Merge pull request #57 from pdimens/dev

add -o
pdimens · Mar 21, 2024 · e86e1b6 · e86e1b6
2 parents 1a8278f + 9e9aa14
commit e86e1b6
Show file tree

Hide file tree

Showing 49 changed files with 650 additions and 738 deletions.
diff --git a/.github/workflows/align.yml b/.github/workflows/align.yml
@@ -23,6 +23,7 @@ on:
       - 'workflow/scripts/makewindows.py'
       - 'test/fastq/**'
       - '**align.yml'
+      - '**__main__.py'
 
   pull_request:
     branches:
@@ -46,6 +47,7 @@ on:
       - 'workflow/scripts/makewindows.py'
       - 'test/fastq/**'
       - '**align.yml'
+      - '**__main__.py'
 
 env:
   CACHE_NUMBER: 0  # increase to reset cache manually
@@ -78,7 +80,7 @@ jobs:
         shell: micromamba-shell {0}
       - name: test bwa
         shell: micromamba-shell {0}
-        run: harpy align bwa -g test/genome/genome.fasta.gz -q -s "--show-failed-logs" test/fastq
+        run: harpy align bwa -g test/genome/genome.fasta.gz -s "--show-failed-logs" test/fastq
   test_ema:
     name: ema
     runs-on: ubuntu-latest
@@ -106,4 +108,4 @@ jobs:
         shell: micromamba-shell {0}
       - name: test ema
         shell: micromamba-shell {0}
-        run: harpy align ema --ema-bins 20 -g test/genome/genome.fasta.gz -q -s "--show-failed-logs" test/fastq
+        run: harpy align ema --ema-bins 20 -g test/genome/genome.fasta.gz -s "--show-failed-logs" test/fastq
diff --git a/.github/workflows/demux.yml b/.github/workflows/demux.yml
@@ -17,6 +17,7 @@ on:
       - '**demux.yml'
       - 'BC_files.py'
       - 'test/data/demux/**'
+      - '**__main__.py'
 
   pull_request:
     branches:
@@ -34,7 +35,7 @@ on:
       - '**demux.yml'
       - 'BC_files.py'
       - 'test/data/demux/**'
-
+      - '**__main__.py'
 
 env:
   CACHE_NUMBER: 0  # increase to reset cache manually

diff --git a/.github/workflows/impute.yml b/.github/workflows/impute.yml
@@ -19,6 +19,7 @@ on:
       - 'workflow/report/Impute.Rmd'
       - 'workflow/report/StitchCollate.Rmd'
       - 'workflow/scripts/stitch_impute.R'
+      - '**__main__.py'
 
   pull_request:
     branches:
@@ -38,6 +39,7 @@ on:
       - 'workflow/report/Impute.Rmd'
       - 'workflow/report/StitchCollate.Rmd'
       - 'workflow/scripts/stitch_impute.R'
+      - '**__main__.py'
 
 env:
   CACHE_NUMBER: 0  # increase to reset cache manually

diff --git a/.github/workflows/phase.yml b/.github/workflows/phase.yml
@@ -20,6 +20,7 @@ on:
       - 'workflow/report/HapCut2.Rmd'
       - 'workflow/scripts/parsePhaseBlocks.py'
       - 'workflow/scripts/summarizeHaplobocks.py'
+      - '**__main__.py'
 
   pull_request:
     branches:
@@ -40,6 +41,7 @@ on:
       - 'workflow/report/HapCut2.Rmd'
       - 'workflow/scripts/parsePhaseBlocks.py'
       - 'workflow/scripts/summarizeHaplobocks.py'
+      - '**__main__.py'
 
 env:
   CACHE_NUMBER: 0  # increase to reset cache manually

diff --git a/.github/workflows/preflight.yml b/.github/workflows/preflight.yml
@@ -20,6 +20,7 @@ on:
       - 'workflow/report/PreflightFastq.Rmd'
       - 'workflow/report/PreflightBam.Rmd'
       - '**preflight.yml'
+      - '**__main__.py'
 
   pull_request:
     branches:
@@ -40,6 +41,7 @@ on:
       - 'workflow/report/PreflightFastq.Rmd'
       - 'workflow/report/PreflightBam.Rmd'
       - '**preflight.yml'
+      - '**__main__.py'
 
 env:
   CACHE_NUMBER: 0  # increase to reset cache manually

diff --git a/.github/workflows/qc.yml b/.github/workflows/qc.yml
@@ -15,6 +15,7 @@ on:
       - '**validations.py'
       - 'test/fastq/**'
       - '**qc.yml'
+      - '**__main__.py'
 
   pull_request:
     branches:
@@ -30,6 +31,7 @@ on:
       - '**validations.py'
       - 'test/fastq/**'
       - '**qc.yml'
+      - '**__main__.py'
 
 env:
   CACHE_NUMBER: 0  # increase to reset cache manually

diff --git a/.github/workflows/variants_snp.yml b/.github/workflows/variants_snp.yml
@@ -19,6 +19,7 @@ on:
       - 'workflow/scripts/makewindows.py'
       - 'test/bam/**'
       - '**variants_snp.yml'
+      - '**__main__.py'
 
   pull_request:
     branches:
@@ -38,6 +39,7 @@ on:
       - 'workflow/scripts/makewindows.py'
       - 'test/bam/**'
       - '**variants_snp.yml'
+      - '**__main__.py'
 
 env:
   CACHE_NUMBER: 0  # increase to reset cache manually
@@ -68,9 +70,12 @@ jobs:
           python3 -m pip install --upgrade build && python3 -m build
           pip install dist/*.whl
           resources/buildforCI.sh
-      - name: variants mpileup
+      - name: snp mpileup
         shell: micromamba-shell {0}
         run: harpy snp mpileup -w 150000 -g test/genome/genome.fasta.gz -q test/bam
+      - name: snp mpileup-pop
+        shell: micromamba-shell {0}
+        run: harpy snp mpileup -w 150000 -g test/genome/genome.fasta.gz -p test/samples.groups -q test/bam
   test_freebayes:
     name: freebayes
     runs-on: ubuntu-latest
@@ -96,6 +101,9 @@ jobs:
           python3 -m pip install --upgrade build && python3 -m build
           pip install dist/*.whl
           resources/buildforCI.sh
-      - name: variants freebayes
+      - name: snp freebayes
+        shell: micromamba-shell {0}
+        run: harpy snp freebayes -w 150000 -g test/genome/genome.fasta.gz -q test/bam
+      - name: snp freebayes-pop
         shell: micromamba-shell {0}
-        run: harpy snp freebayes -w 150000 -g test/genome/genome.fasta.gz -q test/bam
+        run: harpy snp freebayes -w 150000 -g test/genome/genome.fasta.gz -p test/samples.groups -q test/bam
diff --git a/.github/workflows/variants_sv.yml b/.github/workflows/variants_sv.yml
@@ -21,6 +21,7 @@ on:
       - 'workflow/report/Leviathan**.Rmd'
       - 'workflow/report/Naibr**.Rmd'
       - 'workflow/scripts/inferSV.py'
+      - '**__main__.py'
 
   pull_request:
     branches:
@@ -42,6 +43,7 @@ on:
       - 'workflow/report/Leviathan**.Rmd'
       - 'workflow/report/Naibr**.Rmd'
       - 'workflow/scripts/inferSV.py'
+      - '**__main__.py'
 
 env:
   CACHE_NUMBER: 0  # increase to reset cache manually
@@ -79,7 +81,7 @@ jobs:
       - name: leviathan-pop
         if: always()
         shell: micromamba-shell {0}
-        run: harpy sv leviathan -g test/genome/genome.fasta.gz -p test/samples.groups -q -s "--show-failed-logs" test/bam
+        run: harpy sv leviathan -g test/genome/genome.fasta.gz -o SV/leviathanpop -p test/samples.groups -q -s "--show-failed-logs" test/bam
   test_naibr:
     name: naibr
     runs-on: ubuntu-latest
@@ -107,16 +109,16 @@ jobs:
           resources/buildforCI.sh
       - name: naibr
         shell: micromamba-shell {0}
-        run: harpy sv naibr -g test/genome/genome.fasta.gz -q -s "--show-failed-logs" test/bam_phased
+        run: harpy sv naibr -g test/genome/genome.fasta.gz -o SV/naibr -s "--show-failed-logs" test/bam_phased
       - name: naibr pop
         if: always()
         shell: micromamba-shell {0}
-        run: harpy sv naibr -g test/genome/genome.fasta.gz -p test/samples.groups -q -s "--show-failed-logs" test/bam_phased
+        run: harpy sv naibr -g test/genome/genome.fasta.gz -o SV/pop -p test/samples.groups -s "--show-failed-logs" test/bam_phased
       - name: naibr with phasing
         if: always()
         shell: micromamba-shell {0}
-        run: harpy sv naibr -g test/genome/genome.fasta.gz -v test/vcf/test.phased.bcf -q -s "--show-failed-logs" test/bam    
+        run: harpy sv naibr -g test/genome/genome.fasta.gz -o SV/phase -v test/vcf/test.phased.bcf -s "--show-failed-logs" test/bam    
       - name: naibr pop with phasing
         if: always()
         shell: micromamba-shell {0}
-        run: harpy sv naibr -g test/genome/genome.fasta.gz -v test/vcf/test.phased.bcf -p test/samples.groups -q -s "--show-failed-logs" test/bam
+        run: harpy sv naibr -g test/genome/genome.fasta.gz -o SV/phasepop -v test/vcf/test.phased.bcf -p test/samples.groups -s "--show-failed-logs" test/bam
diff --git a/.gitignore b/.gitignore
@@ -1,12 +1,13 @@
 .snakemake/
 .vscode/
-harpyenvs/
+.harpy_envs/
 Seqs/
 QC/
 Demultiplex/
 Genome/
 Align/
-Variants/
+SNP/
+SV/
 Impute/
 Preflight/
 Phase/

diff --git a/pyproject.toml b/pyproject.toml
@@ -4,12 +4,12 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "harpy"
-version = "0.7.3"
+version = "0.8.0"
 authors = [
     {name = "Pavel Dimens"}
 ]
 description = "An automated workflow to demultiplex sequences, trim reads, map sequences, call variants, impute genotypes, and phase haplotypes of Haplotagging data. Batteries included."
-requires-python = ">=3.7"
+requires-python = ">=3.9"
 readme = {file = "README.md", content-type = "text/markdown"}
 license = {text = "GPL-3.0"}
 

diff --git a/resources/createharpyenv.sh b/resources/createharpyenv.sh
@@ -4,9 +4,9 @@
 
 mamba create -n $1 -c bioconda -c conda-forge \
     bcftools=1.19 \
-    pysam=0.22 \
     python \
+    pandas \
     rich-click \
-    snakemake \
+    snakemake-minimal>7 \
     samtools \
     seqtk
diff --git a/resources/meta.yaml b/resources/meta.yaml
@@ -20,15 +20,14 @@ build:
 
 requirements:
   host:
-    - python =3.10
+    - python =3.12
     - pip
   run:
     - bcftools =1.19
     - pandas
-    - pysam =0.22
-    - python =3.10
+    - python >3.10
     - rich-click
-    - snakemake-minimal
+    - snakemake-minimal >7
     - samtools
     - seqtk
     - tabix