diff --git a/ChangeLog.md b/ChangeLog.md --- a/ChangeLog.md +++ b/ChangeLog.md @@ -1,11 +1,18 @@ -# Changelog for ELynx +# Revision history for ELynx ## Unreleased changes +- Improve rooting functions. +- Improve `Topology` data type (but still a lot to do). +- Various additions to the documentation. +- Rename `Measurable` to `HasLength`, `Supported` to `HasSupport`, and `Named` + to `HasLength`. +- Cabal and stack file changes. -## Version 0.5.0 + +## Version 0.5.0.1 - `modLen`, `modSup`. - Newtype wrappers for branch length, branch support, and node name. Those data diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ # The ELynx Suite -Version: 0.5.0. +Version: 0.5.0.1. Reproducible evolution made easy.

@@ -19,18 +19,20 @@ The library packages are: -- **elynx-nexus:** Nexus file support. -- **elynx-markov:** Simulate multi sequence alignments along phylogenetic trees. -- **elynx-seq:** Handle evolutionary sequences and multi sequence alignments. -- **elynx-tools:** Tools for the provided executables. -- **elynx-tree:** Handle phylogenetic trees. +- **[elynx-nexus](https://hackage.haskell.org/package/elynx-nexus):** Nexus file support. +- **[elynx-markov](https://hackage.haskell.org/package/elynx-markov):** Simulate multi sequence alignments along phylogenetic trees. +- **[elynx-seq](https://hackage.haskell.org/package/elynx-seq):** Handle evolutionary sequences and multi sequence alignments. +- **[elynx-tools](https://hackage.haskell.org/package/elynx-tools):** Tools for the provided executables. +- **[elynx-tree](https://hackage.haskell.org/package/elynx-tree):** Handle phylogenetic trees. The executables are: -- **slynx:** Analyze, modify, and simulate evolutionary sequences. -- **tlynx:** Analyze, modify, and simulate phylogenetic trees. -- **elynx:** Validate and redo past analyses. +- **[slynx](https://hackage.haskell.org/package/slynx):** Analyze, modify, and simulate evolutionary sequences. +- **[tlynx](https://hackage.haskell.org/package/tlynx):** Analyze, modify, and simulate phylogenetic trees. +- **[elynx](https://hackage.haskell.org/package/elynx):** Validate and redo past analyses. +Documentation is available on [Hackage](https://hackage.haskell.org/) (use direct links above). + **ELynx is actively developed. We happily receive comments, ideas, feature requests, and pull requests!** @@ -65,34 +67,15 @@ [PATH](https://en.wikipedia.org/wiki/PATH_(variable)) environment variable. Then, they can be used directly. -# Documentation - -Documentation is available on [Hackage](https://hackage.haskell.org/). - -Libraries: - -- [elynx-nexus](https://hackage.haskell.org/package/elynx-nexus) -- [elynx-markov](https://hackage.haskell.org/package/elynx-markov) -- [elynx-seq](https://hackage.haskell.org/package/elynx-seq) -- [elynx-tools](https://hackage.haskell.org/package/elynx-tools) -- [elynx-tree](https://hackage.haskell.org/package/elynx-tree) - -Executables: - -- [elynx](https://hackage.haskell.org/package/elynx) -- [slynx](https://hackage.haskell.org/package/slynx) -- [tlynx](https://hackage.haskell.org/package/tlynx) - - # SLynx Handle evolutionary sequences. slynx --help | head -n -16 - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: slynx [-v|--verbosity VALUE] [-o|--output-file-basename NAME] [-f|--force] [--no-elynx-file] COMMAND @@ -137,9 +120,9 @@ slynx concatenate --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: slynx concatenate (-a|--alphabet NAME) INPUT-FILE Concatenate sequences found in input files. @@ -158,9 +141,9 @@ slynx examine --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: slynx examine (-a|--alphabet NAME) INPUT-FILE [--per-site] Examine sequences. If data is a multi sequence alignment, additionally analyze columns. @@ -180,9 +163,9 @@ slynx filter-rows --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: slynx filter-rows (-a|--alphabet NAME) INPUT-FILE [--longer-than LENGTH] [--shorter-than LENGTH] [--standard-characters] @@ -203,9 +186,9 @@ slynx filter-columns --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: slynx filter-columns (-a|--alphabet NAME) INPUT-FILE [--standard-chars DOUBLE] @@ -227,9 +210,9 @@ slynx simulate --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: slynx simulate (-t|--tree-file Name) [-s|--substitution-model MODEL] [-m|--mixture-model MODEL] [-e|--edm-file NAME] @@ -306,9 +289,9 @@ slynx sub-sample --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: slynx sub-sample (-a|--alphabet NAME) INPUT-FILE (-n|--number-of-sites INT) @@ -336,9 +319,9 @@ slynx translate --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: slynx translate (-a|--alphabet NAME) INPUT-FILE (-r|--reading-frame INT) (-u|--universal-code CODE) @@ -361,9 +344,9 @@ tlynx --help | head -n -16 - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: tlynx [-v|--verbosity VALUE] [-o|--output-file-basename NAME] [-f|--force] [--no-elynx-file] COMMAND @@ -401,9 +384,9 @@ tlynx compare --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: tlynx compare [-n|--normalize] [-b|--bipartitions] [-t|--intersect] [-f|--newick-format FORMAT] NAMES @@ -430,9 +413,9 @@ tlynx examine --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: tlynx examine INPUT-FILE [-f|--newick-format FORMAT] Compute summary statistics of phylogenetic trees. @@ -454,9 +437,9 @@ tlynx simulate --help - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: tlynx simulate (-t|--nTrees INT) (-n|--nLeaves INT) PROCESS [-u|--sub-sample DOUBLE] [-s|--summary-statistics] @@ -491,9 +474,9 @@ elynx --help | head -n -16 - ELynx Suite version 0.5.0. + ELynx Suite version 0.5.0.1. Developed by Dominik Schrempf. - Compiled on November 10, 2020, at 14:29 pm, UTC. + Compiled on December 18, 2020, at 10:14 am, UTC. Usage: elynx COMMAND Validate and redo past ELynx analyses diff --git a/elynx-seq.cabal b/elynx-seq.cabal --- a/elynx-seq.cabal +++ b/elynx-seq.cabal @@ -1,18 +1,19 @@ -cabal-version: 2.2 -name: elynx-seq -version: 0.5.0 -synopsis: Handle molecular sequences -description: Examine, modify, and simulate molecular sequences in a reproducible way. Please see the README on GitHub at . -category: Bioinformatics -homepage: https://github.com/dschrempf/elynx#readme -bug-reports: https://github.com/dschrempf/elynx/issues -author: Dominik Schrempf -maintainer: dominik.schrempf@gmail.com -copyright: Dominik Schrempf (2020) -license: GPL-3.0-or-later -license-file: LICENSE -build-type: Simple +cabal-version: 2.2 +name: elynx-seq +version: 0.5.0.1 +license: GPL-3.0-or-later +license-file: LICENSE +copyright: Dominik Schrempf (2020) +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 @@ -26,72 +27,70 @@ data/TranslateMitochondrialVertebrateProtein.fasta source-repository head - type: git - location: https://github.com/dschrempf/elynx + type: git + location: https://github.com/dschrempf/elynx library - exposed-modules: - ELynx.Data.Alphabet.Alphabet - ELynx.Data.Alphabet.Character - ELynx.Data.Alphabet.DistributionDiversity - ELynx.Data.Character.AminoAcid - ELynx.Data.Character.AminoAcidI - ELynx.Data.Character.AminoAcidS - ELynx.Data.Character.AminoAcidX - ELynx.Data.Character.Character - ELynx.Data.Character.Codon - ELynx.Data.Character.Nucleotide - ELynx.Data.Character.NucleotideI - ELynx.Data.Character.NucleotideX - ELynx.Data.Sequence.Alignment - ELynx.Data.Sequence.Defaults - ELynx.Data.Sequence.Distance - ELynx.Data.Sequence.Sequence - ELynx.Data.Sequence.Translate - ELynx.Export.Sequence.Fasta - ELynx.Import.Sequence.Fasta - other-modules: - Paths_elynx_seq - autogen-modules: - Paths_elynx_seq - hs-source-dirs: - src - ghc-options: -Wall - build-depends: - aeson - , attoparsec - , base >=4.7 && <5 - , bytestring - , containers - , matrices - , mwc-random - , parallel - , primitive - , vector - , vector-th-unbox - , word8 - default-language: Haskell2010 + exposed-modules: + ELynx.Data.Alphabet.Alphabet + ELynx.Data.Alphabet.Character + ELynx.Data.Alphabet.DistributionDiversity + ELynx.Data.Character.AminoAcid + ELynx.Data.Character.AminoAcidI + ELynx.Data.Character.AminoAcidS + ELynx.Data.Character.AminoAcidX + ELynx.Data.Character.Character + ELynx.Data.Character.Codon + ELynx.Data.Character.Nucleotide + ELynx.Data.Character.NucleotideI + ELynx.Data.Character.NucleotideX + ELynx.Data.Sequence.Alignment + ELynx.Data.Sequence.Defaults + ELynx.Data.Sequence.Distance + ELynx.Data.Sequence.Sequence + ELynx.Data.Sequence.Translate + ELynx.Export.Sequence.Fasta + ELynx.Import.Sequence.Fasta + hs-source-dirs: src + other-modules: Paths_elynx_seq + autogen-modules: Paths_elynx_seq + default-language: Haskell2010 + ghc-options: -Wall -Wunused-packages + build-depends: + aeson >=1.5.4.1 && <1.6, + attoparsec >=0.13.2.4 && <0.14, + base >=4.7 && <5, + bytestring >=0.10.10.0 && <0.11, + containers >=0.6.2.1 && <0.7, + matrices >=0.5.0 && <0.6, + mwc-random >=0.14.0.0 && <0.15, + parallel >=3.2.2.0 && <3.3, + primitive >=0.7.1.0 && <0.8, + vector >=0.12.1.2 && <0.13, + vector-th-unbox >=0.2.1.7 && <0.3, + word8 >=0.1.3 && <0.2 + test-suite seq-test - type: exitcode-stdio-1.0 - main-is: Spec.hs - other-modules: - ELynx.Data.Alphabet.DistributionDiversitySpec - ELynx.Data.Sequence.AlignmentSpec - ELynx.Data.Sequence.SequenceSpec - ELynx.Data.Sequence.TranslateSpec - ELynx.Export.Sequence.FastaSpec - ELynx.Import.Sequence.FastaSpec - Paths_elynx_seq - hs-source-dirs: - test - ghc-options: -Wall - build-depends: - base >=4.7 && <5 - , bytestring - , elynx-seq - , elynx-tools - , hspec - , matrices - , vector - default-language: Haskell2010 + type: exitcode-stdio-1.0 + main-is: Spec.hs + hs-source-dirs: test + other-modules: + ELynx.Data.Alphabet.DistributionDiversitySpec + ELynx.Data.Sequence.AlignmentSpec + ELynx.Data.Sequence.SequenceSpec + ELynx.Data.Sequence.TranslateSpec + ELynx.Export.Sequence.FastaSpec + ELynx.Import.Sequence.FastaSpec + Paths_elynx_seq + + default-language: Haskell2010 + ghc-options: -Wall -Wunused-packages + build-depends: + base >=4.7 && <5, + bytestring >=0.10.10.0 && <0.11, + elynx-seq -any, + elynx-tools >=0.5.0.1 && <0.6, + hspec >=2.7.4 && <2.8, + matrices >=0.5.0 && <0.6, + vector >=0.12.1.2 && <0.13 diff --git a/src/ELynx/Data/Alphabet/Alphabet.hs b/src/ELynx/Data/Alphabet/Alphabet.hs --- a/src/ELynx/Data/Alphabet/Alphabet.hs +++ b/src/ELynx/Data/Alphabet/Alphabet.hs @@ -273,7 +273,7 @@ toStdPS '-' = "" toStdPS '.' = "" toStdPS '*' = "" -toStdPS _ = error "toStdPX: Cannot convert to standard amino acid." +toStdPS _ = error "toStdPS: Cannot convert to standard amino acid." proteinI :: AlphabetSpec proteinI = fromChars "ACDEFGHIKLMNPQRSTVWY" "-." "X?" "*JBZ" toStdPI @@ -307,4 +307,4 @@ toStdPI 'Z' = "EQ" toStdPI 'X' = "ACDEFGHIKLMNPQRSTVWY" toStdPI '?' = "ACDEFGHIKLMNPQRSTVWY" -toStdPI _ = error "toStdPX: Cannot convert to standard amino acid." +toStdPI _ = error "toStdPI: Cannot convert to standard amino acid." diff --git a/src/ELynx/Data/Sequence/Alignment.hs b/src/ELynx/Data/Sequence/Alignment.hs --- a/src/ELynx/Data/Sequence/Alignment.hs +++ b/src/ELynx/Data/Sequence/Alignment.hs @@ -244,7 +244,7 @@ -- the number of characters. type FrequencyData = M.Matrix Double --- Map a function on each row of a DIM2 array; parallel version with given chunk size. +-- Map a function on each column of a DIM2 array; parallel version with given chunk size. fMapColParChunk :: (V.Unbox a, V.Unbox b) => Int ->