diff --git a/Changelog.md b/Changelog.md --- a/Changelog.md +++ b/Changelog.md @@ -11,3 +11,5 @@ V 1.4.0: Added single strand mode, and new triallelic treatment. V 1.4.0.1: Improved README, fixed output bug in genoStats.hs + +V 1.4.0.3: Updated to new sequence-formats version, now including reading of genetic position from eigenstrat files. diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -6,13 +6,12 @@ This repository contains some programs that I use for processing sequencing data. -# Installation +# Simple Installation of the main tools 1. Download stack (https://docs.haskellstack.org/en/stable/README/#how-to-install). -2. Clone the repository using `git clone https://github.com/stschiff/sequenceTools.git; cd sequenceTools`. -3. Run `stack install` inside the sequenceTools directory. If everything goes as planned, you should end up having the executables defined in this package under `~/.local/bin`. -4. Add `~/.local/bin` to your PATH, for example by adding to your `~/.profile` or `~/.bash_profile` the line `PATH=$PATH:$HOME/.local/bin`. Run `source ~/.profile` or `source ~/.bash_profile`, respectively, to update your path. -5. Run `pileupCaller --version`. It should output `1.4.0`. You're all set. +2. Run `stack install sequenceTools --resolver nightly`. You should now have the executables from this package under `~/.local/bin`. +3. Add `~/.local/bin` to your PATH, for example by adding to your `~/.profile` or `~/.bash_profile` the line `PATH=$PATH:$HOME/.local/bin`. Run `source ~/.profile` or `source ~/.bash_profile`, respectively, to update your path. +4. Run `pileupCaller --version`. It should output `1.4.0`. You're all set. ## pileupCaller diff --git a/sequenceTools.cabal b/sequenceTools.cabal --- a/sequenceTools.cabal +++ b/sequenceTools.cabal @@ -1,6 +1,6 @@ cabal-version: >=1.10 name: sequenceTools -version: 1.4.0.2 +version: 1.4.0.3 license: GPL-3 license-file: LICENSE maintainer: stephan.schiffels@mac.com @@ -26,7 +26,7 @@ base >=4.7 && <5, optparse-applicative >=0.14.3.0, random >=1.1, - sequence-formats >=1.4.0, + sequence-formats >=1.4.1, bytestring >=0.10.8.2, vector >=0.12.0.3, pipes >=4.3.11 @@ -39,7 +39,7 @@ build-depends: base >=4.12.0.0, sequenceTools -any, - sequence-formats >=1.4.0, + sequence-formats >=1.4.1, optparse-applicative >=0.14.3.0, pipes >=4.3.11, rio >=0.1.11.0, @@ -59,7 +59,7 @@ base >=4.12.0.0, sequenceTools -any, pipes-ordered-zip >=1.1.0, - sequence-formats >=1.4.0, + sequence-formats >=1.4.1, bytestring >=0.10.8.2, vector >=0.12.0.3, optparse-applicative >=0.14.3.0, @@ -72,7 +72,7 @@ default-language: Haskell2010 build-depends: base >=4.12.0.0, - sequence-formats >=1.4.0, + sequence-formats >=1.4.1, sequenceTools -any, foldl >=1.4.5, bytestring >=0.10.8.2, @@ -95,7 +95,7 @@ base >=4.12.0.0, hspec >=2.7.1, sequenceTools -any, - sequence-formats >=1.4.0, + sequence-formats >=1.4.1, vector >=0.12.0.3, bytestring >=0.10.8.2, pipes >=4.3.11 diff --git a/src-executables/genoStats.hs b/src-executables/genoStats.hs --- a/src-executables/genoStats.hs +++ b/src-executables/genoStats.hs @@ -10,7 +10,6 @@ import Control.Foldl (purely, Fold(..)) import Control.Monad (forM_) import Control.Monad.IO.Class (MonadIO, liftIO) -import qualified Data.ByteString.Char8 as B import qualified Data.Vector as V import Lens.Family2 (view) import qualified Options.Applicative as OP @@ -80,7 +79,7 @@ (FreqSumHeader names nrHaps, fsProd) <- case fsFile of Nothing -> readFreqSumStdIn Just fn -> readFreqSumFile fn - let prod = for fsProd $ \(FreqSumEntry chrom _ _ _ _ counts) -> do + let prod = for fsProd $ \(FreqSumEntry chrom _ _ _ _ _ counts) -> do let genotypes = V.fromList $ do (count', nrHap) <- zip counts nrHaps case count' of @@ -90,7 +89,7 @@ Nothing -> return Missing _ -> error "should not happen" yield $ InputEntry chrom genotypes - return (map B.unpack names, prod) + return (names, prod) runWithEigenstrat :: (MonadSafe m) => FilePath -> FilePath -> FilePath -> m ([String], Producer InputEntry m ()) @@ -138,7 +137,7 @@ forM_ (zip names reports) $ \(n, StatsReport mis ref alt het) -> do let total = mis + ref + alt + het misPerc = round $ (fromIntegral mis / fromIntegral total) * (100.0 :: Double) :: Int - liftIO . putStrLn $ printf "%s\t%s\t%d(%d%%)\t%d\t%d\t%d" (unChrom chrom) n mis misPerc ref alt het + liftIO . putStrLn $ printf "%s\t%s\t%d(%d%%)\t%d\t%d\t%d" (show chrom) n mis misPerc ref alt het accumulateAllChromStats :: [String] -> Fold (Chrom, StatsReportAllSamples) (Chrom, StatsReportAllSamples) diff --git a/src-executables/pileupCaller.hs b/src-executables/pileupCaller.hs --- a/src-executables/pileupCaller.hs +++ b/src-executables/pileupCaller.hs @@ -4,11 +4,10 @@ EigenstratIndEntry(..), Sex(..), writeEigenstrat) import SequenceFormats.FreqSum(FreqSumEntry(..), printFreqSumStdOut, FreqSumHeader(..)) import SequenceFormats.Pileup (PileupRow(..), readPileupFromStdIn) -import SequenceTools.Utils (versionInfoOpt, versionInfoText) +import SequenceTools.Utils (versionInfoOpt, versionInfoText, freqSumToEigenstrat) import SequenceTools.PileupCaller (CallingMode(..), callGenotypeFromPileup, callToDosage, - freqSumToEigenstrat, filterTransitions, TransitionsMode(..), cleanSSdamageAllSamples) + filterTransitions, TransitionsMode(..), cleanSSdamageAllSamples) -import qualified Data.ByteString.Char8 as B import Data.List.Split (splitOn) import qualified Data.Vector.Unboxed.Mutable as V import qualified Options.Applicative as OP @@ -223,12 +222,12 @@ let ret = Pipes.for jointProd $ \jointEntry -> case jointEntry of (Just esEntry, Nothing) -> do - let (EigenstratSnpEntry chr pos _ id_ ref alt) = esEntry + let (EigenstratSnpEntry chr pos gpos id_ ref alt) = esEntry dosages = (replicate nrSamples Nothing) liftIO $ addOneSite readStats - yield $ FreqSumEntry chr pos (Just . B.unpack $ id_) ref alt dosages + yield $ FreqSumEntry chr pos (Just id_) (Just gpos) ref alt dosages (Just esEntry, Just pRow) -> do - let (EigenstratSnpEntry chr pos _ id_ ref alt) = esEntry + let (EigenstratSnpEntry chr pos gpos id_ ref alt) = esEntry (PileupRow _ _ _ rawPileupBasesPerSample rawStrandInfoPerSample) = pRow let cleanBasesPerSample = if singleStrandMode @@ -243,7 +242,7 @@ (map length cleanBasesPerSample) (map length congruentBasesPerSample) calls <- liftIO $ mapM (callGenotypeFromPileup mode minDepth) congruentBasesPerSample let genotypes = map (callToDosage ref alt) calls - yield (FreqSumEntry chr pos (Just . B.unpack $ id_) ref alt genotypes) + yield (FreqSumEntry chr pos (Just id_) (Just gpos) ref alt genotypes) _ -> return () return (fst <$> ret) where @@ -274,7 +273,7 @@ MajorityCalling _ -> 1 :: Int RandomCalling -> 1 RandomDiploidCalling -> 2 - let header' = FreqSumHeader (map B.pack sampleNames) [nrHaplotypes | _ <- sampleNames] + let header' = FreqSumHeader sampleNames [nrHaplotypes | _ <- sampleNames] outProd = freqSumProducer >-> filterTransitions transitionsOnly lift . runEffect $ outProd >-> printFreqSumStdOut header' diff --git a/src-executables/vcf2eigenstrat.hs b/src-executables/vcf2eigenstrat.hs --- a/src-executables/vcf2eigenstrat.hs +++ b/src-executables/vcf2eigenstrat.hs @@ -3,12 +3,11 @@ import Pipes.OrderedZip (orderedZip) import SequenceFormats.VCF (readVCFfromStdIn, VCFheader(..), VCFentry(..), isBiallelicSnp, getDosages, vcfToFreqSumEntry) -import SequenceFormats.Eigenstrat (EigenstratSnpEntry(..), readEigenstratSnpFile, writeEigenstrat, - GenoLine, GenoEntry(..), Sex(..), EigenstratIndEntry(..)) +import SequenceFormats.Eigenstrat (EigenstratSnpEntry(..), readEigenstratSnpFile, writeEigenstrat, + Sex(..), EigenstratIndEntry(..)) import SequenceFormats.FreqSum (FreqSumEntry(..), freqSumEntryToText) -import SequenceFormats.Utils (Chrom(..)) -import SequenceTools.Utils (versionInfoText, versionInfoOpt) +import SequenceTools.Utils (versionInfoText, versionInfoOpt, freqSumToEigenstrat) import Control.Exception.Base (throwIO, AssertionFailed(..)) import Control.Monad (when) @@ -16,7 +15,6 @@ import qualified Data.ByteString.Char8 as B import Data.Monoid ((<>)) -- import Debug.Trace (trace) -import Data.Vector (fromList) import qualified Options.Applicative as OP import Pipes (Pipe, yield, (>->), runEffect, Producer, Pipe, for, cat) import qualified Pipes.Prelude as P @@ -65,7 +63,7 @@ Just snpPosFile -> return $ runJointly vcfBodyBiAllelic nrInds snpPosFile Nothing -> return $ runSimple vcfBodyBiAllelic - runEffect $ vcfProducer >-> eigenStratPipe >-> writeEigenstrat genoOut snpOut indOut indEntries + runEffect $ vcfProducer >-> P.map (freqSumToEigenstrat False) >-> writeEigenstrat genoOut snpOut indOut indEntries runJointly :: (MonadIO m, MonadSafe m) => Producer VCFentry m r -> Int -> FilePath -> Producer FreqSumEntry m r runJointly vcfBody nrInds snpPosFile = @@ -78,10 +76,10 @@ processVcfWithSnpFile :: (MonadIO m) => Int -> Pipe (Maybe EigenstratSnpEntry, Maybe VCFentry) FreqSumEntry m r processVcfWithSnpFile nrInds = for cat $ \jointEntry -> do case jointEntry of - (Just (EigenstratSnpEntry snpChrom' snpPos' _ snpId' snpRef' snpAlt'), Nothing) -> do + (Just (EigenstratSnpEntry snpChrom' snpPos' gpos snpId' snpRef' snpAlt'), Nothing) -> do let dosages = replicate nrInds Nothing - yield $ FreqSumEntry snpChrom' snpPos' (Just . B.unpack $ snpId') snpRef' snpAlt' dosages - (Just (EigenstratSnpEntry snpChrom' snpPos' _ snpId' snpRef' snpAlt'), Just vcfEntry) -> do + yield $ FreqSumEntry snpChrom' snpPos' (Just snpId') (Just gpos) snpRef' snpAlt' dosages + (Just (EigenstratSnpEntry snpChrom' snpPos' gpos snpId' snpRef' snpAlt'), Just vcfEntry) -> do dosages <- case getDosages vcfEntry of Right dos -> return dos Left err -> liftIO . throwIO $ AssertionFailed err @@ -95,7 +93,7 @@ then map flipDosages dosages else replicate nrInds Nothing _ -> replicate nrInds Nothing - yield $ FreqSumEntry snpChrom' snpPos' (Just . B.unpack $ snpId') snpRef' snpAlt' normalizedDosages + yield $ FreqSumEntry snpChrom' snpPos' (Just snpId') (Just gpos) snpRef' snpAlt' normalizedDosages _ -> return () where flipDosages dos = case dos of @@ -111,20 +109,3 @@ liftIO . B.putStr . freqSumEntryToText $ e' yield e' Left err -> (liftIO . throwIO) (AssertionFailed err) - -eigenStratPipe :: (MonadIO m) => Pipe FreqSumEntry (EigenstratSnpEntry, GenoLine) m r -eigenStratPipe = P.map vcfToEigenstrat - where - vcfToEigenstrat (FreqSumEntry chrom pos maybeSnpId ref alt dosages) = - let snpId' = case maybeSnpId of - Just i -> B.pack i - Nothing -> B.pack (unChrom chrom <> "_" <> show pos) - snpEntry = EigenstratSnpEntry chrom pos 0.0 snpId' ref alt - genoLine = fromList [dosageToCall d | d <- dosages] - in (snpEntry, genoLine) - dosageToCall d = case d of - Just 0 -> HomRef - Just 1 -> Het - Just 2 -> HomAlt - Nothing -> Missing - _ -> error ("unknown dosage " ++ show d) diff --git a/src/SequenceTools/PileupCaller.hs b/src/SequenceTools/PileupCaller.hs --- a/src/SequenceTools/PileupCaller.hs +++ b/src/SequenceTools/PileupCaller.hs @@ -1,17 +1,14 @@ +{-# LANGUAGE OverloadedStrings #-} module SequenceTools.PileupCaller (callToDosage, Call(..), callGenotypeFromPileup, callMajorityAllele, findMajorityAlleles, callRandomAllele, - callRandomDiploid, dosageToEigenstratGeno, freqSumToEigenstrat, CallingMode(..), + callRandomDiploid, CallingMode(..), TransitionsMode(..), filterTransitions, cleanSSdamageAllSamples) where -import SequenceFormats.Utils (Chrom(..)) import SequenceFormats.FreqSum (FreqSumEntry(..)) -import SequenceFormats.Eigenstrat (EigenstratSnpEntry(..), GenoEntry(..), GenoLine) import SequenceFormats.Pileup (Strand(..)) import SequenceTools.Utils (sampleWithoutReplacement) -import qualified Data.ByteString.Char8 as B import Data.List (sortOn, group, sort) -import Data.Vector (fromList) import Pipes (Pipe, cat) import qualified Pipes.Prelude as P @@ -89,42 +86,15 @@ Just [a1, a2] -> return $ DiploidCall a1 a2 _ -> error "should not happen" --- |convert a freqSum entry to an eigenstrat SNP entry -freqSumToEigenstrat :: Bool -> FreqSumEntry -> (EigenstratSnpEntry, GenoLine) -freqSumToEigenstrat diploidizeCall (FreqSumEntry chrom@(Chrom c) pos maybeSnpId ref alt calls) = - let snpId_ = case maybeSnpId of - Just id_ -> B.pack id_ - Nothing -> B.pack $ c <> "_" <> show pos - snpEntry = EigenstratSnpEntry chrom pos 0.0 snpId_ ref alt - geno = fromList . map (dosageToEigenstratGeno diploidizeCall) $ calls - in (snpEntry, geno) - --- |convert a Dosage to an eigenstrat-encoded genotype -dosageToEigenstratGeno :: Bool -> Maybe Int -> GenoEntry -dosageToEigenstratGeno diploidizeCall c = - if diploidizeCall then - case c of - Just 0 -> HomRef - Just 1 -> HomAlt - Nothing -> Missing - _ -> error "illegal call for pseudo-haploid Calling method" - else - case c of - Just 0 -> HomRef - Just 1 -> Het - Just 2 -> HomAlt - Nothing -> Missing - _ -> error ("unknown genotype " ++ show c) - filterTransitions :: (Monad m) => TransitionsMode -> Pipe FreqSumEntry FreqSumEntry m () filterTransitions transversionsMode = case transversionsMode of SkipTransitions -> - P.filter (\(FreqSumEntry _ _ _ ref alt _) -> isTransversion ref alt) + P.filter (\(FreqSumEntry _ _ _ _ ref alt _) -> isTransversion ref alt) TransitionsMissing -> - P.map (\(FreqSumEntry chrom pos id_ ref alt calls) -> + P.map (\(FreqSumEntry chrom pos id_ gpos ref alt calls) -> let calls' = if isTransversion ref alt then calls else [Nothing | _ <- calls] - in FreqSumEntry chrom pos id_ ref alt calls') + in FreqSumEntry chrom pos id_ gpos ref alt calls') _ -> cat where isTransversion ref alt = not $ isTransition ref alt diff --git a/src/SequenceTools/Utils.hs b/src/SequenceTools/Utils.hs --- a/src/SequenceTools/Utils.hs +++ b/src/SequenceTools/Utils.hs @@ -1,8 +1,16 @@ -module SequenceTools.Utils (versionInfoOpt, versionInfoText, sampleWithoutReplacement) where +{-# LANGUAGE OverloadedStrings #-} +module SequenceTools.Utils (versionInfoOpt, versionInfoText, sampleWithoutReplacement, + freqSumToEigenstrat, dosageToEigenstratGeno) where -import Paths_sequenceTools (version) +import SequenceFormats.FreqSum (FreqSumEntry(..)) +import SequenceFormats.Eigenstrat (EigenstratSnpEntry(..), GenoLine, GenoEntry(..)) +import SequenceFormats.Utils (Chrom(..)) + +import qualified Data.ByteString.Char8 as B +import Data.Vector (fromList) import Data.Version (showVersion) import qualified Options.Applicative as OP +import Paths_sequenceTools (version) import System.Random (randomRIO) versionInfoOpt :: OP.Parser (a -> a) @@ -24,3 +32,33 @@ xs' = remove rn xs go (a:res) xs' (n - 1) remove i xs = let (ys, zs) = splitAt i xs in ys ++ tail zs + +-- |convert a freqSum entry to an eigenstrat SNP entry +freqSumToEigenstrat :: Bool -> FreqSumEntry -> (EigenstratSnpEntry, GenoLine) +freqSumToEigenstrat diploidizeCall (FreqSumEntry chrom@(Chrom c) pos maybeSnpId maybeGeneticPos ref alt calls) = + let snpId_ = case maybeSnpId of + Just id_ -> id_ + Nothing -> c <> "_" <> B.pack (show pos) + geneticPos = case maybeGeneticPos of + Just p -> p + Nothing -> 0.0 + snpEntry = EigenstratSnpEntry chrom pos geneticPos snpId_ ref alt + geno = fromList . map (dosageToEigenstratGeno diploidizeCall) $ calls + in (snpEntry, geno) + +-- |convert a Dosage to an eigenstrat-encoded genotype +dosageToEigenstratGeno :: Bool -> Maybe Int -> GenoEntry +dosageToEigenstratGeno diploidizeCall c = + if diploidizeCall then + case c of + Just 0 -> HomRef + Just 1 -> HomAlt + Nothing -> Missing + _ -> error "illegal call for pseudo-haploid Calling method" + else + case c of + Just 0 -> HomRef + Just 1 -> Het + Just 2 -> HomAlt + Nothing -> Missing + _ -> error ("unknown genotype " ++ show c) diff --git a/test/SequenceTools/PileupCallerSpec.hs b/test/SequenceTools/PileupCallerSpec.hs --- a/test/SequenceTools/PileupCallerSpec.hs +++ b/test/SequenceTools/PileupCallerSpec.hs @@ -1,13 +1,10 @@ {-# LANGUAGE OverloadedStrings #-} module SequenceTools.PileupCallerSpec (spec) where -import SequenceFormats.FreqSum (FreqSumEntry(..)) -import SequenceFormats.Eigenstrat (GenoEntry(..), EigenstratSnpEntry(..)) -import SequenceFormats.Utils (Chrom(..)) -import SequenceFormats.Pileup (Strand(..)) +import SequenceTools.Utils (dosageToEigenstratGeno, freqSumToEigenstrat) import SequenceTools.PileupCaller (callToDosage, Call(..), callGenotypeFromPileup, callMajorityAllele, findMajorityAlleles, callRandomAllele, - callRandomDiploid, dosageToEigenstratGeno, freqSumToEigenstrat, CallingMode(..), + callRandomDiploid, CallingMode(..), TransitionsMode(..), filterTransitions, cleanSSdamageAllSamples) import Control.Monad (replicateM, forM_) @@ -16,6 +13,10 @@ import Data.Vector (fromList) import Pipes (each, (>->)) import qualified Pipes.Prelude as P +import SequenceFormats.FreqSum (FreqSumEntry(..)) +import SequenceFormats.Eigenstrat (GenoEntry(..), EigenstratSnpEntry(..)) +import SequenceFormats.Utils (Chrom(..)) +import SequenceFormats.Pileup (Strand(..)) import Test.Hspec spec :: Spec @@ -129,7 +130,7 @@ testFreqSumToEigenstrat :: Spec testFreqSumToEigenstrat = describe "freqSumtoEigenstrat" $ do - let fs = FreqSumEntry (Chrom "1") 1000 Nothing 'A' 'C' [Just 0, Just 1, Just 1, Nothing, Just 0] + let fs = FreqSumEntry (Chrom "1") 1000 Nothing Nothing 'A' 'C' [Just 0, Just 1, Just 1, Nothing, Just 0] let es = EigenstratSnpEntry (Chrom "1") 1000 0.0 (B.pack "1_1000") 'A' 'C' genoLine = fromList [HomRef, HomAlt, HomAlt, Missing, HomRef] it "should convert a freqSum example correctly to eigenstrat" $ @@ -140,29 +141,29 @@ mockFreqSumData :: [FreqSumEntry] mockFreqSumData = [ - FreqSumEntry (Chrom "1") 1000 (Just "rs1") 'A' 'C' [Just 1, Just 2, Nothing, Just 0, Just 0], - FreqSumEntry (Chrom "1") 2000 (Just "rs2") 'C' 'T' [Just 1, Just 2, Nothing, Just 0, Just 0], - FreqSumEntry (Chrom "1") 3000 (Just "rs3") 'A' 'G' [Just 1, Just 2, Nothing, Just 0, Just 0], - FreqSumEntry (Chrom "2") 1000 (Just "rs4") 'A' 'G' [Just 1, Just 2, Nothing, Just 0, Just 0], - FreqSumEntry (Chrom "2") 2000 (Just "rs5") 'T' 'A' [Just 1, Just 2, Nothing, Just 0, Just 0], - FreqSumEntry (Chrom "2") 3000 (Just "rs6") 'T' 'C' [Just 1, Just 2, Nothing, Just 0, Just 0]] + FreqSumEntry (Chrom "1") 1000 (Just "rs1") Nothing 'A' 'C' [Just 1, Just 2, Nothing, Just 0, Just 0], + FreqSumEntry (Chrom "1") 2000 (Just "rs2") Nothing 'C' 'T' [Just 1, Just 2, Nothing, Just 0, Just 0], + FreqSumEntry (Chrom "1") 3000 (Just "rs3") Nothing 'A' 'G' [Just 1, Just 2, Nothing, Just 0, Just 0], + FreqSumEntry (Chrom "2") 1000 (Just "rs4") Nothing 'A' 'G' [Just 1, Just 2, Nothing, Just 0, Just 0], + FreqSumEntry (Chrom "2") 2000 (Just "rs5") Nothing 'T' 'A' [Just 1, Just 2, Nothing, Just 0, Just 0], + FreqSumEntry (Chrom "2") 3000 (Just "rs6") Nothing 'T' 'C' [Just 1, Just 2, Nothing, Just 0, Just 0]] testFilterTransitions :: Spec testFilterTransitions = describe "filterTransitions" $ do it "should remove transitions with SkipTransitions" $ do let r = P.toList $ each mockFreqSumData >-> filterTransitions SkipTransitions r `shouldBe` [ - FreqSumEntry (Chrom "1") 1000 (Just "rs1") 'A' 'C' [Just 1, Just 2, Nothing, Just 0, Just 0], - FreqSumEntry (Chrom "2") 2000 (Just "rs5") 'T' 'A' [Just 1, Just 2, Nothing, Just 0, Just 0]] + FreqSumEntry (Chrom "1") 1000 (Just "rs1") Nothing 'A' 'C' [Just 1, Just 2, Nothing, Just 0, Just 0], + FreqSumEntry (Chrom "2") 2000 (Just "rs5") Nothing 'T' 'A' [Just 1, Just 2, Nothing, Just 0, Just 0]] it "should mark transitions as missing with TransitionsMissing" $ do let r = P.toList $ each mockFreqSumData >-> filterTransitions TransitionsMissing r `shouldBe` [ - FreqSumEntry (Chrom "1") 1000 (Just "rs1") 'A' 'C' [Just 1, Just 2, Nothing, Just 0, Just 0], - FreqSumEntry (Chrom "1") 2000 (Just "rs2") 'C' 'T' [Nothing, Nothing, Nothing, Nothing, Nothing], - FreqSumEntry (Chrom "1") 3000 (Just "rs3") 'A' 'G' [Nothing, Nothing, Nothing, Nothing, Nothing], - FreqSumEntry (Chrom "2") 1000 (Just "rs4") 'A' 'G' [Nothing, Nothing, Nothing, Nothing, Nothing], - FreqSumEntry (Chrom "2") 2000 (Just "rs5") 'T' 'A' [Just 1, Just 2, Nothing, Just 0, Just 0], - FreqSumEntry (Chrom "2") 3000 (Just "rs6") 'T' 'C' [Nothing, Nothing, Nothing, Nothing, Nothing]] + FreqSumEntry (Chrom "1") 1000 (Just "rs1") Nothing 'A' 'C' [Just 1, Just 2, Nothing, Just 0, Just 0], + FreqSumEntry (Chrom "1") 2000 (Just "rs2") Nothing 'C' 'T' [Nothing, Nothing, Nothing, Nothing, Nothing], + FreqSumEntry (Chrom "1") 3000 (Just "rs3") Nothing 'A' 'G' [Nothing, Nothing, Nothing, Nothing, Nothing], + FreqSumEntry (Chrom "2") 1000 (Just "rs4") Nothing 'A' 'G' [Nothing, Nothing, Nothing, Nothing, Nothing], + FreqSumEntry (Chrom "2") 2000 (Just "rs5") Nothing 'T' 'A' [Just 1, Just 2, Nothing, Just 0, Just 0], + FreqSumEntry (Chrom "2") 3000 (Just "rs6") Nothing 'T' 'C' [Nothing, Nothing, Nothing, Nothing, Nothing]] it "should output all sites with AllSites" $ do let r = P.toList $ each mockFreqSumData >-> filterTransitions AllSites r `shouldBe` mockFreqSumData