Merge branch 'anndata' of ssh://github.com/Golob-Minot/geneshot into …

…anndata
Golob-Minot · Nov 3, 2023 · eeea94e · eeea94e
2 parents e61378f + 330481f
commit eeea94e
Show file tree

Hide file tree

Showing 54 changed files with 680 additions and 1,273 deletions.
diff --git a/.github/workflows/test.yaml b/.github/workflows/test.yaml
@@ -23,13 +23,119 @@ jobs:
           df -h
       - name:  Run preprocess
         run: |
-          NXF_VER=23.10.0 nextflow run modules/preprocess.nf -c nextflow.config.sample -profile testing --manifest data/mock.manifest.csv --output output --host_index data/hg_chr_21_bwa_index.tar.gz  -w work/  -with-docker ubuntu:22.04
+          NXF_VER=23.10.0 nextflow run modules/preprocess.nf --manifest data/mock.manifest.csv --output output --host_index data/hg_chr_21_bwa_index.tar.gz  -w work/  -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
       - name:  Validate results 
         run: |
           tree output/
           [[ -s output/qc/manifest.qc.csv ]]
           [[ -s output/qc/Mock__11.R1.fastq.gz ]]
           [[ -s output/qc/Mock__13__R1.noadapt.nohuman.fq.gz ]]
 
+  composition_metaphlan2:
+    runs-on: ubuntu-22.04
+    env:
+      NXF_ANSI_LOG: 0
+    steps:
+      - uses: actions/checkout@v1
+      - name: Install Nextflow
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+      - name: Free disk space
+        run: |
+          sudo swapoff -a
+          sudo rm -f /swapfile
+          sudo apt clean
+          docker rmi $(docker image ls -aq)
+          df -h
+      - name:  Run geneshot
+        run: |
+          NXF_VER=23.10.0 nextflow run modules/composition.nf --manifest data/example_output/qc/manifest.qc.se.csv --output output -w work/  -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
+      - name:  Validate results 
+        run: |
+          tree output/
+          [[ -s output/MetaPhlAn2/metaphlan2.results.csv.gz ]]
+          [[ -s output/MetaPhlAn2/metaphlan2.species.h5ad ]]
+          
+  allele_catalog:
+    runs-on: ubuntu-22.04
+    env:
+      NXF_ANSI_LOG: 0
+    steps:
+      - uses: actions/checkout@v1
+      - name: Install Nextflow
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+      - name: Free disk space
+        run: |
+          sudo swapoff -a
+          sudo rm -f /swapfile
+          sudo apt clean
+          docker rmi $(docker image ls -aq)
+          df -h
+      - name:  Run geneshot
+        run: |
+          NXF_VER=23.10.0 nextflow run modules/allele_catalog.nf --manifest data/example_output/qc/manifest.qc.csv --output output -w work/  -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing 
+      - name:  Validate results 
+        run: |
+          tree output/
+          [[ -s output/alleles/allele_info.csv.gz ]]
+          [[ -s output/alleles/alleles.faa.gz ]]
+          [[ -s output/alleles/alleles.faa.gz.dmnd ]]
 
+  allele_clustering:
+    runs-on: ubuntu-22.04
+    env:
+      NXF_ANSI_LOG: 0
+    steps:
+      - uses: actions/checkout@v1
+      - name: Install Nextflow
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+      - name: Free disk space
+        run: |
+          sudo swapoff -a
+          sudo rm -f /swapfile
+          sudo apt clean
+          docker rmi $(docker image ls -aq)
+          df -h
+      - name:  Run geneshot
+        run: |
+          NXF_VER=23.10.0 nextflow run modules/allele_clustering.nf --alleles data/example_output/alleles/alleles.faa.gz --allele_info data/example_output/alleles/allele_info.csv.gz --output output -w work/  -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
+      - name:  Validate results 
+        run: |
+          tree output/
+          [[ -s output/alleles/Allele_Cluster_info.csv.gz ]]
+          [[ -s output/alleles/centroids.C100.fastp.gz ]]
+          [[ -s output/alleles/centroids.C90.fastp.gz ]]
+          [[ -s output/alleles/centroids.C50.fastp.gz ]]
+          [[ -s output/alleles/centroids.C100.fastp.gz.dmnd ]]
+          [[ -s output/alleles/centroids.C90.fastp.gz.dmnd ]]
+          [[ -s output/alleles/centroids.C50.fastp.gz.dmnd ]]
 
+  allele_quantification:
+    runs-on: ubuntu-22.04
+    env:
+      NXF_ANSI_LOG: 0
+    steps:
+      - uses: actions/checkout@v1
+      - name: Install Nextflow
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+      - name: Free disk space
+        run: |
+          sudo swapoff -a
+          sudo rm -f /swapfile
+          sudo apt clean
+          docker rmi $(docker image ls -aq)
+          df -h
+      - name:  Run geneshot
+        run: |
+          NXF_VER=23.10.0 nextflow run modules/quantify.nf --manifest data/example_output/qc/manifest.qc.csv --allele_fasta data/example_output/alleles/alleles.faa.gz  --output output -w work/  -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
+      - name:  Validate results 
+        run: |
+          tree output/
+          [[ -s output/quantify/specimen_allele_quantity.h5ad ]]
diff --git a/data/example_output/MetaPhlAn2/by_specimen/Mock__11.metaphlan2.tsv b/data/example_output/MetaPhlAn2/by_specimen/Mock__11.metaphlan2.tsv
@@ -0,0 +1,10 @@
+#SampleID	Metaphlan2_Analysis
+#clade_name	relative_abundance	coverage	average_genome_length_in_the_clade	estimated_number_of_reads_from_the_clade
+k__Bacteria	100.0	0.00026476039184537993	3060646.5783300134	810
+k__Bacteria|p__Proteobacteria	100.0	0.00026476039184537993	3135749.4117566776	830
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria	100.0	0.00026476039184537993	3686133.8101186045	976
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales	100.0	0.00026476039184537993	4079009.895749976	1080
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales|f__Enterobacteriaceae	100.0	0.00026476039184537993	4079009.895749976	1080
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales|f__Enterobacteriaceae|g__Escherichia	100.0	0.00026476039184537993	4803810.298629981	1272
+k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Enterobacteriales|f__Enterobacteriaceae|g__Escherichia|s__Escherichia_unclassified	100.0	0.00026476039184537993	4803810.298629981	1272
+#estimated total number of reads from known clades: 810
diff --git a/data/example_output/MetaPhlAn2/by_specimen/Mock__12.metaphlan2.tsv b/data/example_output/MetaPhlAn2/by_specimen/Mock__12.metaphlan2.tsv
@@ -0,0 +1,2 @@
+#SampleID	Metaphlan2_Analysis
+unclassified	100.0
diff --git a/data/example_output/MetaPhlAn2/by_specimen/Mock__13.metaphlan2.tsv b/data/example_output/MetaPhlAn2/by_specimen/Mock__13.metaphlan2.tsv
@@ -0,0 +1,2 @@
+#SampleID	Metaphlan2_Analysis
+unclassified	100.0
diff --git a/data/example_output/MetaPhlAn2/by_specimen/Mock__14.metaphlan2.tsv b/data/example_output/MetaPhlAn2/by_specimen/Mock__14.metaphlan2.tsv
@@ -0,0 +1,2 @@
+#SampleID	Metaphlan2_Analysis
+unclassified	100.0
diff --git a/data/example_output/MetaPhlAn2/by_specimen/Mock__15.metaphlan2.tsv b/data/example_output/MetaPhlAn2/by_specimen/Mock__15.metaphlan2.tsv
@@ -0,0 +1,2 @@
+#SampleID	Metaphlan2_Analysis
+unclassified	100.0
diff --git a/data/example_output/MetaPhlAn2/metaphlan2.results.csv.gz b/data/example_output/MetaPhlAn2/metaphlan2.results.csv.gz
diff --git a/data/example_output/MetaPhlAn2/metaphlan2.species.h5ad b/data/example_output/MetaPhlAn2/metaphlan2.species.h5ad
diff --git a/data/example_output/alleles/Allele_Cluster_info.csv.gz b/data/example_output/alleles/Allele_Cluster_info.csv.gz
diff --git a/data/example_output/alleles/allele_info.csv.gz b/data/example_output/alleles/allele_info.csv.gz
diff --git a/data/example_output/alleles/alleles.faa.gz b/data/example_output/alleles/alleles.faa.gz
diff --git a/data/example_output/alleles/alleles.faa.gz.dmnd b/data/example_output/alleles/alleles.faa.gz.dmnd
diff --git a/data/example_output/alleles/centroids.C100.fastp.gz b/data/example_output/alleles/centroids.C100.fastp.gz
diff --git a/data/example_output/alleles/centroids.C100.fastp.gz.dmnd b/data/example_output/alleles/centroids.C100.fastp.gz.dmnd
diff --git a/data/example_output/alleles/centroids.C50.fastp.gz b/data/example_output/alleles/centroids.C50.fastp.gz
diff --git a/data/example_output/alleles/centroids.C50.fastp.gz.dmnd b/data/example_output/alleles/centroids.C50.fastp.gz.dmnd
diff --git a/data/example_output/alleles/centroids.C90.fastp.gz b/data/example_output/alleles/centroids.C90.fastp.gz
diff --git a/data/example_output/alleles/centroids.C90.fastp.gz.dmnd b/data/example_output/alleles/centroids.C90.fastp.gz.dmnd
diff --git a/data/example_output/contigs/Mock__11/Mock__11.contigs.fasta.gz b/data/example_output/contigs/Mock__11/Mock__11.contigs.fasta.gz
diff --git a/data/example_output/contigs/Mock__11/Mock__11.faa.gz b/data/example_output/contigs/Mock__11/Mock__11.faa.gz
diff --git a/data/example_output/contigs/Mock__11/Mock__11.fna.gz b/data/example_output/contigs/Mock__11/Mock__11.fna.gz
diff --git a/data/example_output/contigs/Mock__11/Mock__11.gff.gz b/data/example_output/contigs/Mock__11/Mock__11.gff.gz
diff --git a/data/example_output/contigs/Mock__12/Mock__12.contigs.fasta.gz b/data/example_output/contigs/Mock__12/Mock__12.contigs.fasta.gz
diff --git a/data/example_output/contigs/Mock__12/Mock__12.faa.gz b/data/example_output/contigs/Mock__12/Mock__12.faa.gz
diff --git a/data/example_output/contigs/Mock__12/Mock__12.fna.gz b/data/example_output/contigs/Mock__12/Mock__12.fna.gz
diff --git a/data/example_output/contigs/Mock__12/Mock__12.gff.gz b/data/example_output/contigs/Mock__12/Mock__12.gff.gz
diff --git a/data/example_output/contigs/Mock__13/Mock__13.contigs.fasta.gz b/data/example_output/contigs/Mock__13/Mock__13.contigs.fasta.gz
diff --git a/data/example_output/contigs/Mock__13/Mock__13.faa.gz b/data/example_output/contigs/Mock__13/Mock__13.faa.gz
diff --git a/data/example_output/contigs/Mock__13/Mock__13.fna.gz b/data/example_output/contigs/Mock__13/Mock__13.fna.gz
diff --git a/data/example_output/contigs/Mock__13/Mock__13.gff.gz b/data/example_output/contigs/Mock__13/Mock__13.gff.gz
diff --git a/data/example_output/contigs/Mock__14/Mock__14.contigs.fasta.gz b/data/example_output/contigs/Mock__14/Mock__14.contigs.fasta.gz
diff --git a/data/example_output/contigs/Mock__14/Mock__14.faa.gz b/data/example_output/contigs/Mock__14/Mock__14.faa.gz
diff --git a/data/example_output/contigs/Mock__14/Mock__14.fna.gz b/data/example_output/contigs/Mock__14/Mock__14.fna.gz
diff --git a/data/example_output/contigs/Mock__14/Mock__14.gff.gz b/data/example_output/contigs/Mock__14/Mock__14.gff.gz
diff --git a/data/example_output/contigs/Mock__15/Mock__15.contigs.fasta.gz b/data/example_output/contigs/Mock__15/Mock__15.contigs.fasta.gz
diff --git a/data/example_output/contigs/Mock__15/Mock__15.faa.gz b/data/example_output/contigs/Mock__15/Mock__15.faa.gz
diff --git a/data/example_output/contigs/Mock__15/Mock__15.fna.gz b/data/example_output/contigs/Mock__15/Mock__15.fna.gz
diff --git a/data/example_output/contigs/Mock__15/Mock__15.gff.gz b/data/example_output/contigs/Mock__15/Mock__15.gff.gz
diff --git a/data/example_output/qc/manifest.qc.csv b/data/example_output/qc/manifest.qc.csv
@@ -1,6 +1,15 @@
 specimen,R1,R2
+<<<<<<< HEAD
 Mock__13,data/example_output/qc/Mock__13__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__13__R2.noadapt.nohuman.fq.gz
 Mock__14,data/example_output/qc/Mock__14__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__14__R2.noadapt.nohuman.fq.gz
 Mock__12,data/example_output/qc/Mock__12__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__12__R2.noadapt.nohuman.fq.gz
 Mock__15,data/example_output/qc/Mock__15__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__15__R2.noadapt.nohuman.fq.gz
 Mock__11,data/example_output/qc/Mock__11.R1.fastq.gz,data/example_output/qc/Mock__11.R2.fastq.gz
+=======
+Mock__15,data/example_output/qc/Mock__15__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__15__R2.noadapt.nohuman.fq.gz
+Mock__12,data/example_output/qc/Mock__12__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__12__R2.noadapt.nohuman.fq.gz
+Mock__13,data/example_output/qc/Mock__13__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__13__R2.noadapt.nohuman.fq.gz
+Mock__14,data/example_output/qc/Mock__14__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__14__R2.noadapt.nohuman.fq.gz
+Mock__11,data/example_output/qc/Mock__11.R1.fastq.gz,data/example_output/qc/Mock__11.R2.fastq.gz
+
+>>>>>>> 330481f5b4e8f27f9079254c26a021cfe6ebaee5
diff --git a/data/example_output/qc/manifest.qc.se.csv b/data/example_output/qc/manifest.qc.se.csv
@@ -0,0 +1,6 @@
+specimen,R1,R2
+Mock__12,data/example_output/qc/Mock__12__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__12__R2.noadapt.nohuman.fq.gz
+Mock__13,data/example_output/qc/Mock__13__R1.noadapt.nohuman.fq.gz,data/example_output/qc/Mock__13__R2.noadapt.nohuman.fq.gz
+Mock__14,data/example_output/qc/Mock__14__R1.noadapt.nohuman.fq.gz,
+Mock__15,data/example_output/qc/Mock__15__R1.noadapt.nohuman.fq.gz,
+Mock__11,data/example_output/qc/Mock__11.R1.fastq.gz,data/example_output/qc/Mock__11.R2.fastq.gz
diff --git a/data/example_output/quantify/per_specimen_json/Mock__11.json.gz b/data/example_output/quantify/per_specimen_json/Mock__11.json.gz
diff --git a/data/example_output/quantify/per_specimen_json/Mock__12.json.gz b/data/example_output/quantify/per_specimen_json/Mock__12.json.gz
diff --git a/data/example_output/quantify/per_specimen_json/Mock__13.json.gz b/data/example_output/quantify/per_specimen_json/Mock__13.json.gz
diff --git a/data/example_output/quantify/per_specimen_json/Mock__14.json.gz b/data/example_output/quantify/per_specimen_json/Mock__14.json.gz
diff --git a/data/example_output/quantify/per_specimen_json/Mock__15.json.gz b/data/example_output/quantify/per_specimen_json/Mock__15.json.gz
diff --git a/data/example_output/quantify/specimen_allele_quantity.h5ad b/data/example_output/quantify/specimen_allele_quantity.h5ad
diff --git a/data/mock.manifest.composition.csv b/data/mock.manifest.composition.csv