Chore/docs and test cleanup

conf/test.config

@@ -7,7 +7,6 @@
     Usage examples:
         nextflow run sheynkmanlab/lrp2 -profile test_rna,<docker/singularity> --outdir <OUTDIR>
         nextflow run sheynkmanlab/lrp2 -profile test_dda,<docker/singularity> --outdir <OUTDIR>
-        nextflow run sheynkmanlab/lrp2 -profile test_dia,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */
@@ -44,18 +43,4 @@ profiles {
             fragpipe_license_accept = true
         }
     }
-
-    test_dia {
-        params {
-            config_profile_name        = 'RNA + DIA mass spec test profile'
-            config_profile_description = 'Test dataset with RNA and DIA mass spectrometry samples'
-
-            input        = "${projectDir}/sample_data/samplesheet_rna_dia.csv"
-            dataset_name = 'lrptest_dia'
-
-            genome = 'GRCh38.p14.v49'
-            protein_search = 'fragpipe'
-            fragpipe_license_accept = true
-        }
-    }
 }

modules/local/fragpipe/main.nf

@@ -140,11 +140,8 @@ process FRAGPIPE {
 
     # Update workflow with database path and decoy tag
     WORK_DIR="\$(pwd)"
-
-    # Ensure workflow file ends with a newline (some upstream versions omit it)
-    sed -i -e '\$a\\' workflow.workflow
-    echo "database.db-path=\$WORK_DIR/database_with_decoys.fasta" >> workflow.workflow
-    echo "database.decoy-tag=${decoy_tag}" >> workflow.workflow
+    printf "\ndatabase.db-path=%s\n" "\$WORK_DIR/database_with_decoys.fasta" >> workflow.workflow
+    printf "database.decoy-tag=%s\n" "${decoy_tag}" >> workflow.workflow
 
     echo ""
 
@@ -386,4 +383,4 @@ process FRAGPIPE {
         ionquant: 1.10.12
     END_VERSIONS
     """
-}
+}

modules/local/isocall_call/main.nf

@@ -3,7 +3,9 @@ process ISOCALL_CALL {
     label 'process_low'
 
     conda "${moduleDir}/environment.yml"
-    container "quay.io/pacbio/isocall:0.15.0_build1"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'docker://quay.io/pacbio/isocall:0.15.0_build1' :
+        'quay.io/pacbio/isocall:0.15.0_build1' }"
 
     input:
     tuple val(meta), path(merged_profile)
@@ -13,8 +15,7 @@ process ISOCALL_CALL {
 
     output:
     tuple val(meta), path("*.isocall.isoforms.gtf.gz"), emit: gtf
-    tuple val(meta), path("*.isocall.count_matrix.txt"), emit: count_matrix
-    tuple val(meta), path("*_S1_PACBIO_ISOCALL_M5_ISOCALL_CALL_log.txt"), emit: log
+    tuple val(meta), path("*.isocall.count_matrix.csv"), emit: count_matrix
     path "versions.yml", emit: versions
 
     when:
@@ -27,8 +28,6 @@ process ISOCALL_CALL {
     def min_read_support = task.ext.min_read_support ?: params.min_read_support
     def max_bundles_per_gene = task.ext.max_bundles_per_gene ?: params.max_bundles_per_gene
     """
-    exec > >(tee ${prefix}_S1_PACBIO_ISOCALL_M5_ISOCALL_CALL_log.txt) 2>&1
-
     isocall call \\
         --threads $threads \\
         --merged-profile $merged_profile \\
@@ -39,7 +38,9 @@ process ISOCALL_CALL {
         --min-reads-per-isoform $min_read_support \\
         --max-bundles-per-gene $max_bundles_per_gene \\
         $args
-
+
+    mv ${prefix}.isocall.count_matrix.txt ${prefix}.isocall.count_matrix.csv
+
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         isocall: \$( isocall --version 2>&1 | sed 's/isocall //g' )
@@ -50,8 +51,7 @@ process ISOCALL_CALL {
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
     touch ${prefix}.isocall.isoforms.gtf.gz
-    touch ${prefix}.isocall.count_matrix.txt
-    touch ${prefix}_S1_PACBIO_ISOCALL_M5_ISOCALL_CALL_log.txt
+    touch ${prefix}.isocall.count_matrix.csv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/local/sqanti_qc/main.nf

@@ -3,7 +3,7 @@ process SQANTI_QC {
     label 'process_long'
 
     conda "${moduleDir}/environment.yml"
-    container 'docker://docker.io/anaconesalab/sqanti3:5.2.2'
+    container 'docker://docker.io/anaconesalab/sqanti3:v6.0.1'
 
     input:
     tuple val(meta), path(isoforms_gtf), path(flnc_count)
@@ -20,7 +20,6 @@ process SQANTI_QC {
     tuple val(meta), path("*.transcriptome.junctions.txt"), emit: junctions
 //    tuple val(meta), path("*.transcriptome.params.txt"), emit: params
 //    tuple val(meta), path("refAnnotation.*.genePred"), emit: refannotation_genepred
-    tuple val(meta), path("*_S2_TRANSCRIPTOME_M1_SQANTI_QC_log.txt"), emit: log
     path "versions.yml", emit: versions
 
     when:
@@ -31,10 +30,9 @@ process SQANTI_QC {
     def prefix = task.ext.prefix ?: "${meta.id}"
 
     """
-    exec > >(tee ${prefix}_S2_TRANSCRIPTOME_M1_SQANTI_QC_log.txt) 2>&1
-
+
     source /conda/miniconda3/etc/profile.d/conda.sh
-    conda activate SQANTI3.env
+    conda activate sqanti3
 
     # Decompress GTF if it's gzipped
     ISOFORMS_INPUT="$isoforms_gtf"
@@ -48,27 +46,32 @@ process SQANTI_QC {
     fi
 
     sqanti3_qc.py \\
-        --force_id_ignore \\
-        --skipORF \\
-        --output ${prefix}.transcriptome \\
-        --dir . \\
-        --cpus $task.cpus \\
-        --chunks $task.cpus \\
+        --isoforms "\$ISOFORMS_INPUT" \\
+        --refGTF $reference_gtf \\
+        --refFasta $reference_fasta \\
+        -o ${prefix}.transcriptome \\
+        -d . \\
         --report skip \\
-        --fl_count $flnc_count \\
-        "\$ISOFORMS_INPUT" \\
-        $reference_gtf \\
-        $reference_fasta \\
+        --fl $flnc_count \\
         $args
 
+    # Fix single-sample column naming to use "FL.{sample_id}", which is consistent with formatting used for multi-sample runs
+    TAB=\$'\\t'
+    if head -1 ${prefix}.transcriptome_classification.txt | grep -qE "\${TAB}FL\${TAB}|\${TAB}FL\\.\${TAB}"; then
+        SAMPLE_NAME=\$(head -1 $flnc_count | awk -F',' '{print \$2}')
+        awk -v sample="\${SAMPLE_NAME}" 'NR==1 {gsub(/\\tFL\\t|\\tFL\\.\\t/, "\\tFL."sample"\\t")} {print}' \\
+            ${prefix}.transcriptome_classification.txt > ${prefix}.transcriptome_classification.tmp.txt
+        mv ${prefix}.transcriptome_classification.tmp.txt ${prefix}.transcriptome_classification.txt
+    fi
+
     mv ${prefix}.transcriptome_classification.txt ${prefix}.transcriptome.SQANTI_classification.txt
     mv ${prefix}.transcriptome_corrected.gtf ${prefix}.transcriptome.gtf
     mv ${prefix}.transcriptome_corrected.fasta ${prefix}.transcriptome.fasta
     mv ${prefix}.transcriptome_junctions.txt ${prefix}.transcriptome.junctions.txt
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        sqanti3: 5.2.2
+        sqanti3: 6.0.1
     END_VERSIONS
     """
 
@@ -79,11 +82,10 @@ process SQANTI_QC {
     touch ${prefix}.transcriptome.gtf
     touch ${prefix}.transcriptome.fasta
     touch ${prefix}.transcriptome.junctions.txt
-    touch ${prefix}_S2_TRANSCRIPTOME_M1_SQANTI_QC_log.txt
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        sqanti3: 5.2.2
+        sqanti3: 6.0.1
     END_VERSIONS
     """
 }

nextflow.config

@@ -271,7 +271,6 @@ profiles {
     }
     test_rna  { includeConfig 'conf/test.config' }
     test_dda  { includeConfig 'conf/test.config' }
-    test_dia  { includeConfig 'conf/test.config' }
     test_full { includeConfig 'conf/test_full.config' }
 }