Merge branch 'bams_CW-3512' into 'dev'

BAM input CW-3512

See merge request epi2melabs/workflows/wf-transcriptomes!172

.gitlab-ci.yml

@@ -50,7 +50,7 @@ docker-run:
     parallel:
         matrix:
             - MATRIX_NAME: [
-                "fusions", "differential_expression", "isoforms",
+                "fusions", "differential_expression", "isoforms", "isoforms_bam",
                 "only_differential_expression", "differential_expression_gff3",
                 "ncbi_gzip", "ncbi_no_gene_id", "ensembl_with_versions",
                 "differential_expression_mouse", "no_ref_annotation"
@@ -68,6 +68,13 @@ docker-run:
                   --ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa --ref_annotation ${CI_PROJECT_NAME}/data/chr20/gencode.v22.annotation.chr20.gtf --pychopper_backend phmm \
                   -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
               NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
+        - if: $MATRIX_NAME == "isoforms_bam"
+          variables:
+            NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz -C ${CI_PROJECT_NAME}/data/ &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
+            NF_WORKFLOW_OPTS: "--bam  ${CI_PROJECT_NAME}/data/ERR6053095_chr20.bam --transcriptome-source reference-guided \
+                  --ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa --ref_annotation ${CI_PROJECT_NAME}/data/chr20/gencode.v22.annotation.chr20.gtf --pychopper_backend phmm \
+                  -c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
+            NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
         - if: $MATRIX_NAME == "no_ref_annotation"
           variables:
               NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz && tar -xzvf  ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz -C ${CI_PROJECT_NAME}/data/ &&  wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config

README.md

@@ -86,9 +86,9 @@ Find related protocols in the [Nanopore community](https://community.nanoporetec
 ## Input example
 
 <!---Example of input directory structure, delete and edit as appropriate per workflow.--->
-This workflow accepts FASTQ files as input.
+This workflow accepts either FASTQ or BAM files as input.
 
-The FASTQ input parameters for this workflow accept one of three cases: (i) the path to a single FASTQ file; (ii) the path to a top-level directory containing FASTQ files; (iii) the path to a directory containing one level of sub-directories which in turn contain FASTQ files. In the first and second cases (i and ii), a sample name can be supplied with `--sample`. In the last case (iii), the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`. If you are using the workflow for differential expression analysis the last case(iii) will be expected with a minimum of 4 samples (at least 2 replicates of each sample to compare) but we recommend 6 samples (three replicates).
+The FASTQ or BAM input parameters for this workflow accept one of three cases: (i) the path to a single FASTQ or BAM file; (ii) the path to a top-level directory containing FASTQ or BAM files; (iii) the path to a directory containing one level of sub-directories which in turn contain FASTQ or BAM files. In the first and second cases (i and ii), a sample name can be supplied with `--sample`. In the last case (iii), the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`.
 
 ```
 (i)                     (ii)                 (iii)    
@@ -106,7 +106,6 @@ input_reads.fastq   ─── input_directory  ─── input_directory
 
 
 
-
 ## Input parameters
 
 ### Input Options
@@ -114,6 +113,7 @@ input_reads.fastq   ─── input_directory  ─── input_directory
 | Nextflow parameter name  | Type | Description | Help | Default |
 |--------------------------|------|-------------|------|---------|
 | fastq | string | FASTQ files to use in the analysis. | This accepts one of three cases: (i) the path to a single FASTQ file; (ii) the path to a top-level directory containing FASTQ files; (iii) the path to a directory containing one level of sub-directories which in turn contain FASTQ files. In the first and second case, a sample name can be supplied with `--sample`. In the last case, the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`. |  |
+| bam | string | BAM or unaligned BAM (uBAM) files to use in the analysis. | This accepts one of three cases: (i) the path to a single BAM file; (ii) the path to a top-level directory containing BAM files; (iii) the path to a directory containing one level of sub-directories which in turn contain BAM files. In the first and second case, a sample name can be supplied with `--sample`. In the last case, the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`. |  |
 | transcriptome_source | string | Select how the transcriptome used for analysis should be prepared. | To analyse only gene fusions and differential expression use of an existing transcriptome may be preferred and so 'precomputed' should be selected. In this case the 'ref_transcriptome' parameter should be specified. To create a reference transcriptome using an existing reference genome, select 'reference guided' and specify the 'ref_genome' parameter. | reference-guided |
 | ref_genome | string | Path to reference genome sequence [.fa/.fq/.fa.gz/fq.gz]. Required for reference-based workflow. | A reference genome is required for reference-based assembly of a transcriptome. |  |
 | ref_transcriptome | string | Transcriptome reference file. Required for precomputed transcriptome calculation and for differential expression analysis. | A reference transcriptome related to the sample under study. Must be supplied when the 'Transcriptome source' parameter has been set to 'precomputed' or to perform differential expression. |  |

docs/06_input_example.md

@@ -1,7 +1,7 @@
 <!---Example of input directory structure, delete and edit as appropriate per workflow.--->
-This workflow accepts FASTQ files as input.
+This workflow accepts either FASTQ or BAM files as input.
 
-The FASTQ input parameters for this workflow accept one of three cases: (i) the path to a single FASTQ file; (ii) the path to a top-level directory containing FASTQ files; (iii) the path to a directory containing one level of sub-directories which in turn contain FASTQ files. In the first and second cases (i and ii), a sample name can be supplied with `--sample`. In the last case (iii), the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`. If you are using the workflow for differential expression analysis the last case(iii) will be expected with a minimum of 4 samples (at least 2 replicates of each sample to compare) but we recommend 6 samples (three replicates).
+The FASTQ or BAM input parameters for this workflow accept one of three cases: (i) the path to a single FASTQ or BAM file; (ii) the path to a top-level directory containing FASTQ or BAM files; (iii) the path to a directory containing one level of sub-directories which in turn contain FASTQ or BAM files. In the first and second cases (i and ii), a sample name can be supplied with `--sample`. In the last case (iii), the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`.
 
 ```
 (i)                     (ii)                 (iii)    

docs/06_input_parameters.md

@@ -3,6 +3,7 @@
 | Nextflow parameter name  | Type | Description | Help | Default |
 |--------------------------|------|-------------|------|---------|
 | fastq | string | FASTQ files to use in the analysis. | This accepts one of three cases: (i) the path to a single FASTQ file; (ii) the path to a top-level directory containing FASTQ files; (iii) the path to a directory containing one level of sub-directories which in turn contain FASTQ files. In the first and second case, a sample name can be supplied with `--sample`. In the last case, the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`. |  |
+| bam | string | BAM or unaligned BAM (uBAM) files to use in the analysis. | This accepts one of three cases: (i) the path to a single BAM file; (ii) the path to a top-level directory containing BAM files; (iii) the path to a directory containing one level of sub-directories which in turn contain BAM files. In the first and second case, a sample name can be supplied with `--sample`. In the last case, the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`. |  |
 | transcriptome_source | string | Select how the transcriptome used for analysis should be prepared. | To analyse only gene fusions and differential expression use of an existing transcriptome may be preferred and so 'precomputed' should be selected. In this case the 'ref_transcriptome' parameter should be specified. To create a reference transcriptome using an existing reference genome, select 'reference guided' and specify the 'ref_genome' parameter. | reference-guided |
 | ref_genome | string | Path to reference genome sequence [.fa/.fq/.fa.gz/fq.gz]. Required for reference-based workflow. | A reference genome is required for reference-based assembly of a transcriptome. |  |
 | ref_transcriptome | string | Transcriptome reference file. Required for precomputed transcriptome calculation and for differential expression analysis. | A reference transcriptome related to the sample under study. Must be supplied when the 'Transcriptome source' parameter has been set to 'precomputed' or to perform differential expression. |  |

main.nf

@@ -9,7 +9,7 @@ import nextflow.util.BlankSeparatedList;
 import java.util.ArrayList;
 nextflow.enable.dsl = 2
 
-include { fastq_ingress } from './lib/ingress'
+include { fastq_ingress; xam_ingress } from './lib/ingress'
 include { reference_assembly } from './subworkflows/reference_assembly'
 include { gene_fusions } from './subworkflows/JAFFAL/gene_fusions'
 include { differential_expression } from './subworkflows/differential_expression'
@@ -737,18 +737,12 @@ workflow {
 
     Pinguscript.ping_start(nextflow, workflow, params)
 
-    fastq = file(params.fastq, type: "file")
-
     error = null
 
     if (params.containsKey("minimap_index_opts")) {
         error = "`--minimap_index_opts` parameter is deprecated. Use parameter `--minimap2_index_opts` instead."
     }
 
-    if (!fastq.exists()) {
-        error = "--fastq: File doesn't exist, check path."
-    }
-
     if (params.transcriptome_source == "precomputed" && !params.ref_transcriptome){
         error = "As transcriptome source parameter is precomputed you must include a ref_transcriptome parameter"
     }
@@ -808,8 +802,10 @@ workflow {
     }
     if (error){
         throw new Exception(error)
-    }else{
+    }
-        reads = samples = fastq_ingress([
+
+    if (params.fastq) {
+        samples = fastq_ingress([
             "input":params.fastq,
             "sample":params.sample,
             "sample_sheet":params.sample_sheet,
@@ -817,13 +813,24 @@ workflow {
             "stats": true,
             "fastcat_extra_args": "",
             "per_read_stats": true])
+    } else {
+        samples = xam_ingress([
+            "input":params.bam,
+            "sample":params.sample,
+            "sample_sheet":params.sample_sheet,
+            "analyse_unclassified":params.analyse_unclassified,
+            "keep_unaligned": true,
+            "return_fastq": true,
+            "stats": true,
+            "per_read_stats": true])
+    }
 
-        pipeline(reads, ref_genome, ref_annotation,
+    pipeline(samples, ref_genome, ref_annotation,
         jaffal_refBase, params.jaffal_genome, params.jaffal_annotation,
         ref_transcriptome, use_ref_ann)
 
     output(pipeline.out.results)
-    }
+
 }
 
 workflow.onComplete {

nextflow.config

@@ -13,6 +13,7 @@
 params {
     help = false
     fastq = null
+    bam = null
     ref_genome = null
     ref_annotation = null
     transcriptome_source = "reference-guided"

nextflow_schema.json

@@ -23,6 +23,12 @@
                     "description": "FASTQ files to use in the analysis.",
                     "help_text": "This accepts one of three cases: (i) the path to a single FASTQ file; (ii) the path to a top-level directory containing FASTQ files; (iii) the path to a directory containing one level of sub-directories which in turn contain FASTQ files. In the first and second case, a sample name can be supplied with `--sample`. In the last case, the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`."
                 },
+                "bam": {
+                    "type": "string",
+                    "format": "path",
+                    "description": "BAM or unaligned BAM (uBAM) files to use in the analysis.",
+                    "help_text": "This accepts one of three cases: (i) the path to a single BAM file; (ii) the path to a top-level directory containing BAM files; (iii) the path to a directory containing one level of sub-directories which in turn contain BAM files. In the first and second case, a sample name can be supplied with `--sample`. In the last case, the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`."
+                },
                 "transcriptome_source": {
                     "type": "string",
                     "enum": [
@@ -74,10 +80,24 @@
             "allOf": [
                 {
                     "required": [
-                        "fastq",
                         "transcriptome_source"
                     ]
-                }]
+                },
+                {
+                    "oneOf": [
+                        {
+                            "required": [
+                                "fastq"
+                            ]
+                        },
+                        {
+                            "required": [
+                                "bam"
+                            ]
+                        }
+                    ]
+                }
+            ]
         },
         "output_options": {
             "title": "Output Options",