Merge pull request #275 from poseidon-framework/deactivatePloidyCheck

I turned off the ploidy check

CHANGELOG.md

@@ -1,3 +1,5 @@
+- V 1.4.0.2:
+    - Strictly checking ploidy information across the .janno file and the genotype data in the package reading process has unforeseen consequences. Activating this will require some more changes, so we decided to uncomment this code for now.
 - V 1.4.0.1:
     - This patch makes the error output in case of ploidy-mismatches between the Genotype_Ploidy information in Janno and heterozygote genotypes more user-friendly.
     - We fixed a bug in Fetch.hs in the output for comparing local and remote package versions

CHANGELOGRELEASE.md

@@ -1,4 +1,4 @@
-### V 1.4.0.1
+### V 1.4.0.2
 
 This release finally fully enables handling multiple Poseidon package versions with trident. It includes a significant overhaul of the selection language in `forge` and `fetch` with major changes in its implementation and, as a consequence, multiple (subtle, but strictly breaking) changes in its semantics.
 
@@ -42,7 +42,6 @@ The specific individual selection syntax (with `-<Pac1-1.0.1:Group1:Ind1>`) does
 - The Web API and the `list` subcommand now return an extra, boolean field/column `isLatest` to point out if an entity (individual, group, package) is from the latest package version.
 - `list` now also returns column headers with the `--raw` flag. If they are not desired, then they have to be filtered out manually on the command line (e.g. with `trident list ... | tail -n+2`).
 - Duplicate individuals in a package collection do not anymore lead to errors. Instead, only a selection for `forge` (and externally also in `xerxes`), if resulting in multiple individuals in the selection, will lead to errors. `validate` will also fail by default, except `--ignoreDuplicates` is set.
-- The genotype ploidy (`Genotype_Ploidy`) documented in .janno files is now checked when reading the package: If a sample marked as `haploid` has a heterozygote SNP, this now throws an error.
 
 ### V 1.3.0.4
 

poseidon-hs.cabal

@@ -1,5 +1,5 @@
 name:                poseidon-hs
-version:             1.4.0.1
+version:             1.4.0.2
 synopsis:            A package with tools for working with Poseidon Genotype Data
 description:         The tools in this package read and analyse Poseidon-formatted genotype databases, a modular system for storing genotype data from thousands of individuals.
 license:             MIT

src/Poseidon/Package.hs

@@ -38,13 +38,11 @@ import           Poseidon.EntityTypes       (EntitySpec, HasNameAndVersion (..),
                                              PacNameAndVersion (..),
                                              determineRelevantPackages,
                                              isLatestInCollection,
-                                             makePacNameAndVersion,
-                                             renderNameWithVersion)
+                                             makePacNameAndVersion)
 import           Poseidon.GenotypeData      (GenotypeDataSpec (..), joinEntries,
                                              loadGenotypeData, loadIndividuals,
                                              printSNPCopyProgress)
-import           Poseidon.Janno             (JannoGenotypePloidy (..),
-                                             JannoLibraryBuilt (..),
+import           Poseidon.Janno             (JannoLibraryBuilt (..),
                                              JannoList (..), JannoRow (..),
                                              JannoRows (..), JannoSex (..),
                                              JannoUDG (..), createMinimalJanno,
@@ -406,9 +404,9 @@ validateGeno :: PoseidonPackage -> Bool -> PoseidonIO ()
 validateGeno pac checkFullGeno = do
     logA <- envLogAction
     plinkMode <- envInputPlinkMode
-    let jannoRows = getJannoRowsFromPac pac
-    let ploidyList = map jGenotypePloidy jannoRows
-    let indivNames = map jPoseidonID jannoRows
+    --let jannoRows = getJannoRowsFromPac pac
+    --let ploidyList = map jGenotypePloidy jannoRows
+    --let indivNames = map jPoseidonID jannoRows
     liftIO $ catch (
         runSafeT $ do
             -- we're using getJointGenotypeData here on a single package to check for SNP consistency
@@ -418,20 +416,22 @@ validateGeno pac checkFullGeno = do
             if checkFullGeno
             then do
                 currentTime <- liftIO getCurrentTime
-                runEffect $ eigenstratProd >-> checkPloidy logA ploidyList indivNames >-> printSNPCopyProgress logA currentTime >-> P.drain
+                --runEffect $ eigenstratProd >-> checkPloidy logA ploidyList indivNames >-> printSNPCopyProgress logA currentTime >-> P.drain
+                runEffect $ eigenstratProd >-> printSNPCopyProgress logA currentTime >-> P.drain
             else
-                runEffect $ eigenstratProd >-> P.take 100 >-> checkPloidy logA ploidyList indivNames >-> P.drain
+                --runEffect $ eigenstratProd >-> P.take 100 >-> checkPloidy logA ploidyList indivNames >-> P.drain
+                runEffect $ eigenstratProd >-> P.take 100 >-> P.drain
         ) (throwIO . PoseidonGenotypeExceptionForward)
-  where
-    checkPloidy logA ploidyList indivNames = for cat $ \(_, genoLine) -> do
-        let illegals =
-                map (\(_, ind, _) -> renderNameWithVersion pac ++ ": " ++ ind) .
-                filter (\(ploidy, _, geno) -> ploidy == Just Haploid && geno == Het) .
-                zip3 ploidyList indivNames . V.toList $ genoLine
-        unless (null illegals) $ do
-            logWithEnv logA . logDebug $ "The following samples have heterozygote genotypes despite being annotated as \"haploid\" in the Janno file:"
-            mapM_ (logWithEnv logA . logDebug) illegals
-            liftIO . throwIO $ PoseidonGenotypeException "Illegal heterozygote genotypes for individuals marked as 'haploid' in the Janno file. Choose --logMode VerboseLog to output more"
+  -- where
+  --   checkPloidy logA ploidyList indivNames = for cat $ \(_, genoLine) -> do
+  --       let illegals =
+  --               map (\(_, ind, _) -> renderNameWithVersion pac ++ ": " ++ ind) .
+  --               filter (\(ploidy, _, geno) -> ploidy == Just Haploid && geno == Het) .
+  --               zip3 ploidyList indivNames . V.toList $ genoLine
+  --       unless (null illegals) $ do
+  --           logWithEnv logA . logDebug $ "The following samples have heterozygote genotypes despite being annotated as \"haploid\" in the Janno file:"
+  --           mapM_ (logWithEnv logA . logDebug) illegals
+  --           liftIO . throwIO $ PoseidonGenotypeException "Illegal heterozygote genotypes for individuals marked as 'haploid' in the Janno file. Choose --logMode VerboseLog to output more"
 
 
 -- throws exception if any file is missing or checksum is incorrect