * t1**(n-1.0) * ex / (t2**(n+1.0))
+ where d = l - m
+ n = fromIntegral nn
+ ex = exp(-d*x)
+ t1 = 1.0 - ex
+ t2 = l - m*ex
+
+-- | The inverted cumulative probability distribution 'cumulative'. See also
+-- 'D.ContDistr'.
+quantile :: TimeOfOriginDistribution -> Double -> Time
+quantile (TOD n' l m) p
+ | p >= 0 && p <= 1 = -1.0/d * log(t1/t2)
+ | otherwise =
+ error $ "PointProcess.quantile: p must be in [0,1] range. Got: " ++ show p ++ "."
+ where d = l - m
+ n = fromIntegral n'
+ t1 = l*(1.0-p**(1.0/n))
+ t2 = l - p**(1.0/n)*m
+
+instance D.ContGen TimeOfOriginDistribution where
+ genContVar = D.genContinuous
diff --git a/src/ELynx/Distribution/TimeOfOriginNearCritical.hs b/src/ELynx/Distribution/TimeOfOriginNearCritical.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Distribution/TimeOfOriginNearCritical.hs
@@ -0,0 +1,84 @@
+{-# LANGUAGE DeriveDataTypeable #-}
+{-# LANGUAGE DeriveGeneric #-}
+
+{- |
+ Module : ELynx.Distribution.TimeOfOriginNearCritical
+ Description : Distribution of time of origin for birth and death trees
+ Copyright : (c) Dominik Schrempf 2018
+ License : GPL-3
+
+ Maintainer : dominik.schrempf@gmail.com
+ Stability : unstable
+ Portability : portable
+
+Creation date: Tue Feb 13 13:16:18 2018.
+
+See Gernhard, T. (2008). The conditioned reconstructed process. Journal of
+Theoretical Biology, 253(4), 769–778. http://doi.org/10.1016/j.jtbi.2008.04.005.
+
+Distribution of the time of origin for birth and death trees. See corollary 3.3
+in the paper cited above.
+
+-}
+
+module ELynx.Distribution.TimeOfOriginNearCritical
+ ( TimeOfOriginNearCriticalDistribution(..)
+ , cumulative
+ , density
+ , quantile
+ ) where
+
+import Data.Data (Data, Typeable)
+import GHC.Generics (Generic)
+import qualified Statistics.Distribution as D
+
+import ELynx.Distribution.Types
+
+-- | Distribution of the time of origin for a phylogenetic tree evolving under
+-- the birth and death process and conditioned on observing n leaves today.
+data TimeOfOriginNearCriticalDistribution = TONCD
+ { todTN :: Int -- ^ Number of leaves of the tree.
+ , todLa :: Rate -- ^ Birth rate.
+ , todMu :: Rate -- ^ Death rate.
+ } deriving (Eq, Typeable, Data, Generic)
+
+instance D.Distribution TimeOfOriginNearCriticalDistribution where
+ cumulative = cumulative
+
+-- | Cumulative distribution function; see Mathematica notebook.
+cumulative :: TimeOfOriginNearCriticalDistribution -> Time -> Double
+cumulative (TONCD n' l m) t
+ | t <= 0 = 0
+ | otherwise = t1 + t2
+ where d = l - m
+ n = fromIntegral n'
+ t1 = (t*l/(1.0 + t*l)) ** n
+ t2 = (n * t * t1) * d / (2.0 * (1.0 + t*l))
+
+instance D.ContDistr TimeOfOriginNearCriticalDistribution where
+ density = density
+ quantile = quantile
+
+-- | The density function Eq. (5).
+density :: TimeOfOriginNearCriticalDistribution -> Time -> Double
+density (TONCD n' l m) t
+ | t < 0 = 0
+ | otherwise = nom/den
+ where n = fromIntegral n'
+ nom = n * (t*l/(1+t*l))**n * (2+(3+n)*t*l - (1+n)*t*m)
+ den = 2*t*(1+t*l)**2
+
+-- | The inverted cumulative probability distribution 'cumulative'. See also
+-- 'D.ContDistr'.
+quantile :: TimeOfOriginNearCriticalDistribution -> Double -> Time
+quantile (TONCD n' l m) p
+ | p >= 0 && p <= 1 = t1 + t2nom/t2den
+ | otherwise =
+ error $ "PointProcess.quantile: p must be in [0,1] range. Got: " ++ show p ++ "."
+ where n = fromIntegral n'
+ t1 = - p**(1/n)/((-1+p**(1/n))*l)
+ t2nom = p**(2/n)*(m-l)
+ t2den = 2*(-1+p**(1/n))**2 * l**2
+
+instance D.ContGen TimeOfOriginNearCriticalDistribution where
+ genContVar = D.genContinuous
diff --git a/src/ELynx/Distribution/Types.hs b/src/ELynx/Distribution/Types.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Distribution/Types.hs
@@ -0,0 +1,27 @@
+{- |
+Module : ELynx.Distribution.Types
+Description : Data types for distributions on trees
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Wed May 16 12:21:57 2018.
+
+-}
+
+
+module ELynx.Distribution.Types
+ ( Time
+ , Rate
+ ) where
+
+-- | Branch lengths are measured in time.
+type Time = Double
+
+-- | Birth or death rates.
+type Rate = Double
+
+
diff --git a/src/ELynx/Export/Tree/Newick.hs b/src/ELynx/Export/Tree/Newick.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Export/Tree/Newick.hs
@@ -0,0 +1,62 @@
+{- |
+Module : ELynx.Export.Tree.Newick
+Description : Export tree objects to Newick format
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Jan 17 13:51:47 2019.
+
+Parts of the code are from https://hackage.haskell.org/package/BiobaseNewick.
+
+See nomenclature in 'ELynx.Data.Tree.Tree'.
+
+-}
+
+module ELynx.Export.Tree.Newick
+ ( toNewick
+ -- , toNewickPhyloIntTree
+ -- , toNewickPhyloByteStringTree
+ ) where
+
+import qualified Data.ByteString.Lazy.Builder as L
+import qualified Data.ByteString.Lazy.Char8 as L
+import Data.List (intersperse)
+-- import Data.Maybe
+import Data.Tree
+
+import ELynx.Data.Tree.BranchSupportTree
+import ELynx.Data.Tree.MeasurableTree
+import ELynx.Data.Tree.NamedTree
+-- import ELynx.Data.Tree.PhyloTree
+import ELynx.Tools.ByteString (c2w)
+
+-- | General conversion of a tree into a Newick 'L.Bytestring'. Use provided
+-- functions to extract node labels and branch lengths builder objects. See also
+-- Biobase.Newick.Export.
+toNewick :: (Named a, Measurable a, BranchSupportLabel a) => Tree a -> L.ByteString
+toNewick t =
+ L.toLazyByteString $ go t <> L.word8 (c2w ';')
+ where
+ go (Node l []) = lbl l
+ go (Node l ts) = L.word8 (c2w '(')
+ <> mconcat (intersperse (L.word8 $ c2w ',') $ map go ts)
+ <> L.word8 (c2w ')') <> brSup l
+ <> lbl l
+ lbl l = L.lazyByteString (getName l)
+ <> L.word8 (c2w ':')
+ <> L.doubleDec (getLen l)
+ brSup l = maybe mempty L.doubleDec (getBranchSupport l)
+
+-- -- | Convenience function for exporting trees with 'Int' labels and 'Double'
+-- -- branch lengths.
+-- toNewickPhyloIntTree :: Tree PhyloIntLabel -> L.ByteString
+-- toNewickPhyloIntTree = toNewickWith (L.intDec . pLabel) (L.doubleDec . pBrLen)
+
+-- -- | Convenience function for exporting trees with 'L.ByteString' labels and
+-- -- 'Double' branch lengths.
+-- toNewickPhyloByteStringTree :: Tree PhyloByteStringLabel -> L.ByteString
+-- toNewickPhyloByteStringTree = toNewickWith (L.lazyByteString . pLabel) (L.doubleDec . pBrLen)
diff --git a/src/ELynx/Import/Tree/Newick.hs b/src/ELynx/Import/Tree/Newick.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Import/Tree/Newick.hs
@@ -0,0 +1,110 @@
+{- |
+Module : ELynx.Import.Tree.Newick
+Description : Import Newick trees
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Jan 17 14:56:27 2019.
+
+Code partly taken from Biobase.Newick.Import.
+
+[Specifications](http://evolution.genetics.washington.edu/phylip/newicktree.html)
+
+- In particular, no conversion from _ to (space) is done right now.
+
+-}
+
+
+module ELynx.Import.Tree.Newick
+ ( Parser
+ , newick
+ , manyNewick
+ , forest
+ , leaf
+ , node
+ , name
+ , branchLength
+ ) where
+
+import qualified Data.ByteString.Lazy as L
+import Data.Tree
+import Data.Void
+import Data.Word
+import Text.Megaparsec
+import Text.Megaparsec.Byte
+import Text.Megaparsec.Byte.Lexer (decimal, float)
+
+import ELynx.Data.Tree.PhyloTree
+import ELynx.Tools.ByteString (c2w)
+
+-- | Shortcut.
+type Parser = Parsec Void L.ByteString
+
+-- | Parse many Newick trees.
+manyNewick :: Parser [Tree PhyloByteStringLabel]
+manyNewick = some (newick <* space) <* eof "manyNewick"
+
+-- | Parse a Newick tree.
+newick :: Parser (Tree PhyloByteStringLabel)
+newick = tree <* char (c2w ';') "newick"
+
+tree :: Parser (Tree PhyloByteStringLabel)
+tree = space *> (branched <|> leaf) "tree"
+
+branched :: Parser (Tree PhyloByteStringLabel)
+branched = do
+ f <- forest
+ s <- branchSupport
+ n <- node
+ "branched"
+ let n' = n {pBrSup = s}
+ return $ Node n' f
+
+-- | A 'forest' is a set of trees separated by @,@ and enclosed by parentheses.
+forest :: Parser [Tree PhyloByteStringLabel]
+forest = do
+ _ <- char (c2w '(')
+ f <- tree `sepBy1` char (c2w ',')
+ _ <- char (c2w ')')
+ "forest"
+ return f
+
+branchSupport :: Parser (Maybe Double)
+branchSupport = optional $ try float <|> try decimalAsDouble
+
+-- | A 'leaf' is a 'node' without children.
+leaf :: Parser (Tree PhyloByteStringLabel)
+leaf = do
+ n <- node
+ "leaf"
+ return $ Node n []
+
+-- | A 'node' has a name and a 'branchLength'.
+node :: Parser PhyloByteStringLabel
+node = do
+ n <- name
+ b <- branchLength
+ "node"
+ return $ PhyloLabel n Nothing b
+
+checkNameCharacter :: Word8 -> Bool
+checkNameCharacter c = c `notElem` map c2w " :;()[],"
+
+-- | A name can be any string of printable characters except blanks, colons,
+-- semicolons, parentheses, and square brackets (and commas).
+name :: Parser L.ByteString
+name = L.pack <$> many (satisfy checkNameCharacter) "name"
+
+-- | Branch lengths default to 0.
+branchLength :: Parser Double
+branchLength = char (c2w ':') *> branchLengthGiven <|> pure 0 "branchLength"
+
+branchLengthGiven :: Parser Double
+branchLengthGiven = try float <|> decimalAsDouble
+
+decimalAsDouble :: Parser Double
+decimalAsDouble = fromIntegral <$> (decimal :: Parser Int)
diff --git a/src/ELynx/Simulate/Coalescent.hs b/src/ELynx/Simulate/Coalescent.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Simulate/Coalescent.hs
@@ -0,0 +1,62 @@
+{- |
+Module : ELynx.Simulate.Coalescent
+Description : Generate coalescent trees
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Wed May 16 13:13:11 2018.
+
+-}
+
+
+module ELynx.Simulate.Coalescent
+ ( simulate
+ ) where
+
+import Control.Monad.Primitive
+import Data.Tree
+import Statistics.Distribution
+import System.Random.MWC
+
+import ELynx.Data.Tree.MeasurableTree
+import ELynx.Data.Tree.PhyloTree
+import ELynx.Data.Tree.Tree
+import ELynx.Distribution.CoalescentContinuous
+
+-- | Simulate a coalescent tree with @n@ leaves. The branch lengths are in units
+-- of effective population size.
+simulate :: (PrimMonad m)
+ => Int -- ^ Number of leaves.
+ -> Gen (PrimState m)
+ -> m (Tree PhyloIntLabel)
+simulate n = simulate' n 0 trs
+ where trs = [ singleton (PhyloLabel i Nothing 0.0) | i <- [0..n-1] ]
+
+simulate' :: (PrimMonad m)
+ => Int
+ -> Int
+ -> [Tree PhyloIntLabel]
+ -> Gen (PrimState m)
+ -> m (Tree PhyloIntLabel)
+simulate' n a trs g
+ | n <= 0 = error "Cannot construct trees without leaves."
+ | n == 1 && length trs /= 1 = error "Too many trees provided."
+ | n == 1 && length trs == 1 = return $ head trs
+ | otherwise =
+ do
+ -- Indices of the leaves to join will be i-1 and i.
+ i <- uniformR (1, n-1) g
+ -- The time of the coalescent event.
+ t <- genContVar (coalescentDistributionCont n) g
+ let trs' = map (lengthenRoot t) trs -- Move time 't' up on the tree.
+ tl = trs' !! (i-1)
+ tr = trs' !! i
+ -- Join the two chosen trees.
+ tm = Node (PhyloLabel a Nothing 0.0) [tl, tr]
+ -- Take the trees on the left, the merged tree, and the trees on the right.
+ trs'' = take (i-1) trs' ++ [tm] ++ drop (i+1) trs'
+ simulate' (n-1) a trs'' g
diff --git a/src/ELynx/Simulate/PointProcess.hs b/src/ELynx/Simulate/PointProcess.hs
new file mode 100644
--- /dev/null
+++ b/src/ELynx/Simulate/PointProcess.hs
@@ -0,0 +1,233 @@
+{-# LANGUAGE BangPatterns #-}
+
+{- |
+ Module : ELynx.Simulate.PointProcess
+ Description : Point process and functions
+ Copyright : (c) Dominik Schrempf 2018
+ License : GPL-3
+
+ Maintainer : dominik.schrempf@gmail.com
+ Stability : unstable
+ Portability : portable
+
+Creation date: Tue Feb 13 13:16:18 2018.
+
+See Gernhard, T. (2008). The conditioned reconstructed process. Journal of
+Theoretical Biology, 253(4), 769–778. http://doi.org/10.1016/j.jtbi.2008.04.005.
+
+The point process can be used to simulate reconstructed trees under the birth
+and death process.
+
+-}
+
+module ELynx.Simulate.PointProcess
+ ( PointProcess(..)
+ , TimeSpec
+ , simulate
+ , toReconstructedTree
+ , simulateReconstructedTree
+ , simulateNReconstructedTrees
+ ) where
+
+import Control.Monad
+import Control.Monad.Primitive
+import Data.List (mapAccumL)
+import Data.Tree
+import qualified Statistics.Distribution as D (genContVar)
+import System.Random.MWC
+
+import ELynx.Data.Tree.MeasurableTree
+import ELynx.Data.Tree.PhyloTree
+import ELynx.Data.Tree.Tree
+import ELynx.Distribution.BirthDeath
+import ELynx.Distribution.BirthDeathCritical
+import ELynx.Distribution.BirthDeathCriticalNoTime
+import ELynx.Distribution.BirthDeathNearlyCritical
+import ELynx.Distribution.TimeOfOrigin
+import ELynx.Distribution.TimeOfOriginNearCritical
+import ELynx.Distribution.Types
+import ELynx.Tools.Equality
+import ELynx.Tools.List
+
+epsNearCriticalPointProcess :: Double
+epsNearCriticalPointProcess = 1e-5
+
+epsNearCriticalTimeOfOrigin :: Double
+epsNearCriticalTimeOfOrigin = 1e-8
+
+-- | A __point process__ for \(n\) points and of age \(t_{or}\) is defined as
+-- follows. Draw $n$ points on the horizontal axis at \(1,2,\ldots,n\). Pick
+-- \(n-1\) points at locations \((i+1/2, s_i)\), \(i=1,2,\ldots,n-1\);
+-- \(0 < s_i < t_{or}\). There is a bijection between (ranked) oriented trees
+-- and the point process. Usually, a will be 'String' (or 'Int') and b will be
+-- 'Double'.
+data PointProcess a b = PointProcess
+ { points :: ![a]
+ , values :: ![b]
+ , origin :: !b } deriving (Read, Show, Eq)
+
+-- | If nothing, sample time of origin from respective distribution. If time is
+-- given, we need to know if we condition on the time of origin, or the time of
+-- the most recent common ancestor (MRCA).
+type TimeSpec = Maybe (Time, Bool)
+
+-- | Sample a point process using the 'BirthDeathDistribution'. The names of the
+-- points will be integers.
+simulate :: (PrimMonad m)
+ => Int -- ^ Number of points (samples)
+ -> TimeSpec -- ^ Time of origin or MRCA
+ -> Rate -- ^ Birth rate
+ -> Rate -- ^ Death rate
+ -> Gen (PrimState m) -- ^ Generator (see 'System.Random.MWC')
+ -> m (PointProcess Int Double)
+-- No time of origin given. We also don't need to take care of the conditioning
+-- (origin or MRCA).
+simulate n Nothing l m g
+ -- XXX. There is no formula for the over-critical process.
+ | m > l = error "Time of origin distribution formula not available when mu > lambda. Please specify height for the moment."
+ -- For the critical process, we have no idea about the time of origin, but can
+ -- use a specially derived distribution.
+ | m =~= l = do
+ !vs <- replicateM (n-1) (D.genContVar (BDCNTD l) g)
+ -- XXX: The length of the root branch will be 0.
+ let t = maximum vs
+ return $ PointProcess [0..(n-1)] vs t
+ -- For the near critical process, we use a special distribution.
+ | abs (m-l) <= epsNearCriticalTimeOfOrigin = do
+ t <- D.genContVar (TONCD n l m) g
+ simulate n (Just (t, False)) l m g
+ -- For a sub-critical branching process, we can use the formula from Tanja Stadler.
+ | otherwise = do
+ t <- D.genContVar (TOD n l m) g
+ simulate n (Just (t, False)) l m g
+-- Time of origin is given.
+simulate n (Just (t, c)) l m g
+ | n < 1 = error "Number of samples needs to be one or larger."
+ | t < 0.0 = error "Time of origin needs to be positive."
+ | l < 0.0 = error "Birth rate needs to be positive."
+ -- See Stadler, T., & Steel, M. (2019). Swapping birth and death: symmetries
+ -- and transformations in phylodynamic models. , (), .
+ -- http://dx.doi.org/10.1101/494583. Should be possible now.
+ -- -- | m < 0.0 = error "Death rate needs to be positive."
+ -- Now, we have three different cases.
+ -- 1. The critical branching process.
+ -- 2. The near critical branching process.
+ -- 3. Normal values :).
+ | (m =~= l) && not c = do
+ !vs <- replicateM (n-1) (D.genContVar (BDCD t l) g)
+ return $ PointProcess [0..(n-1)] vs t
+ | (abs (m - l) <= epsNearCriticalPointProcess) && not c = do
+ !vs <- replicateM (n-1) (D.genContVar (BDNCD t l m) g)
+ return $ PointProcess [0..(n-1)] vs t
+ | not c = do
+ !vs <- replicateM (n-1) (D.genContVar (BDD t l m) g)
+ return $ PointProcess [0..(n-1)] vs t
+ | (m =~= l) && c = do
+ !vs <- replicateM (n-2) (D.genContVar (BDCD t l) g)
+ vs' <- randomInsert t vs g
+ return $ PointProcess [0..(n-1)] vs' t
+ | (abs (m - l) <= epsNearCriticalPointProcess) && c = do
+ !vs <- replicateM (n-2) (D.genContVar (BDNCD t l m) g)
+ vs' <- randomInsert t vs g
+ return $ PointProcess [0..(n-1)] vs' t
+ | c = do
+ !vs <- replicateM (n-2) (D.genContVar (BDD t l m) g)
+ vs' <- randomInsert t vs g
+ return $ PointProcess [0..(n-1)] vs' t
+ | otherwise = error "simulate: Fell through guard, this should never happen."
+
+-- | Sort the values of a point process and their indices to be (the indices
+-- that they will have while creating the tree).
+sort :: (Ord b) => PointProcess a b -> ([b], [Int])
+sort (PointProcess _ vs _) = (vsSorted, isSorted)
+ where vsIsSorted = sortWithIndices vs
+ vsSorted = map fst vsIsSorted
+ isSorted = flattenIndices $ map snd vsIsSorted
+
+-- Decrement indices that are above the one that is merged.
+flattenIndices :: [Int] -> [Int]
+flattenIndices is = snd $ mapAccumL fAcc [] is
+
+-- The accumulating function. Count the number of indices which are before the
+-- current index and lower than the current index.
+fAcc :: [Int] -> Int -> ([Int], Int)
+fAcc is i = (i:is, i')
+ where i' = i - length (filter ( Int -- ^ Number of trees
+ -> Int -- ^ Number of points (samples)
+ -> TimeSpec -- ^ Time of origin or MRCA
+ -> Rate -- ^ Birth rate
+ -> Rate -- ^ Death rate
+ -> Gen (PrimState m) -- ^ Generator (see 'System.Random.MWC')
+ -> m [Tree PhyloIntLabel]
+simulateNReconstructedTrees nT nP t l m g
+ | nT <= 0 = return []
+ | otherwise = replicateM nT $ simulateReconstructedTree nP t l m g
+
+-- | Use the point process to simulate a reconstructed tree (see
+-- 'toReconstructedTree') possibly with specific height and a fixed number of
+-- leaves according to the birth and death process.
+simulateReconstructedTree
+ :: (PrimMonad m)
+ => Int -- ^ Number of points (samples)
+ -> TimeSpec -- ^ Time of origin or MRCA
+ -> Rate -- ^ Birth rate
+ -> Rate -- ^ Death rate
+ -> Gen (PrimState m) -- ^ Generator (see 'System.Random.MWC')
+ -> m (Tree PhyloIntLabel)
+simulateReconstructedTree n t l m g = toReconstructedTree <$> simulate n t l m g
+
+-- | Convert a point process to a reconstructed tree. See Lemma 2.2.
+
+-- Of course, I decided to only use one tree structure with extinct and extant
+-- leaves (actually a complete tree). So a tree created here just does not
+-- contain extinct leaves. A function 'isReconstructed' is provided to test if a
+-- tree is reconstructed (and not complete) in this sense. However, a complete
+-- tree might show up as "reconstructed", just because, by chance, it does not
+-- contain extinct leaves. I wanted to use a Monoid constraint to get the unit
+-- element, but this fails for classical 'Int's. So, I rather have another
+-- (useless) argument.
+toReconstructedTree :: PointProcess Int Double
+ -> Tree PhyloIntLabel
+toReconstructedTree pp@(PointProcess ps vs o)
+ | length ps /= length vs + 1 = error "Too few or too many points."
+ | length vs <= 1 = error "Too few values."
+ -- -- XXX: Test is deactivated.
+ -- -- | otherwise = if isReconstructed treeOrigin then treeOrigin else error "Error in algorithm."
+ | otherwise = treeOrigin
+ where (vsSorted, isSorted) = sort pp
+ !lvs = [ singleton (PhyloLabel p Nothing 0) | p <- ps ]
+ !heights = replicate (length ps) 0
+ !treeRoot = toReconstructedTree' isSorted vsSorted lvs heights
+ !h = last vsSorted
+ !treeOrigin = lengthenRoot (o-h) treeRoot
+
+-- Move up the tree, connect nodes when they join according to the point process.
+toReconstructedTree' :: [Int] -- Sorted indices, see 'sort'.
+ -> [Double] -- Sorted merge values.
+ -> [Tree PhyloIntLabel] -- Leaves with accumulated root branch lengths.
+ -> [Double] -- Accumulated heights of the leaves.
+ -> Tree PhyloIntLabel
+toReconstructedTree' [] [] trs _ = head trs
+toReconstructedTree' is vs trs hs = toReconstructedTree' is' vs' trs'' hs'
+ -- For the algorithm, see 'ELynx.Coalescent.simulate', but index starts
+ -- at zero.
+ where !i = head is
+ !is' = tail is
+ !v = head vs
+ !vs' = tail vs
+ -- Left: l, right: r.
+ !hl = hs !! i
+ !hr = hs !! (i+1)
+ !dvl = v - hl
+ !dvr = v - hr
+ !tl = lengthenRoot dvl $ trs !! i
+ !tr = lengthenRoot dvr $ trs !! (i+1)
+ !h' = hl + dvl -- Should be the same as 'hr + dvr'.
+ !tm = Node (PhyloLabel 0 Nothing 0) [tl, tr]
+ !trs'' = take i trs ++ [tm] ++ drop (i+2) trs
+ !hs' = take i hs ++ [h'] ++ drop (i+2) hs
diff --git a/test/ELynx/Data/Tree/BipartitionSpec.hs b/test/ELynx/Data/Tree/BipartitionSpec.hs
new file mode 100644
--- /dev/null
+++ b/test/ELynx/Data/Tree/BipartitionSpec.hs
@@ -0,0 +1,79 @@
+{-# LANGUAGE OverloadedStrings #-}
+
+{- |
+Module : ELynx.Data.Tree.BipartitionSpec
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Aug 30 09:38:50 2019.
+
+-}
+
+module ELynx.Data.Tree.BipartitionSpec
+ (spec
+ ) where
+
+import qualified Data.ByteString.Lazy as L
+import qualified Data.Map as M
+import Data.Monoid
+import qualified Data.Set as S
+import Data.Tree
+import Test.Hspec
+
+import ELynx.Data.Tree.Bipartition
+import ELynx.Data.Tree.PhyloTree
+import ELynx.Import.Tree.Newick
+import ELynx.Tools.InputOutput
+
+treeFileSimple :: FilePath
+treeFileSimple = "data/TreeDist.trees"
+
+getSimpleTrees :: IO [Tree PhyloByteStringLabel]
+getSimpleTrees = parseFileWith manyNewick treeFileSimple
+
+bipartitionToBranchAnswer :: M.Map (Bipartition L.ByteString) (Sum Double)
+bipartitionToBranchAnswer =
+ M.fromList [ (bp (S.fromList ["B"]) (S.fromList ["A","C","D","E"]), Sum {getSum = 0.3})
+ , (bp (S.fromList ["B","C","D","E"]) (S.fromList ["A"]), Sum {getSum = 0.1})
+ , (bp (S.fromList ["B","C","E"]) (S.fromList ["A","D"]), Sum {getSum = 5.0e-2})
+ , (bp (S.fromList ["B","E"]) (S.fromList ["A","C","D"]), Sum {getSum = 0.4})
+ , (bp (S.fromList ["C"]) (S.fromList ["A","B","D","E"]), Sum {getSum = 1.0e-2})
+ , (bp (S.fromList ["D"]) (S.fromList ["A","B","C","E"]), Sum {getSum = 0.25})
+ , (bp (S.fromList ["E"]) (S.fromList ["A","B","C","D"]), Sum {getSum = 0.8}) ]
+
+bipartitionsFirstTree :: S.Set (Bipartition L.ByteString)
+bipartitionsFirstTree = S.fromList [ bp (S.fromList ["B"]) (S.fromList ["A","C","D","E"])
+ , bp (S.fromList ["B","C","D","E"]) (S.fromList ["A"])
+ , bp (S.fromList ["B","D","E"]) (S.fromList ["A","C"])
+ , bp (S.fromList ["B","E"]) (S.fromList ["A","C","D"])
+ , bp (S.fromList ["C"]) (S.fromList ["A","B","D","E"])
+ , bp (S.fromList ["D"]) (S.fromList ["A","B","C","E"])
+ , bp (S.fromList ["E"]) (S.fromList ["A","B","C","D"]) ]
+
+bipartitionsSecondTree :: S.Set (Bipartition L.ByteString)
+bipartitionsSecondTree = S.fromList [ bp (S.fromList ["B"]) (S.fromList ["A","C","D","E"])
+ , bp (S.fromList ["B","C","D","E"]) (S.fromList ["A"])
+ , bp (S.fromList ["B","C","E"]) (S.fromList ["A","D"])
+ , bp (S.fromList ["B","E"]) (S.fromList ["A","C","D"])
+ , bp (S.fromList ["C"]) (S.fromList ["A","B","D","E"])
+ , bp (S.fromList ["D"]) (S.fromList ["A","B","C","E"])
+ , bp (S.fromList ["E"]) (S.fromList ["A","B","C","D"])]
+
+spec :: Spec
+spec = do
+ describe "bipartitions" $
+ it "calculates correct bipartitions for sample trees" $ do
+ simpleTrees <- map removeBrLen <$> getSimpleTrees
+ let t1 = head simpleTrees
+ t2 = simpleTrees !! 1
+ bipartitions t1 `shouldBe` bipartitionsFirstTree
+ bipartitions t2 `shouldBe` bipartitionsSecondTree
+ describe "bipartitionToBranch" $
+ it "creates a map from bipartitions to branch lengths" $ do
+ simpleTrees <- getSimpleTrees
+ bipartitionToBranch pLabel (Sum . pBrLen) (simpleTrees !! 2)
+ `shouldBe` bipartitionToBranchAnswer
diff --git a/test/ELynx/Data/Tree/DistanceSpec.hs b/test/ELynx/Data/Tree/DistanceSpec.hs
new file mode 100644
--- /dev/null
+++ b/test/ELynx/Data/Tree/DistanceSpec.hs
@@ -0,0 +1,99 @@
+{-# LANGUAGE FlexibleInstances #-}
+{- |
+Module : ELynx.Data.Tree.DistanceSpec
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Aug 30 09:38:50 2019.
+
+-}
+
+module ELynx.Data.Tree.DistanceSpec
+ (spec
+ ) where
+
+import Data.Tree
+import Test.Hspec
+import Test.QuickCheck
+import Test.QuickCheck.Instances.Containers ()
+
+import ELynx.Data.Tree.Distance
+import ELynx.Data.Tree.NamedTree
+import ELynx.Data.Tree.PhyloTree
+import ELynx.Import.Tree.Newick
+import ELynx.Tools.Equality
+import ELynx.Tools.InputOutput
+
+treeFileSimple :: FilePath
+treeFileSimple = "data/TreeDist.trees"
+
+getSimpleTrees :: IO [Tree PhyloByteStringLabel]
+getSimpleTrees = parseFileWith manyNewick treeFileSimple
+
+treeFileMany :: FilePath
+treeFileMany = "data/Many.trees"
+
+getManyTrees :: IO [Tree PhyloByteStringLabel]
+getManyTrees = parseFileWith manyNewick treeFileMany
+
+-- I used treedist from Phylip to get the correct results.
+-- See http://evolution.genetics.washington.edu/phylip/doc/treedist.html.
+symmetricDistanceAnswers :: [Int]
+symmetricDistanceAnswers =
+ [ 6, 8, 0, 0, 12, 20, 18, 20, 10, 2, 10, 4, 4, 4, 4, 4, 10, 16, 8, 2, 4, 0, 0,
+ 0, 10, 4, 0, 0, 2, 2, 0, 0, 4, 0, 2, 0, 8, 6, 2, 6, 4, 4, 8, 0, 0, 4, 2, 0,
+ 10, 0, 0, 10 ]
+
+branchScoreDistanceAnswers :: [Double]
+branchScoreDistanceAnswers =
+ [ 8.567916e-02, 9.570577e-02, 1.704571e-02, 7.603990e-03, 6.149761e-01,
+ 3.557070e-01, 2.329811e-01, 3.820208e-01, 1.895421e-02, 6.302364e-03,
+ 2.083286e-02, 1.023777e-03, 2.138244e-02, 1.444380e-02, 1.958628e-02,
+ 6.089461e-03, 2.551873e-02, 8.041220e-02, 4.123102e-02, 8.241811e-03,
+ 2.623805e-02, 2.109278e-02, 1.953769e-02, 4.459926e-03, 6.594537e-02,
+ 7.040703e-02, 8.603133e-03, 3.878009e-03, 2.969969e-02, 2.505262e-02,
+ 2.095988e-02, 8.461041e-03, 5.228005e-02, 6.001320e-02, 8.276652e-03,
+ 6.966115e-03, 7.701581e-02, 4.946339e-02, 2.548024e-02, 5.800598e-03,
+ 3.875927e-02, 2.836737e-02, 9.059706e-02, 1.333325e-02, 5.071356e-02,
+ 7.433056e-02, 3.854717e-02, 3.255993e-02, 1.581909e-01, 6.813096e-02,
+ 8.210513e-02, 7.664642e-02 ]
+
+prop_dist_same_tree :: (Num b, Eq b) => (Tree a -> Tree a -> b) -> Tree a -> Bool
+prop_dist_same_tree distanceMeasure t = distanceMeasure t t == 0
+
+-- TODO: Microsporidia trees with branch support values.
+-- getMicrospoPoissonTree :: IO (Tree PhyloByteStringLabel)
+-- getMicrospoPoissonTree = parseFileWith newick "data/MicrospoPoisson.tree"
+-- getMicrospoUDM32Tree = parseFileWith newick "data/MicrospoEDM32.tree"
+-- getMicrospoUDM64Tree = parseFileWith newick "data/MicrospoEDM64.tree"
+
+each :: Int -> [a] -> [a]
+each n = map head . takeWhile (not . null) . iterate (drop n)
+
+spec :: Spec
+spec = do
+ describe "symmetricDistance" $
+ it "calculates correct distances for sample trees" $ do
+ simpleTrees <- getSimpleTrees
+ symmetricDistance (head simpleTrees) (simpleTrees !! 1) `shouldBe` 2
+ manyTrees <- getManyTrees
+ -- Since treedist computes the distance between adjacent pairs, in the
+ -- following manner: [tr0, tr1, tr2, tr3] -> [dist tr0 tr1, dist tr2 tr3],
+ -- we have to skip some distances.
+ each 2 (computeAdjacentDistances (symmetricDistanceWith getName) manyTrees)
+ `shouldBe` symmetricDistanceAnswers
+
+ describe "incompatibleSplitDistance" $
+ it "calculates correct distances for completely collapsed trees" $
+ property $ prop_dist_same_tree (incompatibleSplitsDistance :: Tree PhyloIntLabel -> Tree PhyloIntLabel -> Int)
+
+ describe "branchScoreDistance" $
+ it "calculates correct distances for sample trees" $ do
+ manyTrees <- getManyTrees
+ print branchScoreDistanceAnswers
+ each 2 (computeAdjacentDistances branchScoreDistance manyTrees)
+ `shouldSatisfy` nearlyEqListWith 1e-5 branchScoreDistanceAnswers
diff --git a/test/ELynx/Data/Tree/TreeSpec.hs b/test/ELynx/Data/Tree/TreeSpec.hs
new file mode 100644
--- /dev/null
+++ b/test/ELynx/Data/Tree/TreeSpec.hs
@@ -0,0 +1,66 @@
+{- |
+Module : ELynx.Data.Tree.TreeSpec
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Mon May 6 14:04:05 2019.
+
+-}
+
+module ELynx.Data.Tree.TreeSpec
+ (spec
+ ) where
+
+import qualified Data.ByteString.Lazy.Char8 as L
+import Data.Maybe
+import Data.Tree
+import Test.Hspec
+
+import ELynx.Data.Tree.MeasurableTree
+import ELynx.Data.Tree.PhyloTree
+import ELynx.Data.Tree.Tree
+import ELynx.Import.Tree.Newick hiding (node)
+import ELynx.Tools.InputOutput (parseByteStringWith)
+
+node :: Int -> Tree Int
+node n = Node n []
+
+smallTree :: Tree Int
+smallTree = Node 0 [node 1, node 2]
+
+smallSubTree :: Tree Int
+smallSubTree = Node 0 [node 1]
+
+smallSubTreePruned :: Tree Int
+smallSubTreePruned = node 1
+
+sampleTreeBS :: L.ByteString
+sampleTreeBS = L.pack "(Aeropyrum0:0.5478645225,(((((((((Arabidopsi:0.0701001024,Oryza_sati:0.0765988261):0.0309636193,Gymnosperm:0.0520325624):0.0338982245,Physcomitr:0.0768008916):0.0895714685,(Chlamydomo:0.1136227755,Dunaliella:0.1406347323):0.1117340620):0.0818876186,Rhodophyta:0.3405656487):0.0363527066,((((((Babesia_bo:0.1646969208,Theileria0:0.1519889486):0.1908081096,Plasmodium:0.3250696762):0.0637865908,(Toxoplasma:0.1153570425,Eimeria000:0.1671916078):0.0980136930):0.0518956330,Cryptospor:0.3175062809):0.1607708388,Ciliophora:0.5687502950):0.0624078848,(Phytophtho:0.2016424948,((Thalassios:0.1202730781,Phaeodacty:0.1290341329):0.1772775509,Phaeophyce:0.1989260715):0.0312359673):0.1154768302):0.0311952864):0.0149160316,(((((((((Candida_al:0.1027755272,Saccharomy:0.1190206560):0.1333487870,Neurospora:0.1977309079):0.0522926266,Schizosacc:0.2019603227):0.0567441011,(Cryptococc:0.1948614959,Ustilago_m:0.1564451295):0.0775729694):0.0323959951,Glomus_int:0.1573670796):0.0194701292,Chytridiom:0.2228415254):0.0384370601,Encephalit:1.4622174644):0.0416231688,(((Drosophila:0.2160627753,(Mammalians:0.1080484094,Tunicates0:0.1739253014):0.0289624371):0.0346633757,Hydrozoa00:0.2058137032):0.0480963050,Monosiga_b:0.3020637584):0.0654894239):0.0380915725,(Dictyostel:0.3453588998,Mastigamoe:0.3844779231):0.0478795653):0.0129578395):1.7592083381,((Archaeoglo:0.5402784445,Methanococ:0.4088567459):0.0993669265,Pyrococcus:0.4058713829):0.1734405968):0.2193511807,Pyrobaculu:0.7507718047):0.1646616482,Sulfolobus:0.5404967897);"
+
+
+largeTree :: Tree PhyloByteStringLabel
+largeTree = parseByteStringWith "Sample newick byte string" newick sampleTreeBS
+
+subSampleLargeTree :: Tree PhyloByteStringLabel
+subSampleLargeTree = fromJust $ subTree ((== 'P') . L.head . pLabel) largeTree
+
+spec :: Spec
+spec = do
+ describe "subTree" $ do
+ it "returns nothing if no leaf satisfies prediacte" $
+ subTree (==3) smallTree `shouldBe` Nothing
+ it "returns the correct subtree for a small example" $
+ subTree (==1) smallTree `shouldBe` Just smallSubTree
+
+ describe "pruneWith" $ do
+ it "leaves a normal tree untouched" $
+ pruneWith const largeTree `shouldBe` largeTree
+ it "correctly prunes a small example" $
+ pruneWith const smallSubTree `shouldBe` smallSubTreePruned
+ it "leaves height constant for Measurable trees" $
+ height (prune subSampleLargeTree) `shouldBe` height subSampleLargeTree
+
diff --git a/test/ELynx/Export/Tree/NewickSpec.hs b/test/ELynx/Export/Tree/NewickSpec.hs
new file mode 100644
--- /dev/null
+++ b/test/ELynx/Export/Tree/NewickSpec.hs
@@ -0,0 +1,39 @@
+{- |
+Module : ELynx.Export.Tree.NewickSpec
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Wed Feb 13 11:01:53 2019.
+
+-}
+
+module ELynx.Export.Tree.NewickSpec
+ (spec
+ ) where
+
+import qualified Data.ByteString.Lazy.Char8 as L
+import Data.Tree
+import Test.Hspec
+
+import ELynx.Data.Tree.PhyloTree
+import ELynx.Export.Tree.Newick
+import ELynx.Import.Tree.Newick
+import ELynx.Tools.InputOutput
+
+samplePhyloByteStringTree :: Tree PhyloByteStringLabel
+samplePhyloByteStringTree =
+ parseByteStringWith "Sample newick byte string" newick sampleNewickByteString1
+
+sampleNewickByteString1 :: L.ByteString
+sampleNewickByteString1 = L.pack "(Aeropyrum0:0.5478645225,(((((((((Arabidopsi:0.0701001024,Oryza_sati:0.0765988261):0.0309636193,Gymnosperm:0.0520325624):0.0338982245,Physcomitr:0.0768008916):0.0895714685,(Chlamydomo:0.1136227755,Dunaliella:0.1406347323):0.1117340620):0.0818876186,Rhodophyta:0.3405656487):0.0363527066,((((((Babesia_bo:0.1646969208,Theileria0:0.1519889486):0.1908081096,Plasmodium:0.3250696762):0.0637865908,(Toxoplasma:0.1153570425,Eimeria000:0.1671916078):0.0980136930):0.0518956330,Cryptospor:0.3175062809):0.1607708388,Ciliophora:0.5687502950):0.0624078848,(Phytophtho:0.2016424948,((Thalassios:0.1202730781,Phaeodacty:0.1290341329):0.1772775509,Phaeophyce:0.1989260715):0.0312359673):0.1154768302):0.0311952864):0.0149160316,(((((((((Candida_al:0.1027755272,Saccharomy:0.1190206560):0.1333487870,Neurospora:0.1977309079):0.0522926266,Schizosacc:0.2019603227):0.0567441011,(Cryptococc:0.1948614959,Ustilago_m:0.1564451295):0.0775729694):0.0323959951,Glomus_int:0.1573670796):0.0194701292,Chytridiom:0.2228415254):0.0384370601,Encephalit:1.4622174644):0.0416231688,(((Drosophila:0.2160627753,(Mammalians:0.1080484094,Tunicates0:0.1739253014):0.0289624371):0.0346633757,Hydrozoa00:0.2058137032):0.0480963050,Monosiga_b:0.3020637584):0.0654894239):0.0380915725,(Dictyostel:0.3453588998,Mastigamoe:0.3844779231):0.0478795653):0.0129578395):1.7592083381,((Archaeoglo:0.5402784445,Methanococ:0.4088567459):0.0993669265,Pyrococcus:0.4058713829):0.1734405968):0.2193511807,Pyrobaculu:0.7507718047):0.1646616482,Sulfolobus:0.5404967897);"
+
+spec :: Spec
+spec = describe "parseByteStringWith newick $ toNewickPhyloByteString" $
+ it "should be an invariant" $ do
+ let bs = toNewick samplePhyloByteStringTree
+ parseByteStringWith "Newick string converted from tree object"
+ newick bs `shouldBe` samplePhyloByteStringTree
diff --git a/test/ELynx/Import/Tree/NewickSpec.hs b/test/ELynx/Import/Tree/NewickSpec.hs
new file mode 100644
--- /dev/null
+++ b/test/ELynx/Import/Tree/NewickSpec.hs
@@ -0,0 +1,115 @@
+{- |
+Module : ELynx.Import.Tree.NewickSpec
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Jan 18 10:14:04 2019.
+
+-}
+
+module ELynx.Import.Tree.NewickSpec
+ (spec) where
+
+import qualified Data.ByteString.Lazy.Char8 as L
+import Data.Tree
+import ELynx.Data.Tree.PhyloTree
+import ELynx.Import.Tree.Newick
+import Test.Hspec
+import Test.Hspec.Megaparsec
+import Text.Megaparsec
+
+sampleLabelByteString :: L.ByteString
+sampleLabelByteString = L.pack "name:0.3"
+
+sampleLabel :: PhyloByteStringLabel
+sampleLabel = PhyloLabel (L.pack "name") Nothing 0.3
+
+sampleForestByteString :: L.ByteString
+sampleForestByteString = L.pack "(l,l,(a,b))"
+
+sampleForest :: [Tree PhyloByteStringLabel]
+sampleForest =
+ [ Node { rootLabel = PhyloLabel (L.pack "l") Nothing 0
+ , subForest = []
+ }
+ , Node { rootLabel = PhyloLabel (L.pack "l") Nothing 0
+ , subForest = []
+ }
+ , Node { rootLabel = PhyloLabel (L.pack "") Nothing 0
+ , subForest =
+ [ Node {rootLabel = PhyloLabel (L.pack "a") Nothing 0, subForest = []}
+ , Node {rootLabel = PhyloLabel (L.pack "b") Nothing 0, subForest = []}
+ ]
+ }
+ ]
+
+sampleNewickByteString1 :: L.ByteString
+sampleNewickByteString1 = L.pack "(Aeropyrum0:0.5478645225,(((((((((Arabidopsi:0.0701001024,Oryza_sati:0.0765988261):0.0309636193,Gymnosperm:0.0520325624):0.0338982245,Physcomitr:0.0768008916):0.0895714685,(Chlamydomo:0.1136227755,Dunaliella:0.1406347323):0.1117340620):0.0818876186,Rhodophyta:0.3405656487):0.0363527066,((((((Babesia_bo:0.1646969208,Theileria0:0.1519889486):0.1908081096,Plasmodium:0.3250696762):0.0637865908,(Toxoplasma:0.1153570425,Eimeria000:0.1671916078):0.0980136930):0.0518956330,Cryptospor:0.3175062809):0.1607708388,Ciliophora:0.5687502950):0.0624078848,(Phytophtho:0.2016424948,((Thalassios:0.1202730781,Phaeodacty:0.1290341329):0.1772775509,Phaeophyce:0.1989260715):0.0312359673):0.1154768302):0.0311952864):0.0149160316,(((((((((Candida_al:0.1027755272,Saccharomy:0.1190206560):0.1333487870,Neurospora:0.1977309079):0.0522926266,Schizosacc:0.2019603227):0.0567441011,(Cryptococc:0.1948614959,Ustilago_m:0.1564451295):0.0775729694):0.0323959951,Glomus_int:0.1573670796):0.0194701292,Chytridiom:0.2228415254):0.0384370601,Encephalit:1.4622174644):0.0416231688,(((Drosophila:0.2160627753,(Mammalians:0.1080484094,Tunicates0:0.1739253014):0.0289624371):0.0346633757,Hydrozoa00:0.2058137032):0.0480963050,Monosiga_b:0.3020637584):0.0654894239):0.0380915725,(Dictyostel:0.3453588998,Mastigamoe:0.3844779231):0.0478795653):0.0129578395):1.7592083381,((Archaeoglo:0.5402784445,Methanococ:0.4088567459):0.0993669265,Pyrococcus:0.4058713829):0.1734405968):0.2193511807,Pyrobaculu:0.7507718047):0.1646616482,Sulfolobus:0.5404967897);"
+
+sampleNewickByteString2 :: L.ByteString
+sampleNewickByteString2 = L.pack "(Caenorhabd:0.0176707431,C0briggsae:0.0142817073,(Ancylostom:0.0711440844,(Pristionch:0.1301309005,((Brugia_mal:0.0757534325,Ascaris0su:0.0482660407)1:0.0563924634,(((Meloidogyn:0.1239621893,Heteroderi:0.0987968800)1:0.1136879428,Strongyloi:0.2483437292)1:0.0252467381,(Trichoceph:0.2985037612,((((((Coleoptera:0.0907850846,(Apis0melli:0.0754058285,Hemiptera0:0.1675359618)0.93:0.0085703192)1:0.0146980945,(Siphonapte:0.0556805916,Bombyx0mor:0.0968983509)1:0.0127867903)1:0.0167360185,((Drosophila:0.0492149086,Glossina0m:0.0534390467)1:0.0583462602,Anopheles0:0.0968919941)1:0.0431343553)1:0.0535616453,Crustacea0:0.2247268999)1:0.0252755187,Chelicerat:0.1537491558)1:0.0212497286,((Echinoderm:0.1803896615,(Cephalocho:0.1492264574,(Urochordat:0.2194747834,(Mammalia00:0.0393008407,Actinopter:0.0491700096):0.0858550024)1:0.0157515969)1:0.0132516777)1:0.0203423736,((((((((Neurospora:0.0721607581,Magnaporth:0.0814182810)1:0.0198940548,Gibberella:0.0858192964)1:0.0533872590,Eurotiomyc:0.1058840539)1:0.1266302603,(Candida0al:0.1349957509,Saccharomy:0.1553464572)1:0.1791344287)1:0.0529664967,Schizosacc:0.2550087905)1:0.0723650615,(Ustilago0m:0.2031812772,(Homobasidi:0.1473391802,Cryptococc:0.2070743149)1:0.0347868586)1:0.0790327507)1:0.0727415175,Glomales00:0.1779430068)1:0.0169066667,Chytridiom:0.3028920870)1:0.3311420273)1:0.0278566156)1:0.1049569161)1:0.1366217350)1:0.0171168289)1:0.0345725378)1:0.0542036935)1:0.0879337167)1;"
+
+
+sampleNewickEmptyByteString :: L.ByteString
+sampleNewickEmptyByteString = L.pack "(,(,,),);"
+
+sampleNewickEmpty :: Tree PhyloByteStringLabel
+sampleNewickEmpty =
+ Node { rootLabel = PhyloLabel (L.pack "") Nothing 0
+ , subForest =
+ [ Node {rootLabel = PhyloLabel (L.pack "") Nothing 0, subForest = []}
+ , Node {rootLabel = PhyloLabel (L.pack "") Nothing 0, subForest =
+ [ Node {rootLabel = PhyloLabel (L.pack "") Nothing 0, subForest = []}
+ , Node {rootLabel = PhyloLabel (L.pack "") Nothing 0, subForest = []}
+ , Node {rootLabel = PhyloLabel (L.pack "") Nothing 0, subForest = []}
+ ]
+ }
+ , Node {rootLabel = PhyloLabel (L.pack "") Nothing 0, subForest = []}
+ ]
+ }
+
+spec :: Spec
+spec = do
+ describe "branchLength" $ do
+ it "parses a colon and a branch length" $
+ parse branchLength "" (L.pack ":13.2") `shouldParse` 13.2
+
+ it "returns 0 if no branch length is given" $
+ parse branchLength "" (L.pack "") `shouldParse` 0
+
+ describe "name" $ do
+ it "parses a string of printable characters" $
+ parse name "" (L.pack "aName") `shouldParse` L.pack "aName"
+
+ it "parses blanks, colons, semicolons, parentheses, and sequare brackets" $
+ parse name "" (L.pack "aName bla") `shouldParse` L.pack "aName"
+
+ it "allows empty names" $
+ parse name "" (L.pack "") `shouldParse` L.pack ""
+
+ describe "node" $ do
+ it "parses a tree node" $
+ parse node "" sampleLabelByteString `shouldParse` sampleLabel
+
+ it "parses tree nodes with empty names and branch lengths" $
+ parse node "" (L.pack "") `shouldParse` PhyloLabel (L.pack "") Nothing 0
+
+ describe "leaf" $
+ it "parses a leaf of a tree" $
+ parse leaf "" sampleLabelByteString `shouldParse` Node sampleLabel []
+
+ describe "forest" $
+ it "parses a set of trees within brackets" $
+ parse forest "" sampleForestByteString `shouldParse` sampleForest
+
+ describe "newick" $ do
+ it "parses a newick trees" $ do
+ parse newick "" `shouldSucceedOn` sampleNewickByteString1
+ parse newick "" `shouldSucceedOn` sampleNewickByteString2
+
+ it "parses a weird newick tree without node labels nor branch lengths" $
+ parse newick "" sampleNewickEmptyByteString `shouldParse` sampleNewickEmpty
diff --git a/test/Spec.hs b/test/Spec.hs
new file mode 100644
--- /dev/null
+++ b/test/Spec.hs
@@ -0,0 +1,1 @@
+{-# OPTIONS_GHC -F -pgmF hspec-discover #-}