Adding UMI consensus flow to the pipeline

README.md

@@ -14,6 +14,8 @@ It also performs basic QC and coverage analysis.
 
 The pipeline is built using Nextflow, a workflow tool to run tasks across multiple compute infrastructures in a very portable manner. It comes with docker containers making installation trivial and results highly reproducible.
 
+The pipeline also supports Unique Molecular Identifier (UMI) data. If your samplesheet includes a `umi_type` column (`seq` or `readname`), UMI-aware preprocessing is enabled automatically. Rows with no `umi_type` specified will be processed as non-UMI sequencing data.
+
 Steps inlcude:
 
 1. Demultiplexing using [`BCLconvert`](https://emea.support.illumina.com/sequencing/sequencing_software/bcl-convert.html)
@@ -24,7 +26,13 @@ Steps inlcude:
 6. Alignment QC using [`samtools flagstat`](http://www.htslib.org/doc/samtools-flagstat.html), [`samtools stats`](http://www.htslib.org/doc/samtools-stats.html), [`samtools idxstats`](http://www.htslib.org/doc/samtools-idxstats.html) and [`picard CollecHsMetrics`](https://broadinstitute.github.io/picard/command-line-overview.html#CollectHsMetrics), [`picard CollectWgsMetrics`](https://broadinstitute.github.io/picard/command-line-overview.html#CollectWgsMetrics), [`picard CollectMultipleMetrics`](https://broadinstitute.github.io/picard/command-line-overview.html#CollectMultipleMetrics)
 7. QC aggregation using [`multiqc`](https://multiqc.info/)
 
-![metro map](docs/images/metro_map.png)
+![metro map](docs/images/metro_mapumi.png)
+
+UMI processing (only for rows with `umi_type`):
+- Extract UMI from read sequence (`seq`) or read name (`readname`)
+- Group reads by UMI (fgbio GroupReadsByUmi)
+- Call molecular consensus (fgbio CallMolecularConsensusReads) and filter (fgbio FilterConsensusReads)
+- Re-align filtered consensus reads with BWA-MEM (`-Y`), then sort/index
 
 ## Usage
 
@@ -41,6 +49,12 @@ First, prepare a samplesheet with your input data that looks as follows:
 id,samplename,organism,library,fastq_1,fastq_2
 sample1,sample1,Homo sapiens,Library_Name,reads1.fq.gz,reads2.fq.gz
 ```
+`samplesheet.csv` for fastq inputs with UMI:
+
+```csv
+id,samplename,organism,library,umi_type,fastq_1,fastq_2
+umi_sample1,umi_sample1,Homo sapiens,Library_Name,seq,reads1.fq.gz,reads2.fq.gz
+```
 
 `samplesheet.csv` for flowcell inputs:
 

assets/schema_input.json

@@ -72,6 +72,13 @@
                 "pattern": "^[a-zA-Z0-9_]+.bed$",
                 "default": null
             },
+            "umi_type": {
+                "meta": ["umi_type"],
+                "type": "string",
+                "description": "Distinguish UMI samples (readname, seq) from non-UMI samples",
+                "enum": ["readname", "seq", "none"],
+                "default": "none"
+            },
             "lane": {
                 "type": "integer",
                 "meta": ["lane"],
@@ -110,13 +117,13 @@
         },
         "anyOf": [
             {
-                "required": ["id", "samplename", "organism", "tag", "fastq_1", "fastq_2"]
+                "required": ["id", "samplename", "organism", "tag", "fastq_1", "fastq_2", "umi_type"]
             },
             {
-                "required": ["id", "samplename", "genome", "tag", "fastq_1", "fastq_2"]
+                "required": ["id", "samplename", "genome", "tag", "fastq_1", "fastq_2", "umi_type"]
             },
             {
-                "required": ["id", "samplesheet", "sample_info", "flowcell"]
+                "required": ["id", "samplesheet", "sample_info", "flowcell", "umi_type"]
             }
         ]
     },

modules.json

@@ -51,6 +51,55 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/fastp/fastp.diff"
                     },
+                    "fgbio/callduplexconsensusreads": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
+                    "fgbio/callmolecularconsensusreads": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
+                    "fgbio/collectduplexseqmetrics": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
+                    "fgbio/copyumifromreadname": {
+                        "branch": "master",
+                        "git_sha": "47dbfc0fbcd8e4e3b73d843f4659069441ca8692",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/fgbio/copyumifromreadname/fgbio-copyumifromreadname.diff"
+                    },
+                    "fgbio/fastqtobam": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/fgbio/fastqtobam/fgbio-fastqtobam.diff"
+                    },
+                    "fgbio/filterconsensusreads": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/fgbio/filterconsensusreads/fgbio-filterconsensusreads.diff"
+                    },
+                    "fgbio/groupreadsbyumi": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
+                    "fgbio/sortbam": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
+                    "fgbio/zipperbams": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/fgbio/zipperbams/fgbio-zipperbams.diff"
+                    },
                     "md5sum": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
@@ -103,6 +152,11 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/samtools/coverage/samtools-coverage.diff"
                     },
+                    "samtools/fastq": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
                     "samtools/flagstat": {
                         "branch": "master",
                         "git_sha": "2d20463181b1c38981a02e90d3084b5f9fa8d540",
@@ -118,6 +172,11 @@
                         "git_sha": "2d20463181b1c38981a02e90d3084b5f9fa8d540",
                         "installed_by": ["modules"]
                     },
+                    "samtools/index": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
                     "samtools/sormadup": {
                         "branch": "master",
                         "git_sha": "38f3b0200093498b70ac2d63a83eac5642e3c873",