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/app/Main.hs b/app/Main.hs
new file mode 100644
--- /dev/null
+++ b/app/Main.hs
@@ -0,0 +1,44 @@
+{- |
+Module : Main
+Description : Work with molecular sequence data
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Thu Sep 5 21:53:07 2019.
+
+-}
+
+module Main where
+
+import Control.Monad.Trans.Reader
+
+import Options
+
+import Concatenate.Concatenate
+import Examine.Examine
+import Filter.Filter
+import Simulate.Simulate
+import SubSample.SubSample
+import Translate.Translate
+
+import ELynx.Tools.Logger
+import ELynx.Tools.Options
+
+main :: IO ()
+main = do
+ Arguments g c <- parseArguments
+ let fn = outFileBaseName g
+ lvl = verbosity g
+ lf = (++ ".log") <$> fn
+ case c of
+ Concatenate a -> runReaderT (eLynxWrapper lvl lf concatenateHeader $ concatenateCmd fn) a
+ Examine a -> runReaderT (eLynxWrapper lvl lf examineHeader $ examineCmd fn) a
+ FilterRows a -> runReaderT (eLynxWrapper lvl lf filterRowsHeader $ filterRowsCmd fn) a
+ FilterColumns a -> runReaderT (eLynxWrapper lvl lf filterColumnsHeader $ filterColumnsCmd fn) a
+ Simulate a -> runReaderT (eLynxWrapper lvl lf simulateHeader $ simulateCmd fn) a
+ SubSample a -> runReaderT (eLynxWrapper lvl lf subSampleHeader $ subSampleCmd fn) a
+ Translate a -> runReaderT (eLynxWrapper lvl lf translateHeader $ translateCmd fn) a
diff --git a/app/Options.hs b/app/Options.hs
new file mode 100644
--- /dev/null
+++ b/app/Options.hs
@@ -0,0 +1,129 @@
+{- |
+Module : Options
+Description : SLynx general options
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Sat Sep 7 18:55:03 2019.
+
+-}
+
+module Options
+ ( Arguments (..)
+ , CommandArguments (..)
+ , parseArguments
+ , concatenateHeader
+ , examineHeader
+ , filterRowsHeader
+ , filterColumnsHeader
+ , simulateHeader
+ , subSampleHeader
+ , translateHeader
+ ) where
+
+import Options.Applicative
+import Options.Applicative.Help.Pretty
+
+import Concatenate.Options
+import Examine.Options
+import Filter.Options
+import Simulate.Options
+import SubSample.Options
+import Translate.Options
+
+import ELynx.Data.Alphabet.Alphabet
+import ELynx.Tools.Options
+
+data CommandArguments =
+ Concatenate ConcatenateArguments
+ | Examine ExamineArguments
+ | FilterRows FilterRowsArguments
+ | FilterColumns FilterColumnsArguments
+ | Simulate SimulateArguments
+ | SubSample SubSampleArguments
+ | Translate TranslateArguments
+
+concatenateHeader, examineHeader, filterRowsHeader, filterColumnsHeader, simulateHeader, subSampleHeader, translateHeader :: String
+concatenateHeader = "Concatenate sequences found in input files."
+examineHeader = "Examine sequences."
+filterRowsHeader = "Filter rows (or sequences) found in input files."
+filterColumnsHeader = "Filter columns of multi-sequence alignments."
+simulateHeader = "Simulate multi sequence alignments."
+subSampleHeader = "Sub-sample columns from multi sequence alignments."
+translateHeader = "Translate from DNA to Protein or DNAX to ProteinX."
+
+concatenateCommand :: Mod CommandFields CommandArguments
+concatenateCommand = command "concatenate" $
+ info (Concatenate <$> concatenateArguments)
+ $ header concatenateHeader
+
+examineCommand :: Mod CommandFields CommandArguments
+examineCommand = command "examine" $
+ info (Examine <$> examineArguments)
+ ( fullDesc
+ <> header examineHeader
+ <> progDesc "If data is a multi sequence alignment, additionally analyze columns." )
+
+filterRowsCommand :: Mod CommandFields CommandArguments
+filterRowsCommand = command "filter-rows" $
+ info (FilterRows <$> filterRowsArguments)
+ $ header filterRowsHeader
+
+filterColumnsCommand :: Mod CommandFields CommandArguments
+filterColumnsCommand = command "filter-columns" $
+ info (FilterColumns <$> filterColumnsArguments)
+ $ header filterColumnsHeader
+
+simulateCommand :: Mod CommandFields CommandArguments
+simulateCommand = command "simulate" $
+ info (Simulate <$> simulateArguments)
+ (fullDesc
+ <> header simulateHeader
+ <> footerDoc (Just $ pretty simulateFooter) )
+
+subSampleCommand :: Mod CommandFields CommandArguments
+subSampleCommand = command "sub-sample" $
+ info (SubSample <$> subSampleArguments)
+ ( fullDesc
+ <> header subSampleHeader
+ <> progDesc "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." )
+
+translateCommand :: Mod CommandFields CommandArguments
+translateCommand = command "translate" $
+ info (Translate <$> translateArguments)
+ $ header translateHeader
+
+commandArguments :: Parser CommandArguments
+commandArguments = hsubparser $
+ concatenateCommand
+ <> examineCommand
+ <> filterRowsCommand
+ <> filterColumnsCommand
+ <> simulateCommand
+ <> subSampleCommand
+ <> translateCommand
+
+data Arguments = Arguments
+ { globalArgs :: GlobalArguments
+ , cmdArgs :: CommandArguments }
+
+parseArguments :: IO Arguments
+parseArguments = parseArgumentsWith desc ftr $
+ Arguments
+ <$> globalArguments
+ <*> commandArguments
+
+desc :: [String]
+desc = [ "Analyze, and simulate multi sequence alignments." ]
+
+ftr :: [String]
+ftr = [ "File formats:" ] ++ fs ++
+ [ "", "Alphabet types:" ] ++ as
+ where
+ toListItem = (" - " ++)
+ fs = map toListItem ["FASTA"]
+ as = map (toListItem . alphabetNameVerbose) [(minBound :: Alphabet) ..]
diff --git a/slynx.cabal b/slynx.cabal
new file mode 100644
--- /dev/null
+++ b/slynx.cabal
@@ -0,0 +1,105 @@
+cabal-version: 1.12
+name: slynx
+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 molecular sequences
+description:
+ Examine, modify, and simulate molecular sequences 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:
+ Concatenate.Concatenate
+ Concatenate.Options
+ Examine.Examine
+ Examine.Options
+ Filter.Filter
+ Filter.Options
+ Simulate.Options
+ Simulate.PhyloModel
+ Simulate.Simulate
+ SubSample.Options
+ SubSample.SubSample
+ Tools
+ Translate.Options
+ Translate.Translate
+ hs-source-dirs: src
+ other-modules:
+ Paths_slynx
+ default-language: Haskell2010
+ ghc-options: -Wall
+ build-depends:
+ async >=2.2.2 && <2.3,
+ base >=4.12.0.0 && <4.13,
+ bytestring >=0.10.8.2 && <0.11,
+ containers >=0.6.0.1 && <0.7,
+ data-memocombinators >=0.5.1 && <0.6,
+ elynx-seq >=0.0.1 && <0.1,
+ elynx-tools >=0.0.1 && <0.1,
+ elynx-tree >=0.0.1 && <0.1,
+ hmatrix >=0.20.0.0 && <0.21,
+ integration >=0.2.1 && <0.3,
+ lens >=4.17.1 && <4.18,
+ math-functions >=0.3.1.0 && <0.4,
+ matrices >=0.5.0 && <0.6,
+ megaparsec >=7.0.5 && <7.1,
+ monad-logger >=0.3.30 && <0.4,
+ 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,
+ statistics >=0.15.0.0 && <0.16,
+ text >=1.2.3.1 && <1.3,
+ transformers >=0.5.6.2 && <0.6,
+ vector >=0.12.0.3 && <0.13,
+ vector-th-unbox >=0.2.1.6 && <0.3,
+ word8 >=0.1.3 && <0.2
+
+executable slynx
+ main-is: Main.hs
+ hs-source-dirs: app
+ other-modules:
+ Options
+ Paths_slynx
+ default-language: Haskell2010
+ ghc-options: -Wall -eventlog -threaded -rtsopts -with-rtsopts=-N
+ build-depends:
+ async >=2.2.2 && <2.3,
+ base >=4.12.0.0 && <4.13,
+ bytestring >=0.10.8.2 && <0.11,
+ containers >=0.6.0.1 && <0.7,
+ data-memocombinators >=0.5.1 && <0.6,
+ elynx-seq >=0.0.1 && <0.1,
+ elynx-tools >=0.0.1 && <0.1,
+ hmatrix >=0.20.0.0 && <0.21,
+ integration >=0.2.1 && <0.3,
+ lens >=4.17.1 && <4.18,
+ math-functions >=0.3.1.0 && <0.4,
+ matrices >=0.5.0 && <0.6,
+ megaparsec >=7.0.5 && <7.1,
+ monad-logger >=0.3.30 && <0.4,
+ 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,
+ slynx -any,
+ statistics >=0.15.0.0 && <0.16,
+ text >=1.2.3.1 && <1.3,
+ transformers >=0.5.6.2 && <0.6,
+ vector >=0.12.0.3 && <0.13,
+ vector-th-unbox >=0.2.1.6 && <0.3,
+ word8 >=0.1.3 && <0.2
diff --git a/src/Concatenate/Concatenate.hs b/src/Concatenate/Concatenate.hs
new file mode 100644
--- /dev/null
+++ b/src/Concatenate/Concatenate.hs
@@ -0,0 +1,43 @@
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE TemplateHaskell #-}
+
+{- |
+Module : Analyze.Analyze
+Description : Parse sequence file formats and analyze them
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Oct 5 08:41:05 2018.
+
+-}
+
+module Concatenate.Concatenate
+ ( concatenateCmd
+ )
+where
+
+import Control.Monad.Logger
+import Control.Monad.Trans.Class
+import Control.Monad.Trans.Reader
+
+import Concatenate.Options
+import Tools
+
+import ELynx.Data.Sequence.Sequence
+import ELynx.Export.Sequence.Fasta
+import ELynx.Tools.InputOutput
+
+-- | Concatenate sequences.
+concatenateCmd :: Maybe FilePath -> Concatenate ()
+concatenateCmd outFileBaseName = do
+ $(logInfo) "Command: Concatenate sequences."
+ ConcatenateArguments al fps <- lift ask
+ sss <- mapM (readSeqs al . Just) fps
+ let result = sequencesToFasta $ concatenateSeqs sss
+ let outFilePath = (++ ".fasta") <$> outFileBaseName
+ io "concatenated multi sequence alignment " result outFilePath
+
diff --git a/src/Concatenate/Options.hs b/src/Concatenate/Options.hs
new file mode 100644
--- /dev/null
+++ b/src/Concatenate/Options.hs
@@ -0,0 +1,47 @@
+{- |
+Module : Concatenate.Options
+Description : ELynxSeq argument parsing
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Sun Oct 7 17:29:45 2018.
+
+-}
+
+module Concatenate.Options
+ ( ConcatenateArguments (..)
+ , Concatenate
+ , concatenateArguments
+ ) where
+
+import Control.Applicative
+import Control.Monad.Logger
+import Control.Monad.Trans.Reader
+import Options.Applicative
+
+import Tools
+
+import ELynx.Data.Alphabet.Alphabet
+
+-- | Arguments needed to concatenate multi sequence alignments.
+data ConcatenateArguments = ConcatenateArguments
+ { ccAlphabet :: Alphabet
+ , ccInFiles :: [FilePath] }
+
+-- | Logger and Reader type.
+type Concatenate = LoggingT (ReaderT ConcatenateArguments IO)
+
+-- | Command line parser.
+concatenateArguments :: Parser ConcatenateArguments
+concatenateArguments = ConcatenateArguments
+ <$> alphabetOpt
+ <*> some inFileArg
+
+inFileArg :: Parser FilePath
+inFileArg = strArgument $
+ metavar "INPUT-FILE" <>
+ help "Read sequences from INPUT-FILE"
diff --git a/src/Examine/Examine.hs b/src/Examine/Examine.hs
new file mode 100644
--- /dev/null
+++ b/src/Examine/Examine.hs
@@ -0,0 +1,106 @@
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE TemplateHaskell #-}
+
+{- |
+
+Module : Analyze.Analyze
+Description : Parse sequence file formats and analyze them
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Oct 5 08:41:05 2018.
+
+-}
+
+module Examine.Examine
+ ( examineCmd
+ )
+ where
+
+import Control.Monad.Logger
+import Control.Monad.Trans.Class
+import Control.Monad.Trans.Reader
+import qualified Data.ByteString.Lazy.Char8 as L
+import Text.Printf
+
+import Examine.Options
+import Tools
+
+import ELynx.Data.Sequence.MultiSequenceAlignment
+import ELynx.Data.Sequence.Sequence
+import ELynx.Tools.InputOutput
+
+examineMSA :: Bool -> MultiSequenceAlignment -> L.ByteString
+examineMSA perSiteFlag msa =
+ L.unlines [ L.pack $ "Total number of columns in alignment: "
+ ++ show (msaLength msa)
+ , L.pack $ "Number of columns without gaps: "
+ ++ show (msaLength msaNoGaps)
+ , L.pack $ "Number of columns with standard characters only: "
+ ++ show (msaLength msaOnlyStd)
+ , L.empty
+ , L.pack $ "Total number of characters: " ++ show nTot
+ , L.pack $ "Standard (i.e., not extended IUPAC) characters: "
+ ++ show (nTot - nIUPAC - nGaps - nUnknowns)
+ , L.pack $ "Extended IUPAC characters: " ++ show nIUPAC
+ , L.pack $ "Gaps: " ++ show nGaps
+ , L.pack $ "Unknowns: " ++ show nUnknowns
+ , L.pack $ "Percentage of standard characters: "
+ ++ printf "%.3f" (1.0 - percentageIUPAC - percentageGaps - percentageUnknowns)
+ , L.pack $ "Percentage of extended IUPAC characters: "
+ ++ printf "%.3f" percentageIUPAC
+ , L.pack $ "Percentage of gaps: "
+ ++ printf "%.3f" percentageGaps
+ , L.pack $ "Percentage of unknowns: "
+ ++ printf "%.3f" percentageUnknowns
+ , L.empty
+ , L.pack "Mean effective number of states (measured using entropy):"
+ , L.pack "Across whole alignment: "
+ <> L.pack (printf "%.3f" kEffMean)
+ , L.pack "Across columns without gaps: "
+ <> L.pack (printf "%.3f" kEffMeanNoGaps)
+ , L.pack "Across columns without extended IUPAC characters: "
+ <> L.pack (printf "%.3f" kEffMeanOnlyStd)
+ ]
+ <> perSiteBS
+ where
+ nTot = msaLength msa * msaNSequences msa
+ nIUPAC = countIUPACChars msa
+ nGaps = countGaps msa
+ nUnknowns = countUnknowns msa
+ percentageIUPAC = fromIntegral nIUPAC / fromIntegral nTot :: Double
+ percentageGaps = fromIntegral nGaps / fromIntegral nTot :: Double
+ percentageUnknowns = fromIntegral nUnknowns / fromIntegral nTot :: Double
+ msaNoGaps = filterColumnsNoGaps msa
+ msaOnlyStd = filterColumnsOnlyStd msaNoGaps
+ kEffs = kEffEntropy . toFrequencyData $ msa
+ kEffsNoGaps = kEffEntropy . toFrequencyData $ msaNoGaps
+ kEffsOnlyStd = kEffEntropy . toFrequencyData $ msaOnlyStd
+ kEffMean = sum kEffs / fromIntegral (length kEffs)
+ kEffMeanNoGaps = sum kEffsNoGaps / fromIntegral (length kEffsNoGaps)
+ kEffMeanOnlyStd = sum kEffsOnlyStd / fromIntegral (length kEffsOnlyStd)
+ perSiteBS = if perSiteFlag
+ then L.unlines [ L.pack "Effective number of used states per site:"
+ , L.pack . show $ kEffs
+ ]
+ else L.empty
+
+examine :: Bool -> [Sequence] -> L.ByteString
+examine perSiteFlag ss = summarizeSequenceList ss <>
+ case fromSequenceList ss of
+ Left _ -> L.empty
+ Right msa -> L.pack "\n" <> examineMSA perSiteFlag msa
+
+-- | Examine sequences.
+examineCmd :: Maybe FilePath -> Examine ()
+examineCmd outFileBaseName = do
+ $(logInfo) "Command: Examine sequences."
+ ExamineArguments al inFile perSiteFlag <- lift ask
+ ss <- readSeqs al inFile
+ let result = examine perSiteFlag ss
+ let outFilePath = (++ ".out") <$> outFileBaseName
+ io "result of examination" result outFilePath
diff --git a/src/Examine/Options.hs b/src/Examine/Options.hs
new file mode 100644
--- /dev/null
+++ b/src/Examine/Options.hs
@@ -0,0 +1,54 @@
+{- |
+Module : Examine.Options
+Description : ELynxSeq argument parsing
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Sun Oct 7 17:29:45 2018.
+
+-}
+
+module Examine.Options
+ ( ExamineArguments (..)
+ , Examine
+ , examineArguments
+ ) where
+
+import Control.Applicative
+import Control.Monad.Logger
+import Control.Monad.Trans.Reader
+import Options.Applicative
+
+import Tools
+
+import ELynx.Data.Alphabet.Alphabet
+
+-- | Arguments needed to examine sequences.
+data ExamineArguments = ExamineArguments
+ { exAlphabet :: Alphabet
+ , exInFile :: Maybe FilePath
+ , exPerSite :: Bool }
+
+-- | Logger and Reader type.
+type Examine = LoggingT (ReaderT ExamineArguments IO)
+
+-- | Command line parser.
+examineArguments :: Parser ExamineArguments
+examineArguments = ExamineArguments
+ <$> alphabetOpt
+ <*> optional filePathArg
+ <*> examinePerSiteOpt
+
+examinePerSiteOpt :: Parser Bool
+examinePerSiteOpt = switch $
+ long "per-site" <>
+ help "Report per site summary statistics"
+
+filePathArg :: Parser FilePath
+filePathArg = strArgument $
+ metavar "INPUT-FILE" <>
+ help "Read sequences from INPUT-FILE"
diff --git a/src/Filter/Filter.hs b/src/Filter/Filter.hs
new file mode 100644
--- /dev/null
+++ b/src/Filter/Filter.hs
@@ -0,0 +1,76 @@
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE TemplateHaskell #-}
+
+{- |
+Module : Analyze.Analyze
+Description : Parse sequence file formats and analyze them
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Oct 5 08:41:05 2018.
+
+-}
+
+module Filter.Filter
+ ( filterRowsCmd
+ , filterColumnsCmd
+ )
+ where
+
+import Control.Monad.Logger
+import Control.Monad.Trans.Class
+import Control.Monad.Trans.Reader
+import qualified Data.ByteString.Lazy.Char8 as L
+import Data.Maybe (fromMaybe)
+import qualified Data.Text as T
+
+import Filter.Options
+import Tools
+
+import ELynx.Data.Sequence.MultiSequenceAlignment
+import ELynx.Data.Sequence.Sequence
+import ELynx.Export.Sequence.Fasta
+import ELynx.Tools.InputOutput
+import ELynx.Tools.Misc
+
+filterRows :: Maybe Int -> Maybe Int -> [Sequence] -> L.ByteString
+filterRows ml ms ss = sequencesToFasta $ compose filters ss
+ where filters = map (fromMaybe id) [filterLongerThan <$> ml, filterShorterThan <$> ms]
+
+-- | Filter sequences.
+filterRowsCmd :: Maybe FilePath -> FilterRows ()
+filterRowsCmd outFileBaseName = do
+ $(logInfo) "Command: Filter sequences of a list of sequences."
+ FilterRowsArguments al inFile long short <- lift ask
+ maybe (return ())
+ (\val -> $(logInfo) $ T.pack $ " Keep sequences longer than " <> show val <> ".") long
+ maybe (return ())
+ (\val -> $(logInfo) $ T.pack $ " Keep sequences shorter than " <> show val <> ".") short
+ ss <- readSeqs al inFile
+ let result = filterRows long short ss
+ let outFilePath = (++ ".fasta") <$> outFileBaseName
+ io "filtered sequences" result outFilePath
+
+filterColumns :: Maybe Double -> [Sequence] -> L.ByteString
+filterColumns ms ss = sequencesToFasta . toSequenceList $ compose filters msa
+ where msa = either error id (fromSequenceList ss)
+ filters = map (fromMaybe id) [ filterColumnsStd <$> ms ]
+
+-- | Filter columns.
+filterColumnsCmd :: Maybe FilePath -> FilterColumns ()
+filterColumnsCmd outFileBaseName = do
+ $(logInfo) "Command: Filter columns of a multi sequence alignment."
+ FilterColumnsArguments al inFile standard <- lift ask
+ case standard of
+ Nothing -> return ()
+ Just p -> $(logInfo) $ T.pack $
+ " Keep columns with a proportion of standard (non-IUPAC) characters larger than "
+ ++ show p ++ "."
+ ss <- readSeqs al inFile
+ let result = filterColumns standard ss
+ let outFilePath = (++ ".fasta") <$> outFileBaseName
+ io "filtered sequences" result outFilePath
diff --git a/src/Filter/Options.hs b/src/Filter/Options.hs
new file mode 100644
--- /dev/null
+++ b/src/Filter/Options.hs
@@ -0,0 +1,88 @@
+{- |
+Module : Filter.Options
+Description : ELynxSeq argument parsing
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Sun Oct 7 17:29:45 2018.
+
+-}
+
+module Filter.Options
+ ( FilterRowsArguments (..)
+ , FilterColumnsArguments (..)
+ , FilterRows
+ , FilterColumns
+ , filterRowsArguments
+ , filterColumnsArguments
+ ) where
+
+import Control.Applicative
+import Control.Monad.Logger
+import Control.Monad.Trans.Reader
+import Options.Applicative
+
+import Tools
+
+import ELynx.Data.Alphabet.Alphabet
+
+-- | Arguments needed for filtering sequences.
+data FilterRowsArguments = FilterRowsArguments
+ { frAlphabet :: Alphabet
+ , frInFile :: Maybe FilePath
+ , frLonger :: Maybe Int
+ , frShorter :: Maybe Int }
+
+-- | Arguments needed for filtering columns of a multi sequence alignment.
+data FilterColumnsArguments = FilterColumnsArguments
+ { fcAlphabet :: Alphabet
+ , fcInFile :: Maybe FilePath
+ , fcStandard :: Maybe Double }
+
+-- | Logger and Reader for sequence filtering.
+type FilterRows = LoggingT (ReaderT FilterRowsArguments IO)
+
+-- | Logger and Reader for column filtering.
+type FilterColumns = LoggingT (ReaderT FilterColumnsArguments IO)
+
+-- | Command line parser.
+filterRowsArguments :: Parser FilterRowsArguments
+filterRowsArguments = FilterRowsArguments
+ <$> alphabetOpt
+ <*> optional inFileArg
+ <*> filterLongerThanOpt
+ <*> filterShorterThanOpt
+
+filterLongerThanOpt :: Parser (Maybe Int)
+filterLongerThanOpt = optional $ option auto $
+ long "longer-than" <>
+ metavar "LENGTH" <>
+ help "Only keep sequences longer than LENGTH"
+
+filterShorterThanOpt :: Parser (Maybe Int)
+filterShorterThanOpt = optional $ option auto $
+ long "shorter-than" <>
+ metavar "LENGTH" <>
+ help "Only keep sequences shorter than LENGTH"
+
+-- | Command line parser.
+filterColumnsArguments :: Parser FilterColumnsArguments
+filterColumnsArguments = FilterColumnsArguments
+ <$> alphabetOpt
+ <*> optional inFileArg
+ <*> filterStandardOpt
+
+filterStandardOpt :: Parser (Maybe Double)
+filterStandardOpt = optional $ option auto $
+ long "standard-chars" <>
+ metavar "DOUBLE" <>
+ help "Keep columns with a proportion standard (non-IUPAC) characters larger than DOUBLE in [0,1]"
+
+inFileArg :: Parser FilePath
+inFileArg = strArgument $
+ metavar "INPUT-FILE" <>
+ help "Read sequences from INPUT-FILE"
diff --git a/src/Simulate/Options.hs b/src/Simulate/Options.hs
new file mode 100644
--- /dev/null
+++ b/src/Simulate/Options.hs
@@ -0,0 +1,168 @@
+{- |
+Module : Simulate.Options
+Description : ELynxSim argument parsing
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Sun Oct 7 17:29:45 2018.
+
+Available options:
+ -h,--help Show this help text
+ -v,--version Show version
+ -t,--tree-file NAME Specify tree file NAME
+ -s,--substitution-model MODEL
+ Set the phylogenetic substitution model; available
+ models are shown below
+ -m,--mixture-model MODEL Set the phylogenetic mixture model; available models
+ are shown below
+ -l,--length NUMBER Set alignment length to NUMBER
+ -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
+ -e,--seed [INT] Set seed for the random number generator; list of 32
+ bit integers with up to 256 elements (default: [0])
+ -q,--quiet Be quiet
+ -o,--output-file NAME Specify output file NAME
+
+
+-}
+
+
+module Simulate.Options
+ ( GammaRateHeterogeneityParams
+ , SimulateArguments (..)
+ , Simulate
+ , simulateArguments
+ , simulateFooter
+ ) where
+
+import Control.Monad.Logger
+import Control.Monad.Trans.Reader
+import Data.List
+import Data.Word
+import Options.Applicative
+
+import ELynx.Tools.Options
+
+-- | Number of gamma rate categories and alpha parameter.
+type GammaRateHeterogeneityParams = (Int, Double)
+
+-- | Arguments needed to simulate sequences.
+data SimulateArguments = SimulateArguments
+ { argsTreeFile :: FilePath
+ , argsSubstitutionModelString :: Maybe String
+ , argsMixtureModelString :: Maybe String
+ , argsEDMFile :: Maybe FilePath
+ , argsMixtureWeights :: Maybe [Double]
+ , argsGammaParams :: Maybe GammaRateHeterogeneityParams
+ , argsLength :: Int
+ , argsMaybeSeed :: Maybe [Word32]
+ }
+
+-- | A simulation can log stuff and read the necessary arguments.
+type Simulate = LoggingT (ReaderT SimulateArguments IO)
+
+-- | Sub command parser.
+simulateArguments :: Parser SimulateArguments
+simulateArguments = SimulateArguments
+ <$> treeFileOpt
+ <*> phyloSubstitutionModelOpt
+ <*> phyloMixtureModelOpt
+ <*> maybeEDMFileOpt
+ <*> maybeMixtureWeights
+ <*> maybeGammaParams
+ <*> lengthOpt
+ <*> seedOpt
+
+treeFileOpt :: Parser FilePath
+treeFileOpt = strOption $
+ long "tree-file"
+ <> short 't'
+ <> metavar "Name"
+ <> help "Read trees from file NAME"
+
+phyloSubstitutionModelOpt :: Parser (Maybe String)
+phyloSubstitutionModelOpt = optional $ strOption $
+ long "substitution-model"
+ <> short 's'
+ <> metavar "MODEL"
+ <> help "Set the phylogenetic substitution model; available models are shown below (mutually exclusive with -m option)"
+
+phyloMixtureModelOpt :: Parser (Maybe String)
+phyloMixtureModelOpt = optional $ strOption
+ ( long "mixture-model"
+ <> short 'm'
+ <> metavar "MODEL"
+ <> help "Set the phylogenetic mixture model; available models are shown below (mutually exclusive with -s option)" )
+
+maybeEDMFileOpt :: Parser (Maybe FilePath)
+maybeEDMFileOpt = optional $ strOption
+ ( long "edm-file"
+ <> short 'e'
+ <> metavar "NAME"
+ <> help "Empirical distribution model file NAME in Phylobayes format" )
+
+maybeMixtureWeights :: Parser (Maybe [Double])
+maybeMixtureWeights = optional $ option auto
+ ( long "mixture-model-weights"
+ <> short 'w'
+ <> metavar "\"[DOUBLE,DOUBLE,...]\""
+ <> help "Weights of mixture model components" )
+
+maybeGammaParams :: Parser (Maybe GammaRateHeterogeneityParams)
+maybeGammaParams = optional $ option auto
+ ( long "gamma-rate-heterogeneity"
+ <> short 'g'
+ <> metavar "\"(NCAT,SHAPE)\""
+ <> help "Number of gamma rate categories and shape parameter" )
+
+lengthOpt :: Parser Int
+lengthOpt = option auto
+ ( long "length"
+ <> short 'l'
+ <> metavar "NUMBER"
+ <> help "Set alignment length to NUMBER" )
+
+-- | The model specification is somewhat complicated, so we need to provide
+-- additional help.
+simulateFooter :: String
+simulateFooter = intercalate "\n" $ sms ++ mms
+ where
+ sms =
+ [ "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{...}"
+ ]
+ mms =
+ [ ""
+ , "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."
+ ]
diff --git a/src/Simulate/PhyloModel.hs b/src/Simulate/PhyloModel.hs
new file mode 100644
--- /dev/null
+++ b/src/Simulate/PhyloModel.hs
@@ -0,0 +1,188 @@
+{- |
+Module : Simulate.PhyloModel
+Description : Parse and interpret the model string
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Feb 1 13:32:16 2019.
+
+-}
+
+module Simulate.PhyloModel
+ ( getPhyloModel
+ ) where
+
+import qualified Data.ByteString.Lazy.Char8 as L
+import Data.Maybe
+import Data.Void
+import Data.Word (Word8)
+import Numeric.LinearAlgebra (norm_1, size,
+ vector)
+import Text.Megaparsec
+import Text.Megaparsec.Byte
+import Text.Megaparsec.Byte.Lexer
+
+import ELynx.Data.MarkovProcess.AminoAcid
+import ELynx.Data.MarkovProcess.CXXModels
+import qualified ELynx.Data.MarkovProcess.MixtureModel as M
+import ELynx.Data.MarkovProcess.Nucleotide
+import qualified ELynx.Data.MarkovProcess.PhyloModel as P
+import ELynx.Data.MarkovProcess.RateMatrix
+import qualified ELynx.Data.MarkovProcess.SubstitutionModel as S
+import ELynx.Import.MarkovProcess.EDMModelPhylobayes (EDMComponent)
+import ELynx.Tools.ByteString
+import ELynx.Tools.Equality
+import ELynx.Tools.InputOutput
+
+type Parser = Parsec Void L.ByteString
+
+bs :: String -> L.ByteString
+bs = L.pack
+
+nNuc :: Int
+-- nNuc = length (alphabet :: [Nucleotide])
+nNuc = 4
+
+nAA :: Int
+-- nAA = length (alphabet :: [AminoAcid])
+nAA = 20
+
+-- Model parameters between square brackets.
+paramsStart :: Word8
+paramsStart = c2w '['
+
+paramsEnd :: Word8
+paramsEnd = c2w ']'
+
+-- Stationary distribution between curly brackets.
+sdStart :: Word8
+sdStart = c2w '{'
+
+sdEnd :: Word8
+sdEnd = c2w '}'
+
+-- Mixture model components between round brackets.
+mmStart :: Word8
+mmStart = c2w '('
+
+mmEnd :: Word8
+mmEnd = c2w ')'
+
+separator :: Word8
+separator = c2w ','
+
+name :: Parser String
+name = L.unpack <$>
+ takeWhile1P (Just "Model name") (`notElem` [paramsStart, paramsEnd, sdStart, sdEnd, mmStart, mmEnd, separator])
+
+params :: Parser [Double]
+params = between (char paramsStart) (char paramsEnd) (sepBy1 float (char separator))
+
+stationaryDistribution :: Parser StationaryDistribution
+stationaryDistribution = do
+ f <- vector <$> between (char sdStart) (char sdEnd) (sepBy1 float (char separator))
+ if nearlyEq (norm_1 f) 1.0
+ then return f
+ else error $ "Sum of stationary distribution is " ++ show (norm_1 f)
+ ++ " but should be 1.0."
+
+assertLength :: StationaryDistribution -> Int -> a -> a
+assertLength d n r = if size d /= n
+ then error $ "Length of stationary distribution is " ++ show (size d)
+ ++ " but should be " ++ show n ++ "."
+ else r
+
+-- This is the main function that connects the model string, the parameters and
+-- the stationary distribution. It should check that the model is valid.
+assembleSubstitutionModel :: String -> Maybe S.Params -> Maybe StationaryDistribution
+ -> Either String S.SubstitutionModel
+-- DNA models.
+assembleSubstitutionModel "JC" Nothing Nothing = Right jc
+assembleSubstitutionModel "HKY" (Just [k]) (Just d) = Right $ assertLength d nNuc $ hky k d
+-- Protein models.
+assembleSubstitutionModel "LG" Nothing Nothing = Right lg
+assembleSubstitutionModel "LG-Custom" Nothing (Just d) = Right $ assertLength d nAA $ lgCustom Nothing d
+assembleSubstitutionModel "WAG" Nothing Nothing = Right wag
+assembleSubstitutionModel "WAG-Custom" Nothing (Just d) = Right $ assertLength d nAA $ wagCustom Nothing d
+assembleSubstitutionModel "Poisson" Nothing Nothing = Right poisson
+assembleSubstitutionModel "Poisson-Custom" Nothing (Just d) = Right $ assertLength d nAA $ poissonCustom Nothing d
+-- Ohterwisse, we cannot assemble the model.
+assembleSubstitutionModel n mps mf = Left $ unlines
+ [ "Cannot assemble substitution model. "
+ , "Name: " ++ show n
+ , "Parameters: " ++ show mps
+ , "Stationary distribution: " ++ show mf ]
+
+parseSubstitutionModel :: Parser S.SubstitutionModel
+parseSubstitutionModel = do
+ n <- name
+ mps <- optional params
+ mf <- optional stationaryDistribution
+ let esm = assembleSubstitutionModel n mps mf
+ case esm of
+ Left err -> fail err
+ Right sm -> return sm
+
+edmModel :: [EDMComponent] -> Maybe [M.Weight] -> Parser M.MixtureModel
+edmModel cs mws = do
+ _ <- chunk (bs "EDM")
+ _ <- char mmStart
+ n <- name
+ mps <- optional params
+ _ <- char mmEnd
+ let sms = map (\c -> assembleSubstitutionModel n mps (Just $ snd c)) cs
+ edmName = "EDM" ++ show (length cs)
+ ws = fromMaybe (map fst cs) mws
+ errs = [ e | (Left e) <- sms ]
+ if not $ null errs
+ then fail $ head errs
+ else return $ M.MixtureModel edmName
+ [ M.Component w sm | (w, Right sm) <- zip ws sms ]
+
+cxxModel :: Maybe [M.Weight] -> Parser M.MixtureModel
+cxxModel mws = do
+ _ <- char (c2w 'C')
+ n <- decimal :: Parser Int
+ case cxx n mws of
+ Nothing -> fail "Only 10, 20, 30, 40, 50, and 60 components are supported."
+ Just m -> return m
+
+standardMixtureModel :: [M.Weight] -> Parser M.MixtureModel
+standardMixtureModel ws = do
+ _ <- chunk (bs "MIXTURE")
+ _ <- char mmStart
+ sms <- parseSubstitutionModel `sepBy1` char separator
+ _ <- char mmEnd
+ return $ M.MixtureModel "MIXTURE"
+ [ M.Component w sm | (w, sm) <- zip ws sms]
+
+mixtureModel :: Maybe [EDMComponent] -> Maybe [M.Weight] -> Parser M.MixtureModel
+mixtureModel Nothing Nothing = try (cxxModel Nothing) <|> fail "No weights provided."
+mixtureModel Nothing mws@(Just ws) = try (cxxModel mws) <|> standardMixtureModel ws
+mixtureModel (Just cs) mws = edmModel cs mws
+
+-- | Parse the phylogenetic model string. The argument list is somewhat long,
+-- but models can have many parameters and we have to check for redundant
+-- parameters.
+--
+-- @
+-- getPhyloModel maybeSubstitutionModelString maybeMixtureModelString maybeEDMComponents
+-- @
+getPhyloModel :: Maybe String -> Maybe String -> Maybe [M.Weight] -> Maybe [EDMComponent]
+ -> Either String P.PhyloModel
+getPhyloModel Nothing Nothing _ _ =
+ Left "No model was given. See help."
+getPhyloModel (Just _) (Just _) _ _ =
+ Left "Both, substitution and mixture model string given; use only one."
+getPhyloModel (Just s) Nothing Nothing Nothing =
+ Right $ P.SubstitutionModel $ parseStringWith "Substitution model string" parseSubstitutionModel s
+getPhyloModel (Just _) Nothing (Just _) _ =
+ Left "Weights given; but cannot be used with substitution model."
+getPhyloModel (Just _) Nothing _ (Just _) =
+ Left "Empirical distribution mixture model components given; but cannot be used with substitution model."
+getPhyloModel Nothing (Just m) mws mcs =
+ Right $ P.MixtureModel $ parseStringWith "Mixture model string" (mixtureModel mcs mws) m
diff --git a/src/Simulate/Simulate.hs b/src/Simulate/Simulate.hs
new file mode 100644
--- /dev/null
+++ b/src/Simulate/Simulate.hs
@@ -0,0 +1,158 @@
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE TemplateHaskell #-}
+
+{- |
+Module : Simulate.Simulate
+Description : Simulate multiple sequence alignments
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Mon Jan 28 14:12:52 2019.
+
+-}
+
+module Simulate.Simulate
+ ( simulateCmd )
+where
+
+import Control.Concurrent
+import Control.Concurrent.Async
+import Control.Lens
+import Control.Monad.IO.Class
+import Control.Monad.Logger
+import Control.Monad.Trans.Class
+import Control.Monad.Trans.Reader
+import qualified Data.ByteString.Lazy as L
+import qualified Data.ByteString.Lazy.Char8 as LC
+import qualified Data.Set as Set
+import qualified Data.Text as T
+import qualified Data.Text.Lazy as LT
+import qualified Data.Text.Lazy.Encoding as LT
+import Data.Tree
+import qualified Data.Vector.Unboxed as V
+import Numeric.LinearAlgebra hiding ((<>))
+import System.Random.MWC
+
+import Simulate.Options
+import Simulate.PhyloModel
+
+import ELynx.Data.Alphabet.Alphabet as A
+import ELynx.Data.MarkovProcess.GammaRateHeterogeneity
+import qualified ELynx.Data.MarkovProcess.MixtureModel as M
+import qualified ELynx.Data.MarkovProcess.PhyloModel as P
+import qualified ELynx.Data.MarkovProcess.SubstitutionModel as S
+import ELynx.Data.Sequence.MultiSequenceAlignment
+import ELynx.Data.Sequence.Sequence hiding (name)
+import ELynx.Data.Tree.MeasurableTree
+import ELynx.Data.Tree.NamedTree
+import ELynx.Data.Tree.Tree
+import ELynx.Export.Sequence.Fasta
+import ELynx.Import.MarkovProcess.EDMModelPhylobayes hiding (Parser)
+import ELynx.Import.Tree.Newick hiding (name)
+import ELynx.Simulate.MarkovProcessAlongTree
+
+import ELynx.Tools.ByteString
+import ELynx.Tools.Concurrent
+import ELynx.Tools.InputOutput
+import ELynx.Tools.Misc
+
+-- Simulate a 'MultiSequenceAlignment' for a given phylogenetic model,
+-- phylogenetic tree, and alignment length.
+simulateMSA :: (Measurable a, Named a)
+ => P.PhyloModel -> Tree a -> Int -> GenIO
+ -> IO MultiSequenceAlignment
+simulateMSA pm t n g = do
+ c <- getNumCapabilities
+ gs <- splitGen c g
+ let chunks = getChunks c n
+ leafStatesS <- case pm of
+ P.SubstitutionModel sm -> mapConcurrently
+ (\(num, gen) -> simulateAndFlattenNSitesAlongTree num d e t gen) (zip chunks gs)
+ where d = sm ^. S.stationaryDistribution
+ e = sm ^. S.exchangeabilityMatrix
+ P.MixtureModel mm -> mapConcurrently
+ (\(num, gen) -> simulateAndFlattenNSitesAlongTreeMixtureModel num ws ds es t gen) (zip chunks gs)
+ where
+ ws = vector $ M.getWeights mm
+ ds = map (view S.stationaryDistribution) $ M.getSubstitutionModels mm
+ es = map (view S.exchangeabilityMatrix) $ M.getSubstitutionModels mm
+ -- XXX: The horizontal concatenation might be slow. If so, 'concatenateSeqs'
+ -- or 'concatenateMSAs' can be used, which directly appends vectors.
+ let leafStates = horizontalConcat leafStatesS
+ leafNames = map getName $ leaves t
+ code = P.getAlphabet pm
+ -- XXX: Probably use type safe stuff here?
+ alph = A.all $ alphabetSpec code
+ sequences = [ Sequence sName code (V.fromList $ map (`Set.elemAt` alph) ss) |
+ (sName, ss) <- zip leafNames leafStates ]
+ return $ either error id $ fromSequenceList sequences
+
+-- Summarize EDM components; line to be printed to screen or log.
+summarizeEDMComponents :: [EDMComponent] -> L.ByteString
+summarizeEDMComponents cs = LC.pack
+ $ "Empiricial distribution mixture model with "
+ ++ show (length cs) ++ " components."
+
+-- XXX. Maybe provide human readable model file. But then, why is this
+-- necessary. A human readable summary is reported anyways, and for Protein
+-- models the exchangeabilities are too many.
+reportModel :: Maybe FilePath -> P.PhyloModel -> Simulate ()
+reportModel outFn m = do
+ let modelFn = (<> ".model") <$> outFn
+ io "model definition (machine readable)" (bsShow m <> "\n") modelFn
+
+-- | Simulate sequences.
+simulateCmd :: Maybe FilePath -> Simulate ()
+simulateCmd outFn = do
+ a <- lift ask
+ $(logInfo) "Read tree."
+ let treeFile = argsTreeFile a
+ tree <- liftIO $ parseFileWith newick treeFile
+ $(logInfo) $ LT.toStrict $ LT.decodeUtf8 $ summarize tree
+
+ let edmFile = argsEDMFile a
+ edmCs <- case edmFile of
+ Nothing -> return Nothing
+ Just edmF -> do
+ $(logInfo) "Read EDM file."
+ liftIO $ Just <$> parseFileWith phylobayes edmF
+ maybe (return ()) ($(logInfo) . LT.toStrict . LT.decodeUtf8 . summarizeEDMComponents) edmCs
+
+ $(logInfo) "Read model string."
+ let ms = argsSubstitutionModelString a
+ mm = argsMixtureModelString a
+ mws = argsMixtureWeights a
+ eitherPhyloModel' = getPhyloModel ms mm mws edmCs
+ phyloModel' <- case eitherPhyloModel' of
+ Left err -> lift $ error err
+ Right pm -> return pm
+
+ let maybeGammaParams = argsGammaParams a
+ phyloModel <- case maybeGammaParams of
+ Nothing -> do
+ $(logInfo) $ LT.toStrict $ LT.decodeUtf8
+ $ LC.unlines $ P.summarize phyloModel'
+ return phyloModel'
+ Just (n, alpha) -> do
+ $(logInfo) $ LT.toStrict $ LT.decodeUtf8
+ $ LC.unlines $ P.summarize phyloModel' ++ summarizeGammaRateHeterogeneity n alpha
+ return $ expand n alpha phyloModel'
+ reportModel outFn phyloModel
+
+ $(logInfo) "Simulate alignment."
+ let alignmentLength = argsLength a
+ $(logInfo) $ T.pack $ "Length: " <> show alignmentLength <> "."
+ let maybeSeed = argsMaybeSeed a
+ gen <- case maybeSeed of
+ Nothing -> $(logInfo) "Seed: random"
+ >> liftIO createSystemRandom
+ Just s -> $(logInfo) (T.pack ("Seed: " <> show s <> "."))
+ >> liftIO (initialize (V.fromList s))
+ msa <- liftIO $ simulateMSA phyloModel tree alignmentLength gen
+ let output = (sequencesToFasta . toSequenceList) msa
+ outFile = (<> ".fasta") <$> outFn
+ io "simulated multi sequence alignment" output outFile
diff --git a/src/SubSample/Options.hs b/src/SubSample/Options.hs
new file mode 100644
--- /dev/null
+++ b/src/SubSample/Options.hs
@@ -0,0 +1,69 @@
+{- |
+Module : SubSample.Options
+Description : ELynxSeq argument parsing
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Sun Oct 7 17:29:45 2018.
+
+-}
+
+module SubSample.Options
+ ( SubSampleArguments (..)
+ , SubSample
+ , subSampleArguments
+ ) where
+
+import Control.Applicative
+import Control.Monad.Logger
+import Control.Monad.Trans.Reader
+import Data.Word
+import Options.Applicative
+
+import Tools
+
+import ELynx.Data.Alphabet.Alphabet
+import ELynx.Tools.Options
+
+-- | Data structure holding the Command line arguments.
+data SubSampleArguments = SubSampleArguments
+ { ssAlphabet :: Alphabet
+ , ssInFile :: Maybe FilePath
+ , ssNSites :: Int
+ , ssNAlignments :: Int
+ , ssMbSeed :: Maybe [Word32] }
+
+-- | The sub sample command can log stuff and read necessary arguments.
+type SubSample = LoggingT (ReaderT SubSampleArguments IO)
+
+-- | Sub command parser.
+subSampleArguments :: Parser SubSampleArguments
+subSampleArguments = SubSampleArguments
+ <$> alphabetOpt
+ <*> optional filePathArg
+ <*> subSampleNSitesOpt
+ <*> subSampleNAlignmentsOpt
+ <*> seedOpt
+
+subSampleNSitesOpt :: Parser Int
+subSampleNSitesOpt = option auto $
+ long "number-of-sites" <>
+ short 'n' <>
+ metavar "INT" <>
+ help "Number of sites randomly drawn with replacement"
+
+subSampleNAlignmentsOpt :: Parser Int
+subSampleNAlignmentsOpt = option auto $
+ long "number-of-alignments" <>
+ short 'm' <>
+ metavar "INT" <>
+ help "Number of multi sequence alignments to be created"
+
+filePathArg :: Parser FilePath
+filePathArg = strArgument $
+ metavar "INPUT-FILE" <>
+ help "Read sequences from INPUT-FILE"
diff --git a/src/SubSample/SubSample.hs b/src/SubSample/SubSample.hs
new file mode 100644
--- /dev/null
+++ b/src/SubSample/SubSample.hs
@@ -0,0 +1,70 @@
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE TemplateHaskell #-}
+
+{- |
+Module : Analyze.Analyze
+Description : Parse sequence file formats and analyze them
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Oct 5 08:41:05 2018.
+
+-}
+
+module SubSample.SubSample
+ ( subSampleCmd
+ )
+where
+
+import Control.Monad
+import Control.Monad.IO.Class
+import Control.Monad.Logger
+import Control.Monad.Trans.Class
+import Control.Monad.Trans.Reader
+import qualified Data.Text as T
+import qualified Data.Text.Lazy as LT
+import qualified Data.Text.Lazy.Builder as LT
+import qualified Data.Text.Lazy.Builder.Int as LT
+import qualified Data.Vector as V
+import System.Random.MWC
+
+import SubSample.Options
+import Tools
+
+import ELynx.Data.Sequence.MultiSequenceAlignment
+import ELynx.Export.Sequence.Fasta
+import ELynx.Tools.InputOutput
+
+-- | Get a given number of output file names with provided suffix.
+--
+-- > getOutFilePaths "BasePath" 11 "fasta"
+--
+-- Will result in @BasePath.00.fasta@ up to @BasePath.10.fasta@.
+getOutFilePaths :: String -> Int -> String -> [FilePath]
+getOutFilePaths file n suffix = [ file ++ "." ++ digitStr i ++ "." ++ suffix
+ | i <- [0 .. n-1] ]
+ where nDigits = ceiling $ logBase (10 :: Double) (fromIntegral n)
+ digitStr i = T.unpack $ T.justifyRight nDigits '0' (LT.toStrict $ LT.toLazyText $ LT.decimal i)
+
+-- | Sub sample sequences.
+subSampleCmd :: Maybe FilePath -- ^ Output file base name
+ -> SubSample ()
+subSampleCmd outFileBaseName = do
+ SubSampleArguments al inFile nSites nAlignments seed <- lift ask
+ $(logInfo) "Command: Sub sample from a multi sequence alignment."
+ $(logInfo) $ T.pack $ " Sample " <> show nSites <> " sites."
+ $(logInfo) $ T.pack $ " Sample " <> show nAlignments <> " multi sequence alignments."
+ ss <- readSeqs al inFile
+ gen <- liftIO $ maybe createSystemRandom (initialize . V.fromList) seed
+ let msa = either error id (fromSequenceList ss)
+ samples <- lift $ replicateM nAlignments $ randomSubSample nSites msa gen
+ let results = map (sequencesToFasta . toSequenceList) samples
+ outFilePaths <- case outFileBaseName of
+ Nothing -> return $ repeat Nothing
+ Just fn -> return $ Just <$> getOutFilePaths fn nAlignments "fasta"
+ zipWithM_ (io "sub sampled multi sequence alignments") results outFilePaths
+
diff --git a/src/Tools.hs b/src/Tools.hs
new file mode 100644
--- /dev/null
+++ b/src/Tools.hs
@@ -0,0 +1,53 @@
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE TemplateHaskell #-}
+
+{- |
+Module : Tools
+Description : Common tools for sequence lynx
+Copyright : (c) Dominik Schrempf 2019
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Sat Sep 7 06:24:22 2019.
+
+-}
+
+module Tools
+ ( -- * Tools
+ readSeqs
+ -- * Options
+ , alphabetOpt
+ ) where
+
+import Control.Monad.IO.Class
+import Control.Monad.Logger
+import qualified Data.Text as T
+import Options.Applicative
+
+import ELynx.Data.Alphabet.Alphabet
+import ELynx.Data.Sequence.Sequence
+import ELynx.Import.Sequence.Fasta
+import ELynx.Tools.InputOutput
+
+-- | Read sequences of given alphabet from file or standard input.
+readSeqs :: (MonadIO m, MonadLogger m) => Alphabet -> Maybe FilePath -> m [Sequence]
+readSeqs a mfp = do
+ case mfp of
+ Nothing -> $(logInfo) $ T.pack
+ $ "Read sequences from standard input; alphabet "
+ <> show a <> "."
+ Just fp -> $(logInfo) $ T.pack
+ $ "Read sequences from file "
+ <> fp <> "; alphabet" <> show a <> "."
+ liftIO $ parseFileOrIOWith (fasta a) mfp
+
+-- | Command line option to specify the alphabet. Used by various commands.
+alphabetOpt :: Parser Alphabet
+alphabetOpt = option auto $
+ long "alphabet" <>
+ short 'a' <>
+ metavar "NAME" <>
+ help "Specify alphabet type NAME"
diff --git a/src/Translate/Options.hs b/src/Translate/Options.hs
new file mode 100644
--- /dev/null
+++ b/src/Translate/Options.hs
@@ -0,0 +1,71 @@
+{- |
+Module : Translate.Options
+Description : ELynxSeq argument parsing
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Sun Oct 7 17:29:45 2018.
+
+-}
+
+module Translate.Options
+ ( TranslateArguments (..)
+ , Translate
+ , translateArguments
+ ) where
+
+import Control.Applicative
+import Control.Monad.Logger
+import Control.Monad.Trans.Reader
+import Data.List
+import Options.Applicative
+
+import Tools
+
+import ELynx.Data.Alphabet.Alphabet
+import ELynx.Data.Character.Codon
+import ELynx.Tools.Misc
+
+-- | Arguments needed to translate sequences.
+data TranslateArguments = TranslateArguments
+ { trAlphabet :: Alphabet
+ , trInFile :: Maybe FilePath
+ , trReadingFrame :: Int
+ , trUniversalCode :: UniversalCode }
+
+-- | Logger and Reader type.
+type Translate = LoggingT (ReaderT TranslateArguments IO)
+
+-- | Command line parser.
+translateArguments :: Parser TranslateArguments
+translateArguments = TranslateArguments <$>
+ alphabetOpt <*>
+ optional inFileArg <*>
+ readingFrameOpt <*>
+ universalCodeOpt
+
+readingFrameOpt :: Parser Int
+readingFrameOpt = option auto $
+ long "reading-frame" <>
+ short 'r' <>
+ metavar "INT" <>
+ help "Reading frame [0|1|2]."
+
+universalCodeOpt :: Parser UniversalCode
+universalCodeOpt = option auto $
+ long "universal-code" <>
+ short 'u' <>
+ metavar "CODE" <>
+ help ("universal code; one of: " ++ codeStr ++ ".")
+ where codes = allValues :: [UniversalCode]
+ codeWords = map show codes
+ codeStr = intercalate ", " codeWords
+
+inFileArg :: Parser FilePath
+inFileArg = strArgument $
+ metavar "INPUT-FILE" <>
+ help "Read sequences from INPUT-FILE"
diff --git a/src/Translate/Translate.hs b/src/Translate/Translate.hs
new file mode 100644
--- /dev/null
+++ b/src/Translate/Translate.hs
@@ -0,0 +1,51 @@
+{-# LANGUAGE OverloadedStrings #-}
+{-# LANGUAGE TemplateHaskell #-}
+
+{- |
+Module : Analyze.Analyze
+Description : Parse sequence file formats and analyze them
+Copyright : (c) Dominik Schrempf 2018
+License : GPL-3
+
+Maintainer : dominik.schrempf@gmail.com
+Stability : unstable
+Portability : portable
+
+Creation date: Fri Oct 5 08:41:05 2018.
+
+-}
+
+module Translate.Translate
+ ( translateCmd
+ )
+ where
+
+import Control.Monad.Logger
+import Control.Monad.Trans.Class
+import Control.Monad.Trans.Reader
+import qualified Data.Text as T
+
+import Tools
+import Translate.Options
+
+import ELynx.Data.Character.Codon
+import ELynx.Data.Sequence.Sequence
+import ELynx.Data.Sequence.Translate
+import ELynx.Export.Sequence.Fasta
+import ELynx.Tools.InputOutput
+
+translateSeqs :: Int -> UniversalCode -> [Sequence] -> [Sequence]
+translateSeqs rf uc = map (translateSeq uc rf)
+
+-- | Translate sequences.
+translateCmd :: Maybe FilePath -> Translate ()
+translateCmd outFileBaseName = do
+ $(logInfo) "Command: Translate sequences to amino acids."
+ TranslateArguments al inFile rf uc <- lift ask
+ $(logInfo) $ T.pack $ " Universal code: " <> show uc <> "."
+ $(logInfo) $ T.pack $ " Reading frame: " <> show rf <> "."
+ $(logInfo) ""
+ ss <- readSeqs al inFile
+ let result = sequencesToFasta $ translateSeqs rf uc ss
+ let outFilePath = (++ ".fasta") <$> outFileBaseName
+ io "translated sequences" result outFilePath