Release v0.5.0 (#33)

Author: leahkemp

README.md

@@ -26,12 +26,14 @@ snp_indel_calling{{"SNP/indel variant calling"}}
 snp_indel_phasing{{"SNP/indel phasing"}}
 snp_indel_annotation{{"SNP/indel annotation (optional - hg38 only)"}}
 haplotagging{{"Haplotagging bams"}}
+calculate_base_mod_freqs{{"Calculate base modificiation frequencies (ont data only)"}}
 generate_meth_probs{{"Generate site methylation probabilities (pacbio data only)"}}
 sv_calling{{"Structural variant calling"}}
 sv_annotation{{"Structural variant annotation (optional - hg38 only)"}}
 
 input_data-.->merging-.->alignment-.->snp_indel_calling-.->snp_indel_phasing-.->haplotagging-.->sv_calling
 alignment-.->depth
+alignment-.->calculate_base_mod_freqs
 alignment-.->haplotagging
 haplotagging-.->generate_meth_probs
 snp_indel_phasing-.->snp_indel_annotation
@@ -85,17 +87,20 @@ haplotagging_s2{{"Description: haplotagging bams <br><br> Main tools: WhatsHap <
 haplotagging_s3{{"Description: haplotagging bams <br><br> Main tools: WhatsHap <br><br> Commands: whatshap haplotag"}}
 haplotagging_s4{{"Description: haplotagging bams <br><br> Main tools: WhatsHap <br><br> Commands: whatshap haplotag"}}
 
-generate_meth_probs_s2{{"Description: Generate site methylation probabilities <br><br> Main tools: pb-CpG-tools <br><br> Commands: aligned_bam_to_cpg_scores"}}
+calculate_base_mod_freqs_s1{{"Description: calculate base modificiation frequencies <br><br> Main tools: minimod <br><br> Commands: minimod mod-freq"}}
+generate_meth_probs_s2{{"Description: generate site methylation probabilities <br><br> Main tools: pb-CpG-tools <br><br> Commands: aligned_bam_to_cpg_scores"}}
+calculate_base_mod_freqs_s3{{"Description: calculate base modificiation frequencies <br><br> Main tools: minimod <br><br> Commands: minimod mod-freq"}}
+calculate_base_mod_freqs_s4{{"Description: calculate base modificiation frequencies <br><br> Main tools: minimod <br><br> Commands: minimod mod-freq"}}
 
 sv_calling_s1{{"Description: structural variant calling <br><br> Main tools: Sniffles2 and/or cuteSV <br><br> Commands: sniffles and/or cuteSV"}}
 sv_calling_s2{{"Description: structural variant calling <br><br> Main tools: Sniffles2 and/or cuteSV <br><br> Commands: sniffles and/or cuteSV"}}
 sv_calling_s3{{"Description: structural variant calling <br><br> Main tools: Sniffles2 and/or cuteSV <br><br> Commands: sniffles and/or cuteSV"}}
 sv_calling_s4{{"Description: structural variant calling <br><br> Main tools: Sniffles2 and/or cuteSV <br><br> Commands: sniffles and/or cuteSV"}}
 
-sv_annotation_s1{{"Description: Structural variant annotation (optional - hg38 only)" <br><br> Main tools: ensembl-vep <br><br> Commands: vep}}
-sv_annotation_s2{{"Description: Structural variant annotation (optional - hg38 only)" <br><br> Main tools: ensembl-vep <br><br> Commands: vep}}
-sv_annotation_s3{{"Description: Structural variant annotation (optional - hg38 only)" <br><br> Main tools: ensembl-vep <br><br> Commands: vep}}
-sv_annotation_s4{{"Description: Structural variant annotation (optional - hg38 only)" <br><br> Main tools: ensembl-vep <br><br> Commands: vep}}
+sv_annotation_s1{{"Description: structural variant annotation (optional - hg38 only)" <br><br> Main tools: ensembl-vep <br><br> Commands: vep}}
+sv_annotation_s2{{"Description: structural variant annotation (optional - hg38 only)" <br><br> Main tools: ensembl-vep <br><br> Commands: vep}}
+sv_annotation_s3{{"Description: structural variant annotation (optional - hg38 only)" <br><br> Main tools: ensembl-vep <br><br> Commands: vep}}
+sv_annotation_s4{{"Description: structural variant annotation (optional - hg38 only)" <br><br> Main tools: ensembl-vep <br><br> Commands: vep}}
 
 ont_data_f1-.->merging_m1-.->alignment_s1-.->snp_indel_calling_s1-.->snp_indel_phasing_s1-.->haplotagging_s1-.->sv_calling_s1
 ont_data_f2-.->merging_m1
@@ -109,6 +114,10 @@ alignment_s2-.->depth_s2
 alignment_s3-.->depth_s3
 alignment_s4-.->depth_s4
 
+alignment_s1-.->calculate_base_mod_freqs_s1
+alignment_s3-.->calculate_base_mod_freqs_s3
+alignment_s4-.->calculate_base_mod_freqs_s4
+
 alignment_s1-.->haplotagging_s1
 alignment_s2-.->haplotagging_s2
 alignment_s3-.->haplotagging_s3
@@ -142,6 +151,7 @@ sv_calling_s4-.->sv_annotation_s4
 - [Sniffles2](https://github.com/fritzsedlazeck/Sniffles) and/or [cuteSV](https://github.com/tjiangHIT/cuteSV)
 - [Samtools](https://github.com/samtools/samtools)
 - [mosdepth](https://github.com/brentp/mosdepth)
+- [minimod](https://github.com/warp9seq/minimod?tab=readme-ov-file)
 - [pb-CpG-tools](https://github.com/PacificBiosciences/pb-CpG-tools)
 - [ensembl-vep](https://github.com/Ensembl/ensembl-vep)
 
@@ -164,6 +174,7 @@ sv_calling_s4-.->sv_annotation_s4
 - Alignment depth per chromosome (and per region in the case of targeted sequencing) (optional)
 - Phased Clair3 or DeepVariant SNP/indel VCF file
 - Phased and annotated Clair3 or DeepVariant SNP/indel VCF file (optional - hg38 only)
+- Bed base modification frequencies (ont only)
 - Bed and bigwig site methylation probabilities for complete read set and separate haplotypes (pacbio only)
 - Phased Sniffles2 and/or un-phased cuteSV SV VCF file
 - Phased and annotated Sniffles2 and/or un-phased and annotated cuteSV SV VCF file

config/nextflow_pipeface.config

@@ -50,6 +50,14 @@ process {
         module = 'minimap2/2.28:samtools/1.19'
     }
 
+    withName: minimod {
+        queue = 'normal'
+        cpus = '8'
+        time = '2h'
+        memory = '32GB'
+        module = 'minimod/0.2.0'
+    }
+
     withName: mosdepth {
         queue = 'normal'
         cpus = '8'

docs/run_on_nci.md

@@ -159,6 +159,7 @@ Requirements:
 - provide full file paths
 - multiple entries for a given `sample_id` are required to have the same file extension in the `file` column (eg. '.bam', '.fastq.gz' or '.fastq')
 - for entries in the `file` column, the file extension must be either '.bam', '.fastq.gz' or '.fastq' (as appropriate)
+- for entries in the `file` column, files containing methylation data should be provided in uBAM format (and not FASTQ format)
 - entries in the `data_type` column must be either 'ont' or 'pacbio' (as appropriate)
 
 ## 4. Modify nextflow_pipeface.config

docs/software_versions.txt

@@ -1,5 +1,6 @@
 Samtools: 1.19
 Minimap2: 2.28-r1209
+minimod: 0.2.0
 mosdepth: 0.3.9
 Clair3: 1.0.9
 DeepVariant 1.6.1

pipeface.nf

@@ -219,10 +219,11 @@ process minimap2 {
         """
         # run minimap
         minimap2 \
+        -y \
+        -Y \
         --secondary=no \
         --MD \
-        -a \
-        -Y \
+	-a \
         -x $preset \
         -t ${task.cpus} \
         $ref \
@@ -241,6 +242,53 @@ process minimap2 {
 
 }
 
+process minimod {
+
+    def software = "minimod"
+
+    publishDir "$outdir/$family_id/$outdir2/$sample_id", mode: 'copy', overwrite: true, saveAs: { filename -> "$sample_id.$ref_name.$software.$filename" }, pattern: 'modfreqs.bed'
+
+    input:
+        tuple val(sample_id), val(family_id), path(bam), val(data_type)
+        val ref
+        val ref_index
+        val outdir
+        val outdir2
+        val ref_name
+
+    output:
+        tuple val(sample_id), val(family_id), path('modfreqs.bed'), optional: true
+
+    script:
+    if( data_type == 'ont' )
+        """
+        # stage bam and bam index
+        # do this here instead of input tuple so I can handle processing an aligned bam as an input file without requiring a bam index for ubam input
+        bam_loc=\$(realpath ${bam})
+        ln -sf \${bam_loc} sorted.bam
+        ln -sf \${bam_loc}.bai .
+        ln -sf \${bam_loc}.bai sorted.bam.bai
+        # run minimod
+        minimod \
+        mod-freq \
+        -b \
+        $ref \
+        $bam \
+        -t ${task.cpus} \
+        -o modfreqs.bed
+        """
+    else if( data_type == 'pacbio' )
+        """
+        echo "Data type is pacbio, not running minimod on this data."
+        """
+
+    stub:
+        """
+        touch modfreqs.bed
+        """
+
+}
+
 process mosdepth {
 
     def depth_software = "mosdepth"
@@ -1251,6 +1299,7 @@ workflow {
         bam = id_tuple.join(files_tuple, by: [0,1])
     }
     if ( in_data_format == 'ubam_fastq' | in_data_format == 'aligned_bam' ) {
+        minimod(bam.join(data_type_tuple, by: [0,1]), ref, ref_index, outdir, outdir2, ref_name)
         if ( calculate_depth == 'yes' ) {
             mosdepth(bam.join(regions_of_interest_tuple, by: [0,1]), mosdepth_binary, outdir, outdir2, ref_name)
         }