diff --git a/ChangeLog.md b/ChangeLog.md --- a/ChangeLog.md +++ b/ChangeLog.md @@ -5,6 +5,16 @@ ## Unreleased changes +## Version 0.6.0.0 + +- **elynx-tree:** remove parallel folds with layers (`parBranchFoldMapWithLayer` + too special and slow). +- **elynx-tree:** fix various tree instances; add zip trees with appropriate + instances. +- Remove `monad-logger` dependency and implement lighter alternative. +- Significant changes to the tool chain. + + ## Version 0.5.1.0 - **elynx-tree:** new functions `isValidPath`, `isLeaf`, `depth`; add conversion diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ # The ELynx Suite -Version: 0.5.1.0. +Version: 0.6.0.0. Reproducible evolution made easy.

@@ -39,7 +39,7 @@ # Installation -ELynx is written in [Haskell](https://www.haskell.org/) and can be installed with [Stack](https://docs.haskellstack.org/en/stable/README/). +ELynx is written in [Haskell](https://www.haskell.org/) and can be installed with [cabal-install](https://cabal.readthedocs.io/en/3.4/cabal-commands.html) or [Stack](https://docs.haskellstack.org/en/stable/README/). 1. Install Stack with your package manager, or directly from the web page. @@ -67,15 +67,15 @@ [PATH](https://en.wikipedia.org/wiki/PATH_(variable)) environment variable. Then, they can be used directly. -# SLynx +# Get help -Handle evolutionary sequences. +For example: - stack exec slynx -- --help | head -n -16 + slynx --help - ELynx Suite version 0.5.1.0. + ELynx Suite version 0.6.0.0. Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. + Compiled on September 3, 2021, at 20:56 pm, UTC. Usage: slynx [-v|--verbosity VALUE] [-o|--output-file-basename NAME] [-f|--force] [--no-elynx-file] COMMAND @@ -84,7 +84,7 @@ Available options: -h,--help Show this help text -V,--version Show version - -v,--verbosity VALUE Be verbose; one of: Quiet Warning Info Debug + -v,--verbosity VALUE Be verbose; one of: Quiet Warn Info Debug (default: Info) -o,--output-file-basename NAME Specify base name of output file @@ -112,107 +112,33 @@ - Protein (amino acids) - ProteinX (amino acids; including gaps) - ProteinS (amino acids; including gaps, and translation stops) - - -## Concatenate - -Concatenate multi sequence alignments. - - stack exec slynx -- concatenate --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: slynx concatenate (-a|--alphabet NAME) INPUT-FILE - Concatenate sequences found in input files. - - Available options: - -h,--help Show this help text - -V,--version Show version - -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`. - - stack exec slynx -- examine --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: slynx examine (-a|--alphabet NAME) INPUT-FILE [--per-site] - Examine sequences. If data is a multi sequence alignment, additionally analyze columns. - - Available options: - -h,--help Show this help text - -V,--version Show version - -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`. - - stack exec slynx -- filter-rows --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: slynx filter-rows (-a|--alphabet NAME) INPUT-FILE [--longer-than LENGTH] - [--shorter-than LENGTH] [--standard-characters] - Filter rows (or sequences) found in input files. - - Available options: - -h,--help Show this help text - -V,--version Show version - -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 - --standard-characters Only keep sequences containing at least one standard - (i.e., non-IUPAC) character - -h,--help Show this help text - -Filter columns of multi sequence alignments with `filter-columns`. - - stack exec slynx -- filter-columns --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. + - ProteinI (amino acids; including gaps, translation stops, and IUPAC codes) + ELynx + ----- + A Haskell library and tool set for computational biology. The goal of ELynx is + reproducible research. Evolutionary sequences and phylogenetic trees can be + read, viewed, modified and simulated. The command line with all arguments is + logged consistently, and automatically. Data integrity is verified using SHA256 + sums so that validation of past analyses is possible without the need to + recompute the result. - Usage: slynx filter-columns (-a|--alphabet NAME) INPUT-FILE - [--standard-chars DOUBLE] - Filter columns of multi sequence alignments. + slynx Analyze, modify, and simulate evolutionary sequences. + tlynx Analyze, modify, and simulate phylogenetic trees. + elynx Validate and redo past analyses. - Available options: - -h,--help Show this help text - -V,--version Show version - -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 + Get help for sub commands: + slynx examine --help -## Simulate +## Sub command -Simulate sequences with `slynx simulate`. +The documentation of sub commands can be accessed separately: - stack exec slynx -- simulate --help + slynx simulate --help - ELynx Suite version 0.5.1.0. + ELynx Suite version 0.6.0.0. Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. + Compiled on September 3, 2021, at 20:56 pm, UTC. Usage: slynx simulate (-t|--tree-file Name) [-s|--substitution-model MODEL] [-m|--mixture-model MODEL] [-e|--edm-file NAME] @@ -281,315 +207,4 @@ LG exchangeabilities with site profiles (Phylobayes) given in FILES. -m "EDM(LG-Custom)" -p FILES For special mixture models, mixture weights are optional. - - -## Sub-sample - -Sub-sample columns from multi sequence alignments. - - stack exec slynx -- sub-sample --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: slynx sub-sample (-a|--alphabet NAME) INPUT-FILE - (-n|--number-of-sites INT) - (-m|--number-of-alignments INT) [-S|--seed [INT]] - Sub-sample columns from multi sequence alignments. - - Available options: - -h,--help Show this help text - -V,--version Show version - -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 - - Create a given number of multi sequence alignments, each of which contains a given number of random sites drawn from the original multi sequence alignment. - - -## Translate - -Translate sequences. - - stack exec slynx -- translate --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: slynx translate (-a|--alphabet NAME) INPUT-FILE (-r|--reading-frame INT) - (-u|--universal-code CODE) - Translate from DNA to Protein or DNAX to ProteinX. - - Available options: - -h,--help Show this help text - -V,--version Show version - -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. - - stack exec tlynx -- --help | head -n -16 - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: tlynx [-v|--verbosity VALUE] [-o|--output-file-basename NAME] - [-f|--force] [--no-elynx-file] 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 - -f,--force Ignore previous analysis and overwrite existing - output files. - --no-elynx-file Do not write data required to reproduce an analysis. - - Available commands: - compare Compare two phylogenetic trees (compute distances and branch-wise differences). - connect Connect two phylogenetic trees in all ways (possibly honoring constraints). - distance Compute distances between many phylogenetic trees. - examine Compute summary statistics of phylogenetic trees. - shuffle Shuffle a phylogenetic tree (keep coalescent times, but shuffle topology and leaves). - simulate Simulate phylogenetic trees using a birth and death or coalescent process. - - - Available tree file formats: - - Newick Standard: Branch support values are stored in square brackets after branch lengths. - - Newick IqTree: Branch support values are stored as node names after the closing bracket of forests. - - Newick RevBayes: Key-value pairs is provided in square brackets after node names as well as branch lengths. XXX: Key value pairs are ignored at the moment. - - -## Compare - -Compute distances between phylogenetic trees. - - stack exec tlynx -- compare --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: tlynx compare [-n|--normalize] [-b|--bipartitions] [-t|--intersect] - [-f|--newick-format FORMAT] NAMES - Compare two phylogenetic trees (compute distances and branch-wise differences). - - Available options: - -h,--help Show this help text - -V,--version Show version - -n,--normalize Normalize trees before comparison - -b,--bipartitions Print and plot common and missing bipartitions - -t,--intersect Compare intersections; i.e., before comparison, drop - leaves that are not present in the other tree - -f,--newick-format FORMAT - Newick tree format: Standard, IqTree, or RevBayes; - default: Standard; for detailed help, see 'tlynx - --help' - NAMES Tree files - -h,--help Show this help text - - -## Connect - -Connect two phylogenetic tree in all ways (possibly honoring constraints). - - stack exec tlynx -- connect --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: tlynx connect [-f|--newick-format FORMAT] [-c|--contraints CONSTRAINTS] - TREE-FILE-A TREE-FILE-B - Connect two phylogenetic trees in all ways (possibly honoring constraints). - - Available options: - -h,--help Show this help text - -V,--version Show version - -f,--newick-format FORMAT - Newick tree format: Standard, IqTree, or RevBayes; - default: Standard; for detailed help, see 'tlynx - --help' - -c,--contraints CONSTRAINTS - File containing one or more Newick trees to be used - as constraints - TREE-FILE-A File containing the first Newick tree - TREE-FILE-B File containing the second Newick tree - -h,--help Show this help text - - -## Distancce - -Compute distances between many phylogenetic trees. - - stack exec tlynx -- distance --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: tlynx distance (-d|--distance MEASURE) [-n|--normalize] [-t|--intersect] - [-s|--summary-statistics] - [-m|--master-tree-file MASTER-TREE-File] - [-f|--newick-format FORMAT] [INPUT-FILES] - Compute distances between many phylogenetic trees. - - Available options: - -h,--help Show this help text - -V,--version Show version - -d,--distance MEASURE Type of distance to calculate (available distance - measures are listed below) - -n,--normalize Normalize trees before distance calculation; only - affect distances depending on branch lengths - -t,--intersect Compare intersections; i.e., before comparison, drop - leaves that are not present in the other tree - -s,--summary-statistics Report summary statistics only - -m,--master-tree-file MASTER-TREE-File - Compare all trees to the tree in the master tree - file. - -f,--newick-format FORMAT - Newick tree format: Standard, IqTree, or RevBayes; - default: Standard; for detailed help, see 'tlynx - --help' - 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 - - Distance measures: - symmetric Symmetric distance (Robinson-Foulds distance). - incompatible-split[VAL] Incompatible split distance. Collapse branches with (normalized) - support less than 0.0<=VAL<=1.0 before distance calculation; - if, let's say, VAL>0.7, only well supported differences contribute - to the total distance. - branch-score Branch score distance. - - -## Examine - -Compute summary statistics of phylogenetic trees. - - stack exec tlynx -- examine --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: tlynx examine INPUT-FILE [-f|--newick-format FORMAT] - Compute summary statistics of phylogenetic trees. - - Available options: - -h,--help Show this help text - -V,--version Show version - INPUT-FILE Read trees from INPUT-FILE - -f,--newick-format FORMAT - Newick tree format: Standard, IqTree, or RevBayes; - default: Standard; for detailed help, see 'tlynx - --help' - -h,--help Show this help text - - -## Shuffle - -Shuffle a phylogenetic tree (keep coalescent times, but shuffle topology and -leaves). - - stack exec tlynx -- shuffle --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: tlynx shuffle [-f|--newick-format FORMAT] [-n|--replicates N] TREE-FILE - [-S|--seed [INT]] - Shuffle a phylogenetic tree (keep coalescent times, but shuffle topology and leaves). - - Available options: - -h,--help Show this help text - -V,--version Show version - -f,--newick-format FORMAT - Newick tree format: Standard, IqTree, or RevBayes; - default: Standard; for detailed help, see 'tlynx - --help' - -n,--replicates N Number of trees to generate - TREE-FILE File containing a Newick tree - -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 - - -## Simulate - -Simulate phylogenetic trees using birth and death processes. - - stack exec tlynx -- simulate --help - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: tlynx simulate (-t|--nTrees INT) (-n|--nLeaves INT) PROCESS - [-u|--sub-sample DOUBLE] [-s|--summary-statistics] - [-S|--seed [INT]] - Simulate phylogenetic trees using a birth and death or coalescent process. - - Available options: - -h,--help Show this help text - -V,--version Show version - -t,--nTrees INT Number of trees - -n,--nLeaves INT Number of leaves per tree - -u,--sub-sample DOUBLE Perform sub-sampling; see below. - -s,--summary-statistics For each branch, print length and number of children - -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 - - Available processes: - birthdeath Birth and death process - coalescent Coalescent process - - See, for example, 'tlynx simulate birthdeath --help'. - Sub-sample with probability p: - 1. Simulate one big tree with n'=round(n/p), n'>=n, leaves; - 2. Randomly sample sub-trees with n leaves. - (With p=1.0, the same tree is reported over and over again.) - - -# ELynx - -Validate and (optionally) redo past ELynx analyses. - - stack exec elynx -- --help | head -n -16 - - ELynx Suite version 0.5.1.0. - Developed by Dominik Schrempf. - Compiled on June 12, 2021, at 14:54 pm, UTC. - - Usage: elynx COMMAND - Validate and redo past ELynx analyses - - Available options: - -h,--help Show this help text - -V,--version Show version - - Available commands: - validate Validate an ELynx analysis - redo Redo an ELynx analysis diff --git a/slynx.cabal b/slynx.cabal --- a/slynx.cabal +++ b/slynx.cabal @@ -1,77 +1,77 @@ -cabal-version: 2.2 -name: slynx -version: 0.5.1.1 -license: GPL-3.0-or-later -license-file: LICENSE -copyright: Dominik Schrempf (2021) -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 . +cabal-version: 2.2 +name: slynx +version: 0.6.0.0 +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 (2021) +license: GPL-3.0-or-later +license-file: LICENSE +build-type: Simple -category: Bioinformatics -build-type: Simple extra-source-files: README.md ChangeLog.md source-repository head - type: git - location: https://github.com/dschrempf/elynx + type: git + location: https://github.com/dschrempf/elynx library - exposed-modules: - SLynx.Concatenate.Concatenate - SLynx.Concatenate.Options - SLynx.Examine.Examine - SLynx.Examine.Options - SLynx.Filter.Filter - SLynx.Filter.Options - SLynx.Options - SLynx.Simulate.Options - SLynx.Simulate.PhyloModel - SLynx.Simulate.Simulate - SLynx.SLynx - SLynx.SubSample.Options - SLynx.SubSample.SubSample - SLynx.Tools - SLynx.Translate.Options - SLynx.Translate.Translate - - hs-source-dirs: src - other-modules: Paths_slynx - autogen-modules: Paths_slynx - default-language: Haskell2010 - ghc-options: -Wall -Wunused-packages - build-depends: - attoparsec >=0.13.2.5, - base >=4.7 && <5, - bytestring >=0.10.12.0, - containers >=0.6.2.1, - elynx-markov >=0.5.1.1, - elynx-seq >=0.5.1.1, - elynx-tools >=0.5.1.1, - elynx-tree >=0.5.1.1, - hmatrix >=0.20.2, - monad-logger >=0.3.36, - mwc-random >=0.15.0.1, - optparse-applicative >=0.16.1.0, - statistics >=0.15.2.0, - text >=1.2.4.1, - transformers >=0.5.6.2, - vector >=0.12.3.0 + exposed-modules: + SLynx.Concatenate.Concatenate + SLynx.Concatenate.Options + SLynx.Examine.Examine + SLynx.Examine.Options + SLynx.Filter.Filter + SLynx.Filter.Options + SLynx.Options + SLynx.Simulate.Options + SLynx.Simulate.PhyloModel + SLynx.Simulate.Simulate + SLynx.SLynx + SLynx.SubSample.Options + SLynx.SubSample.SubSample + SLynx.Tools + SLynx.Translate.Options + SLynx.Translate.Translate + other-modules: + Paths_slynx + autogen-modules: + Paths_slynx + hs-source-dirs: src + ghc-options: -Wall -Wunused-packages + build-depends: + attoparsec + , base >=4.7 && <5 + , bytestring + , containers + , elynx-markov + , elynx-seq + , elynx-tools + , elynx-tree + , hmatrix + , mwc-random + , optparse-applicative + , statistics + , text + , transformers + , vector + default-language: Haskell2010 executable slynx - main-is: Main.hs - hs-source-dirs: app - other-modules: Paths_slynx - default-language: Haskell2010 - ghc-options: - -Wall -Wunused-packages -threaded -rtsopts -with-rtsopts=-N - - build-depends: - base >=4.7 && <5, - slynx -any + main-is: Main.hs + other-modules: + Paths_slynx + autogen-modules: + Paths_slynx + hs-source-dirs: app + ghc-options: -Wall -Wunused-packages -threaded -rtsopts -with-rtsopts=-N + build-depends: + base >=4.7 && <5 + , slynx + default-language: Haskell2010 diff --git a/src/SLynx/Concatenate/Concatenate.hs b/src/SLynx/Concatenate/Concatenate.hs --- a/src/SLynx/Concatenate/Concatenate.hs +++ b/src/SLynx/Concatenate/Concatenate.hs @@ -17,8 +17,7 @@ ) where -import Control.Monad.Logger -import Control.Monad.Trans.Reader (ask) +import Control.Monad.Trans.Reader import qualified ELynx.Data.Sequence.Sequence as S import ELynx.Export.Sequence.Fasta import ELynx.Tools @@ -28,8 +27,7 @@ -- | Concatenate sequences. concatenateCmd :: ELynx ConcatenateArguments () concatenateCmd = do - (ConcatenateArguments al fps) <- local <$> ask - $(logInfo) "Command: Concatenate sequences." + (ConcatenateArguments al fps) <- reader localArguments sss <- mapM (readSeqs al) fps let result = sequencesToFasta $ S.concatSequences sss out "concatenated multi sequence alignment " result ".fasta" diff --git a/src/SLynx/Examine/Examine.hs b/src/SLynx/Examine/Examine.hs --- a/src/SLynx/Examine/Examine.hs +++ b/src/SLynx/Examine/Examine.hs @@ -18,8 +18,7 @@ ) where -import Control.Monad.Logger -import Control.Monad.Trans.Reader (ask) +import Control.Monad.Trans.Reader import qualified Data.ByteString.Lazy.Char8 as BL import qualified Data.Set as S import qualified Data.Vector.Unboxed as V @@ -157,8 +156,7 @@ -- | Examine sequences. examineCmd :: ELynx ExamineArguments () examineCmd = do - (ExamineArguments al inFile perSiteFlag) <- local <$> ask - $(logInfo) "Command: Examine sequences." + (ExamineArguments al inFile perSiteFlag) <- localArguments <$> ask ss <- readSeqs al inFile let result = examine perSiteFlag ss out "result of examination" result ".out" diff --git a/src/SLynx/Filter/Filter.hs b/src/SLynx/Filter/Filter.hs --- a/src/SLynx/Filter/Filter.hs +++ b/src/SLynx/Filter/Filter.hs @@ -19,11 +19,9 @@ where import Control.Monad (when) -import Control.Monad.Logger -import Control.Monad.Trans.Reader (ask) +import Control.Monad.Trans.Reader import qualified Data.ByteString.Lazy.Char8 as BL import Data.Maybe (fromMaybe) -import qualified Data.Text as T import qualified ELynx.Data.Sequence.Alignment as M import qualified ELynx.Data.Sequence.Sequence as S import ELynx.Export.Sequence.Fasta @@ -41,22 +39,21 @@ -- | Filter sequences. filterRowsCmd :: ELynx FilterRowsArguments () filterRowsCmd = do - (FilterRowsArguments al inFile long short std) <- local <$> ask - $(logInfo) "Command: Filter sequences of a list of sequences." + (FilterRowsArguments al inFile long short std) <- localArguments <$> ask maybe (return ()) ( \val -> - $(logInfo) $ T.pack $ " Keep sequences longer than " <> show val <> "." + logInfoS $ " Keep sequences longer than " <> show val <> "." ) long maybe (return ()) ( \val -> - $(logInfo) $ T.pack $ " Keep sequences shorter than " <> show val <> "." + logInfoS $ " Keep sequences shorter than " <> show val <> "." ) short when std $ - $(logInfo) + logInfoS " Keep sequences containing at least one standard (i.e., non-IUPAC) character." ss <- readSeqs al inFile let result = filterRows long short std ss @@ -71,16 +68,14 @@ -- | Filter columns. filterColsCmd :: ELynx FilterColsArguments () filterColsCmd = do - (FilterColsArguments al inFile standard) <- local <$> ask - $(logInfo) "Command: Filter columns of a multi sequence alignment." + (FilterColsArguments al inFile standard) <- localArguments <$> 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 - ++ "." + logInfoS $ + " Keep columns with a proportion of standard (non-IUPAC) characters larger than " + ++ show p + ++ "." ss <- readSeqs al inFile let result = filterCols standard ss out "filtered sequences" result ".fasta" diff --git a/src/SLynx/SLynx.hs b/src/SLynx/SLynx.hs --- a/src/SLynx/SLynx.hs +++ b/src/SLynx/SLynx.hs @@ -27,35 +27,15 @@ -- | Run SLynx with given arguments. slynx :: Arguments CommandArguments -> IO () slynx c = case local c of - Concatenate _ -> - eLynxWrapper - c - (\(Arguments g (Concatenate l)) -> Arguments g l) - concatenateCmd - Examine _ -> - eLynxWrapper c (\(Arguments g (Examine l)) -> Arguments g l) examineCmd - FilterCols _ -> - eLynxWrapper - c - (\(Arguments g (FilterCols l)) -> Arguments g l) - filterColsCmd - FilterRows _ -> - eLynxWrapper - c - (\(Arguments g (FilterRows l)) -> Arguments g l) - filterRowsCmd - Simulate _ -> - eLynxWrapper c (\(Arguments g (Simulate l)) -> Arguments g l) simulateCmd - SubSample _ -> - eLynxWrapper - c - (\(Arguments g (SubSample l)) -> Arguments g l) - subSampleCmd - Translate _ -> - eLynxWrapper - c - (\(Arguments g (Translate l)) -> Arguments g l) - translateCmd + Concatenate l -> eLynxWrapper g l Concatenate concatenateCmd + Examine l -> eLynxWrapper g l Examine examineCmd + FilterCols l -> eLynxWrapper g l FilterCols filterColsCmd + FilterRows l -> eLynxWrapper g l FilterRows filterRowsCmd + Simulate l -> eLynxWrapper g l Simulate simulateCmd + SubSample l -> eLynxWrapper g l SubSample subSampleCmd + Translate l -> eLynxWrapper g l Translate translateCmd + where + g = global c -- | Run SLynx, parse arguments from command line. rSLynx :: IO () diff --git a/src/SLynx/Simulate/Options.hs b/src/SLynx/Simulate/Options.hs --- a/src/SLynx/Simulate/Options.hs +++ b/src/SLynx/Simulate/Options.hs @@ -60,7 +60,7 @@ argsMixtureWeights :: Maybe [Double], argsGammaParams :: Maybe GammaRateHeterogeneityParams, argsLength :: Int, - argsSeed :: Seed + argsSeed :: SeedOpt } deriving (Eq, Show, Generic) @@ -70,7 +70,7 @@ (maybeToList (argsEDMFile a) ++ fromMaybe [] (argsSiteprofilesFiles a)) outSuffixes _ = [".model.gz", ".fasta"] getSeed = Just . argsSeed - setSeed a s = a {argsSeed = Fixed s} + setSeed a s = a {argsSeed = s} parser = simulateArguments cmdName = "simulate" cmdDsc = ["Simulate multi sequence alignments."] diff --git a/src/SLynx/Simulate/Simulate.hs b/src/SLynx/Simulate/Simulate.hs --- a/src/SLynx/Simulate/Simulate.hs +++ b/src/SLynx/Simulate/Simulate.hs @@ -20,7 +20,6 @@ import Control.Applicative ((<|>)) import Control.Monad import Control.Monad.IO.Class -import Control.Monad.Logger import Control.Monad.Trans.Class import Control.Monad.Trans.Reader (ask) import qualified Data.ByteString.Builder as BB @@ -28,9 +27,6 @@ import Data.List import Data.Maybe 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 qualified Data.Vector as V import qualified Data.Vector.Storable as VS import qualified Data.Vector.Unboxed as U @@ -66,7 +62,7 @@ writeSiteDists :: [Int] -> V.Vector MR.StationaryDistribution -> ELynx SimulateArguments () -- writeSiteDists is ds = out "site distributions of distribution mixture model" output ".sitedists" writeSiteDists componentIs ds = do - mbn <- outFileBaseName . global <$> ask + mbn <- outFileBaseName . globalArguments <$> ask case mbn of Nothing -> return () Just bn -> liftIO $ BL.writeFile (bn <> ".sitedists") output @@ -85,7 +81,7 @@ GenIO -> ELynx SimulateArguments () simulateAlignment pm t' n g = do - let t = fromLength . getLen <$> toTreeBranchLabels t' + let t = fromLength . getLength <$> toTreeBranchLabels t' leafStates <- case pm of MP.SubstitutionModel sm -> liftIO $ simulateAndFlattenPar n d e t g where @@ -110,7 +106,7 @@ | (sName, ss) <- zip leafNames leafStates ] output = sequencesToFasta sequences - $(logInfo) "" + logInfoS "" out "simulated multi sequence alignment" output ".fasta" -- Summarize EDM components; line to be printed to screen or log. @@ -123,19 +119,19 @@ reportModel :: MP.PhyloModel -> ELynx SimulateArguments () reportModel m = do - as <- global <$> ask + as <- globalArguments <$> ask if writeElynxFile as then ( do let bn = outFileBaseName as case bn of Nothing -> - $(logInfo) + logInfoS "No output file provided; omit writing machine-readable phylogenetic model." Just _ -> out "model definition (machine readable)" (BL.pack (show m) <> "\n") ".model.gz" ) - else $(logInfo) "No elynx file required; omit writing machine-readable phylogenetic model." + else logInfoS "No elynx file required; omit writing machine-readable phylogenetic model." pretty :: Length -> String pretty = printf "%.5f" . fromLength @@ -220,46 +216,45 @@ -- | Simulate sequences. simulateCmd :: ELynx SimulateArguments () simulateCmd = do - l <- local <$> ask + l <- localArguments <$> ask let treeFile = argsTreeFile l - $(logInfo) "" - $(logInfo) $ T.pack $ "Read tree from file '" ++ treeFile ++ "'." + logInfoS "" + logInfoS $ "Read tree from file '" ++ treeFile ++ "'." tree <- liftIO $ parseFileWith (newick Standard) treeFile - let t' = either error id $ phyloToLengthTree tree - $(logInfo) $ T.pack $ "Number of leaves: " ++ show (length $ leaves t') - $(logInfo) $ LT.toStrict $ LT.decodeUtf8 $ summarizeLengths t' + let t' = either error id $ toLengthTree tree + logInfoS $ "Number of leaves: " ++ show (length $ leaves t') + logInfoB $ summarizeLengths t' let edmFile = argsEDMFile l let sProfileFiles = argsSiteprofilesFiles l - $(logInfo) "" - $(logDebug) "Read EDM file or siteprofile files." + logInfoS "" + logDebugS "Read EDM file or siteprofile files." when (isJust edmFile && isJust sProfileFiles) $ error "Got both: --edm-file and --siteprofile-files." edmCs <- case edmFile of Nothing -> return Nothing Just edmF -> do - $(logInfo) "Read EDM file." + logInfoS "Read EDM file." liftIO $ Just <$> parseFileWith phylobayes edmF maybe (return ()) - ($(logInfo) . LT.toStrict . LT.decodeUtf8 . summarizeEDMComponents) + (logInfoB . summarizeEDMComponents) edmCs sProfiles <- case sProfileFiles of Nothing -> return Nothing Just fns -> do - $(logInfo) $ - T.pack $ - "Read siteprofiles from " - ++ show (length fns) - ++ " file(s)." - $(logDebug) $ T.pack $ "The file names are:" ++ show fns + logInfoS $ + "Read siteprofiles from " + ++ show (length fns) + ++ " file(s)." + logDebugS $ "The file names are:" ++ show fns xs <- liftIO $ mapM (parseFileWith siteprofiles) fns return $ Just $ concat xs maybe (return ()) - ($(logInfo) . LT.toStrict . LT.decodeUtf8 . summarizeEDMComponents) + (logInfoB . summarizeEDMComponents) sProfiles let edmCsOrSiteprofiles = edmCs <|> sProfiles - $(logInfo) "Read model string." + logInfoS "Read model string." let ms = argsSubstitutionModelString l mm = argsMixtureModelString l mws = argsMixtureWeights l @@ -270,31 +265,19 @@ let maybeGammaParams = argsGammaParams l phyloModel <- case maybeGammaParams of Nothing -> do - $(logInfo) $ - LT.toStrict $ - LT.decodeUtf8 $ - BL.unlines $ - summarizePM - phyloModel' + logInfoB $ BL.unlines $ summarizePM phyloModel' return phyloModel' Just (n, alpha) -> do - $(logInfo) $ - LT.toStrict $ - LT.decodeUtf8 $ - BL.intercalate "\n" $ - summarizePM phyloModel' - $(logInfo) "" - $(logInfo) $ - LT.toStrict $ - LT.decodeUtf8 $ - BL.intercalate "\n" $ - summarizeGammaRateHeterogeneity n alpha + logInfoB $ BL.intercalate "\n" $ summarizePM phyloModel' + logInfoS "" + logInfoB $ BL.intercalate "\n" $ summarizeGammaRateHeterogeneity n alpha return $ expand n alpha phyloModel' reportModel phyloModel - $(logInfo) "Simulate alignment." + logInfoS "Simulate alignment." let alignmentLength = argsLength l - $(logInfo) $ T.pack $ "Length: " <> show alignmentLength <> "." - gen <- case argsSeed l of - Random -> error "simulateCmd: seed not available; please contact maintainer." - Fixed s -> liftIO $ initialize s + logInfoS $ "Length: " <> show alignmentLength <> "." + gen <- liftIO <$> initialize $ case argsSeed l of + RandomUnset -> error "simulateCmd: seed not available; please contact maintainer." + RandomSet s -> s + Fixed s -> s simulateAlignment phyloModel t' alignmentLength gen diff --git a/src/SLynx/SubSample/Options.hs b/src/SLynx/SubSample/Options.hs --- a/src/SLynx/SubSample/Options.hs +++ b/src/SLynx/SubSample/Options.hs @@ -33,7 +33,7 @@ ssInFile :: FilePath, ssNSites :: Int, ssNAlignments :: Int, - ssMbSeed :: Seed + ssMbSeed :: SeedOpt } deriving (Eq, Show, Generic) @@ -55,7 +55,7 @@ inFiles = pure . ssInFile outSuffixes a = getOutSuffixes (ssNAlignments a) "fasta" getSeed = Just . ssMbSeed - setSeed a s = a {ssMbSeed = Fixed s} + setSeed a s = a {ssMbSeed = s} parser = subSampleArguments cmdName = "sub-sample" cmdDsc = ["Sub-sample columns from multi sequence alignments."] diff --git a/src/SLynx/SubSample/SubSample.hs b/src/SLynx/SubSample/SubSample.hs --- a/src/SLynx/SubSample/SubSample.hs +++ b/src/SLynx/SubSample/SubSample.hs @@ -19,9 +19,7 @@ import Control.Monad import Control.Monad.IO.Class -import Control.Monad.Logger import Control.Monad.Trans.Reader (ask) -import qualified Data.Text as T import qualified ELynx.Data.Sequence.Alignment as M import ELynx.Export.Sequence.Fasta import ELynx.Tools @@ -32,14 +30,9 @@ -- | Sub sample sequences. subSampleCmd :: ELynx SubSampleArguments () subSampleCmd = do - (SubSampleArguments al inFile nSites nAlignments (Fixed s)) <- local <$> 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." + (SubSampleArguments al inFile nSites nAlignments (Fixed s)) <- localArguments <$> ask + logInfoS $ " Sample " <> show nSites <> " sites." + logInfoS $ " Sample " <> show nAlignments <> " multi sequence alignments." ss <- readSeqs al inFile gen <- liftIO $ initialize s let a = either error id (M.fromSequences ss) diff --git a/src/SLynx/Tools.hs b/src/SLynx/Tools.hs --- a/src/SLynx/Tools.hs +++ b/src/SLynx/Tools.hs @@ -22,45 +22,25 @@ where import Control.Monad.IO.Class -import Control.Monad.Logger -import qualified Data.Text as T import ELynx.Data.Alphabet.Alphabet import ELynx.Data.Sequence.Sequence import ELynx.Import.Sequence.Fasta import ELynx.Tools import Options.Applicative --- -- | 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 - -- | Read sequences of given alphabet from file or standard input. -readSeqs :: (MonadIO m, MonadLogger m) => Alphabet -> FilePath -> m [Sequence] +readSeqs :: + (HasLock e, HasLogHandles e, HasVerbosity e) => + Alphabet -> + FilePath -> + Logger e [Sequence] readSeqs a fp = do - $(logInfo) $ - T.pack $ - "Read sequences from file " - <> fp - <> "; alphabet " - <> show a - <> "." + logInfoS $ + "Read sequences from file " + <> fp + <> "; alphabet " + <> show a + <> "." liftIO $ parseFileWith (fasta a) fp -- | Command line option to specify the alphabet. Used by various commands. diff --git a/src/SLynx/Translate/Translate.hs b/src/SLynx/Translate/Translate.hs --- a/src/SLynx/Translate/Translate.hs +++ b/src/SLynx/Translate/Translate.hs @@ -17,9 +17,7 @@ ) where -import Control.Monad.Logger -import Control.Monad.Trans.Reader (ask) -import qualified Data.Text as T +import Control.Monad.Trans.Reader import ELynx.Data.Character.Codon import ELynx.Data.Sequence.Sequence import ELynx.Data.Sequence.Translate @@ -34,11 +32,10 @@ -- | Translate sequences. translateCmd :: ELynx TranslateArguments () translateCmd = do - (TranslateArguments al inFile rf uc) <- local <$> ask - $(logInfo) "Command: Translate sequences to amino acids." - $(logInfo) $ T.pack $ " Universal code: " <> show uc <> "." - $(logInfo) $ T.pack $ " Reading frame: " <> show rf <> "." - $(logInfo) "" + (TranslateArguments al inFile rf uc) <- localArguments <$> ask + logInfoS $ " Universal code: " <> show uc <> "." + logInfoS $ " Reading frame: " <> show rf <> "." + logInfoS "" ss <- readSeqs al inFile let result = sequencesToFasta $ translateSeqs rf uc ss out "translated sequences" result "fasta"