Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

hap1/hap2 scaffolding #51

Merged
merged 16 commits into from
Sep 6, 2024
Merged

hap1/hap2 scaffolding #51

Show file tree
Hide file tree
Changes from 12 commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
4eaea4d
Initiate scaffolding of hap1/hap2 contigs
Aug 1, 2024
f2e0856
Fix modules
Aug 1, 2024
0a18c54
Fix naming prefix
Aug 5, 2024
830fa9c
Fix naming error
Aug 5, 2024
9a2a39a
Fix meta after hic mapping
Aug 5, 2024
92c35da
Fix collision in scaffolding hap1/hap2 naming
Aug 5, 2024
f23a356
Run BUSCO on alts for hap1/hap2
Aug 5, 2024
59dd0d5
Move busco constants outside of main block
Aug 6, 2024
b0a9671
Fix warning and do linting checks
Aug 14, 2024
fc3c7f9
Parametrize hap1/hap2 within meta for scaffolding
Aug 15, 2024
3559a52
Merge conflict
Aug 15, 2024
1895861
Environment file for hifiasm module
Aug 29, 2024
eaa8851
Update usage.md
ksenia-krasheninnikova Sep 5, 2024
42fee8e
Update output.md
ksenia-krasheninnikova Sep 5, 2024
951a321
Prettier fix
Sep 5, 2024
cbc319e
Update output.md
ksenia-krasheninnikova Sep 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
207 changes: 188 additions & 19 deletions conf/modules.config
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ process {
]
}

withName: '.*GENOME_STATISTICS_RAW:BUSCO' {
withName: '.*GENOME_STATISTICS_RAW:BUSCO_PRI' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasm}/${meta.id}.p_ctg.${meta.lineage}.busco" },
mode: params.publish_dir_mode,
Expand Down Expand Up @@ -132,17 +132,17 @@ process {
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}
withName: '.*RAW_ASSEMBLY:GFA_TO_FASTA_PRI_HIC' {
ext.prefix = { "${meta.id}.asm.hic.p_ctg" }
withName: '.*RAW_ASSEMBLY:GFA_TO_FASTA_HAP1_HIC' {
ext.prefix = { "${meta.id}.asm.hic.hap1" }
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

withName: '.*RAW_ASSEMBLY:GFA_TO_FASTA_ALT_HIC' {
ext.prefix = { "${meta.id}.asm.hic.a_ctg" }
withName: '.*RAW_ASSEMBLY:GFA_TO_FASTA_HAP2_HIC' {
ext.prefix = { "${meta.id}.asm.hic.hap2" }
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}" },
mode: params.publish_dir_mode,
Expand All @@ -158,7 +158,7 @@ process {
]
}
withName: '.*GENOME_STATISTICS_RAW_HIC:GFASTATS_PRI' {
ext.prefix = { "${meta.id}.asm.hic.p_ctg" }
ext.prefix = { "${meta.id}.asm.hic.hap1" }
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}" },
mode: params.publish_dir_mode,
Expand All @@ -167,16 +167,30 @@ process {
}

withName: '.*GENOME_STATISTICS_RAW_HIC:GFASTATS_HAP' {
ext.prefix = { "${meta.id}.asm.hic.a_ctg" }
ext.prefix = { "${meta.id}.asm.hic.hap2" }
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}" },
mode: params.publish_dir_mode,
pattern: '*assembly_summary'
]
}
withName: '.*GENOME_STATISTICS_RAW_HIC:BUSCO' {

withName: '.*GENOME_STATISTICS_RAW_HIC:BUSCO_PRI' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/${meta.id}.p_ctg.${meta.lineage}.busco" },
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/${meta.id}.hap1.${meta.lineage}.busco" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.endsWith('busco.log') ? filename :
filename.endsWith('full_table.tsv') ? filename :
filename.endsWith('missing_busco_list.tsv') ? filename :
filename.startsWith('short_summary') ? filename :
filename.endsWith('busco.batch_summary.txt') ? filename :
null }
]
}

withName: '.*GENOME_STATISTICS_RAW_HIC:BUSCO_HAP' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/${meta.id}.hap2.${meta.lineage}.busco" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.endsWith('busco.log') ? filename :
filename.endsWith('full_table.tsv') ? filename :
Expand All @@ -189,7 +203,7 @@ process {

withName: '.*GENOME_STATISTICS_RAW_HIC:MERQURYFK_MERQURYFK' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/${meta.id}.p_ctg.ccs.merquryk" },
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/${meta.id}.hap1.ccs.merquryk" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
Expand Down Expand Up @@ -332,7 +346,7 @@ process {
]
}

withName: '.*GENOME_STATISTICS_PURGED:BUSCO' {
withName: '.*GENOME_STATISTICS_PURGED:BUSCO_PRI' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasm}/purging/${meta.id}.purged.${meta.lineage}.busco" },
mode: params.publish_dir_mode,
Expand Down Expand Up @@ -499,7 +513,7 @@ process {
]
}

withName: '.*HIC_MAPPING:SAMTOOLS_MERGE_HIC_MAPPING' {
withName: '.*HIC_MAPPING.*:SAMTOOLS_MERGE_HIC_MAPPING' {
ext.prefix = { "${meta.id}_merged" }
}

Expand Down Expand Up @@ -530,7 +544,7 @@ process {
}


withName: '.*HIC_MAPPING:CONVERT_STATS:SAMTOOLS_VIEW' {
withName: '.*HIC_MAPPING.*:CONVERT_STATS:SAMTOOLS_VIEW' {
ext.args = "--output-fmt cram"
}

Expand Down Expand Up @@ -559,7 +573,7 @@ process {
}

// Set up of the scffolding pipeline
withName: 'YAHS' {
withName: '.*SCAFFOLDING:YAHS' {
ext.prefix = 'out'
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasm}/scaffolding/yahs/out.break.yahs" },
Expand All @@ -568,7 +582,7 @@ process {
]
}

withName: 'COOLER_CLOAD' {
withName: '.*SCAFFOLDING:COOLER_CLOAD' {
// Positions in the input file are zero-based;
// chrom1 field number (one-based) is 2;
// pos1 field number (one-based) is 3;
Expand All @@ -582,7 +596,7 @@ process {
]
}

withName: 'PRETEXTSNAPSHOT' {
withName: '.*SCAFFOLDING:PRETEXTSNAPSHOT' {
// Make one plot containing all sequences
ext.args = '--sequences \"=full\"'
publishDir = [
Expand All @@ -592,7 +606,7 @@ process {
]
}

withName: 'JUICER_TOOLS_PRE' {
withName: '.*SCAFFOLDING:JUICER_TOOLS_PRE' {
ext.juicer_tools_jar = 'juicer_tools.1.9.9_jcuda.0.8.jar'
ext.juicer_jvm_params = '-Xms1g -Xmx6g'
publishDir = [
Expand All @@ -602,7 +616,7 @@ process {
]
}

withName: 'JUICER_PRE' {
withName: '.*SCAFFOLDING:JUICER_PRE' {
ext.args2 = "LC_ALL=C sort -k2,2d -k6,6d -S50G | awk '\$3>=0 && \$7>=0'"
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasm}/scaffolding/yahs/out.break.yahs" },
Expand All @@ -620,7 +634,7 @@ process {
]
}

withName: '.*GENOME_STATISTICS_SCAFFOLDS:BUSCO' {
withName: '.*GENOME_STATISTICS_SCAFFOLDS:BUSCO_PRI' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasm}/scaffolding/yahs/out.break.yahs/out_scaffolds_final.${meta.lineage}.busco" },
mode: params.publish_dir_mode,
Expand All @@ -640,6 +654,161 @@ process {
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

// Scaffolding hap1/hap2
if (params.hifiasm_hic_on) {

withName: '.*HIC_MAPPING_HAP.*:SAMTOOLS_MARKDUP_HIC_MAPPING' {
ext.prefix = { "${meta.id}_mkdup" }
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

withName: '.*HIC_MAPPING_HAP.*:BAMTOBED_SORT' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}


withName: '.*HIC_MAPPING_HAP.*:CONVERT_STATS:SAMTOOLS_STATS' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

withName: '.*HIC_MAPPING_HAP.*:CONVERT_STATS:SAMTOOLS_FLAGSTAT' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

withName: '.*HIC_MAPPING_HAP.*:CONVERT_STATS:SAMTOOLS_IDXSTATS' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

withName: '.*SCAFFOLDING_HAP.*:YAHS' {
ext.prefix = { "${meta.hap_id}" }
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}/yahs/out.break.yahs" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]

}

withName: '.*SCAFFOLDING_HAP.*:COOLER_CLOAD' {
// Positions in the input file are zero-based;
// chrom1 field number (one-based) is 2;
// pos1 field number (one-based) is 3;
// chrom2 field number (one-based) is 6;
// pos2 field number (one-based) is 7
ext.args = 'pairs -0 -c1 2 -p1 3 -c2 6 -p2 7'
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}/yahs/out.break.yahs" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

withName: '.*SCAFFOLDING_HAP.*:PRETEXTSNAPSHOT' {
// Make one plot containing all sequences
ext.args = '--sequences \"=full\"'
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}/yahs/out.break.yahs" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

withName: '.*SCAFFOLDING_HAP.*:JUICER_TOOLS_PRE' {
ext.juicer_tools_jar = 'juicer_tools.1.9.9_jcuda.0.8.jar'
ext.juicer_jvm_params = '-Xms1g -Xmx6g'
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}/yahs/out.break.yahs" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

withName: '.*SCAFFOLDING_HAP.*:JUICER_PRE' {
ext.args2 = "LC_ALL=C sort -k2,2d -k6,6d -S50G | awk '\$3>=0 && \$7>=0'"
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_${meta.hap_id}/yahs/out.break.yahs" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}
}

// End of hap1/hap2 scaffolding

withName: '.*GENOME_STATISTICS_SCAFFOLDS_HAPS:GFASTATS_PRI' {
ext.prefix = { "${meta.id}_scaffolds_final" }
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_hap1/yahs/out.break.yahs" },
mode: params.publish_dir_mode,
pattern: '*assembly_summary'
]
}

withName: '.*GENOME_STATISTICS_SCAFFOLDS_HAPS:GFASTATS_HAP' {
ext.prefix = { "${meta.id}_scaffolds_final" }
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_hap2/yahs/out.break.yahs" },
mode: params.publish_dir_mode,
pattern: '*assembly_summary'
]
}

withName: '.*GENOME_STATISTICS_SCAFFOLDS_HAPS:BUSCO_PRI' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_hap1/yahs/out.break.yahs/out_scaffolds_final.${meta.lineage}.busco" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.endsWith('busco.log') ? filename :
filename.endsWith('full_table.tsv') ? filename :
filename.endsWith('missing_busco_list.tsv') ? filename :
filename.startsWith('short_summary') ? filename :
filename.endsWith('busco.batch_summary.txt') ? filename :
null }
]
}

withName: '.*GENOME_STATISTICS_SCAFFOLDS_HAPS:BUSCO_HAP' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_hap2/yahs/out.break.yahs/out_scaffolds_final.${meta.lineage}.busco" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.endsWith('busco.log') ? filename :
filename.endsWith('full_table.tsv') ? filename :
filename.endsWith('missing_busco_list.tsv') ? filename :
filename.startsWith('short_summary') ? filename :
filename.endsWith('busco.batch_summary.txt') ? filename :
null }
]
}

withName: '.*GENOME_STATISTICS_SCAFFOLDS_HAPS:MERQURYFK_MERQURYFK' {
publishDir = [
path: { "${params.outdir}/${meta.id}.${params.hifiasmhic}/scaffolding_hap1/yahs/out.break.yahs/out_scaffolds_final.ccs.merquryk" },
mode: params.publish_dir_mode,
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
}

// End of Scaffolding hap1/hap2
// End of Set up of the scaffolding pipeline

//Set up of assembly stats subworkflow
Expand Down
8 changes: 8 additions & 0 deletions modules/nf-core/hifiasm/environment.yml
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

21 changes: 17 additions & 4 deletions modules/nf-core/hifiasm/hifiasm.diff
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

Loading
Loading