new feature for multiple popnames

Changelog.md

@@ -1,5 +1,10 @@
 # Changelog
 
+- V 1.5.4.0:
+   - updated sequence-formats dependency allows more lenient parsing of pileup-data, now also allowing for arbitrary reference alleles (not just ACTGN). This won't affect calling (sites where the pileup-reference is something different from the SNP-file input are declared missing), but will be less disruptive when parsing pileup-input.
+   - improved error output for parsing problems with pileup-format data. Now only a small part of the problematic chunk is output, hopefully easing error interpretation in such cases
+   - output a useful error message if the number of samples passed in --sampleNames is inconsistent with the pileup-input
+   - `--samplePopName` now accepts multiple pop-names, separated by comma. The number of pop-names must then match the number of samples.
 - V 1.5.3.2: fixed a bug in vcf2eigenstrat that would fail on VCFs with missing Quality values.
 - V 1.5.3.1: updated to latest GHC pedantic compilation
 - V 1.5.3: Upgraded to sequence-formats 1.7.0 introducing an option for plink popName encoding, and improved pileup-Parsing to allow for skip-reference characters

sequenceTools.cabal

@@ -1,5 +1,5 @@
 name:                sequenceTools
-version:             1.5.3.2
+version:             1.5.4.0
 synopsis:            A package with tools for processing DNA sequencing data
 description:         The tools in this package process sequencing Data, in particular from ancient DNA sequencing libraries. Key tool in this package is pileupCaller, a tool to randomly sample genotypes from sequencing data.
 license:             GPL-3

src-executables/pileupCaller.hs

@@ -247,7 +247,7 @@ runMain = do
         FreqSumFormat -> outputFreqSum freqSumProducer
         EigenstratFormat outPrefix -> outputEigenStratOrPlink outPrefix popNames Nothing freqSumProducer
         PlinkFormat outPrefix popNameMode -> outputEigenStratOrPlink outPrefix popNames (Just popNameMode) freqSumProducer
-    --outputStats
+    outputStats
 
 pileupToFreqSum :: Producer PileupRow (SafeT IO) () -> App (Producer FreqSumEntry (SafeT IO) ())
 pileupToFreqSum pileupProducer = do
@@ -304,8 +304,8 @@ addOneSite readStats = modifyIORef' (rsTotalSites readStats) (+1)
 
 updateStatsAllSamples :: ReadStats -> [Int] -> [Int] -> [Int] -> IO ()
 updateStatsAllSamples readStats rawBaseCounts damageCleanedBaseCounts congruencyCleanedBaseCounts = do
-    let n = V.length (rsRawReads readStats)
-    when (length rawBaseCounts /= n) $
+    let nSamples = V.length (rsRawReads readStats)
+    when (length rawBaseCounts /= nSamples) $
         throwIO (UserInputException "number of individuals specified differs from number of individuals in the pileup input")
     sequence_ [V.modify (rsRawReads readStats) (+n) i | (i, n) <- zip [0..] rawBaseCounts]
     sequence_ [V.modify (rsReadsCleanedSS readStats) (+n) i | (i, n) <- zip [0..] damageCleanedBaseCounts]

src-executables/vcf2eigenstrat.hs

@@ -5,7 +5,7 @@ import SequenceFormats.VCF (readVCFfromStdIn, VCFheader(..), VCFentry(..),
                      isBiallelicSnp, getDosages, vcfToFreqSumEntry)
 import SequenceFormats.Eigenstrat (EigenstratSnpEntry(..), readEigenstratSnpFile, writeEigenstrat,
     Sex(..), EigenstratIndEntry(..))
-import SequenceFormats.FreqSum (FreqSumEntry(..), freqSumEntryToText)
+import SequenceFormats.FreqSum (FreqSumEntry(..))
 
 import SequenceTools.Utils (versionInfoText, versionInfoOpt, freqSumToEigenstrat)