Merge pull request #42 from nf-core/readd_quantification

Add alignment based quantification with Salmon
nf-core · Apr 8, 2024 · fda4028 · fda4028
2 parents 9f2403f + 5560996
commit fda4028
Show file tree

Hide file tree

Showing 39 changed files with 3,475 additions and 11 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -17,7 +17,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[#35](https://github.com/nf-core/riboseq/pull/35) - Sortmerna: index once ([@pinin4fjords](https://github.com/pinin4fjords), review by [@maxulysse](https://github.com/maxulysse))
 - [[#36](https://github.com/nf-core/riboseq/pull/36) - Bump bbsplit module to prevent index overwrites ([@pinin4fjords](https://github.com/pinin4fjords), review by [@maxulysse](https://github.com/maxulysse))
 - [#38](https://github.com/nf-core/riboseq/pull/38) - Important! Template update for nf-core/tools v2.13.1 ([@nf-core-bot](https://github.com/nf-core-bot), [@pinin4fjords](https://github.com/pinin4fjords))
-- [#40](https://github.com/nf-core/riboseq/pull/40) - Ribotricer orf prediction ([@pinin4fjords](https://github.com/pinin4fjords), review by )
+- [#40](https://github.com/nf-core/riboseq/pull/40) - Ribotricer orf prediction ([@pinin4fjords](https://github.com/pinin4fjords), review by [@maxulysse](https://github.com/maxulysse))
+- [#42](https://github.com/nf-core/riboseq/pull/42) - Add alignment based quantification with Salmon ([@pinin4fjords](https://github.com/pinin4fjords), review by [@maxulysse](https://github.com/maxulysse))
 
 Initial release of nf-core/riboseq, created with the [nf-core](https://nf-co.re/) template.
 

diff --git a/conf/modules.config b/conf/modules.config
@@ -623,36 +623,48 @@ if (!params.skip_alignment && params.aligner == 'star') {
         withName: '.*:QUANTIFY_STAR_SALMON:SALMON_QUANT' {
             ext.args   = { params.extra_salmon_quant_args ?: '' }
             publishDir = [
-                path: { "${params.outdir}/${params.aligner}" },
+                path: { "${params.outdir}/quantification/salmon" },
                 mode: params.publish_dir_mode,
                 saveAs: { filename -> filename.equals('versions.yml') || filename.endsWith('_meta_info.json') ? null : filename }
             ]
         }
 
-        withName: '.*:QUANTIFY_STAR_SALMON:TX2GENE' {
+        withName: '.*:QUANTIFY_STAR_SALMON:CUSTOM_TX2GENE' {
             publishDir = [
-                path: { "${params.outdir}/${params.aligner}" },
+                path: { "${params.outdir}/quantification" },
                 mode: params.publish_dir_mode,
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ]
         }
 
-        withName: '.*:QUANTIFY_STAR_SALMON:TXIMPORT' {
+        withName: '.*:QUANTIFY_STAR_SALMON:TXIMETA_TXIMPORT' {
             ext.prefix = { "${quant_type}.merged" }
             publishDir = [
-                path: { "${params.outdir}/${params.aligner}" },
+                path: { "${params.outdir}/quantification/salmon" },
                 mode: params.publish_dir_mode,
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ]
         }
 
         withName: '.*:QUANTIFY_STAR_SALMON:SE_.*' {
             publishDir = [
-                path: { "${params.outdir}/${params.aligner}" },
+                path: { "${params.outdir}/quantification/salmon" },
                 mode: params.publish_dir_mode,
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ]
         }
+        withName: '.*:QUANTIFY_STAR_SALMON:SE_GENE' {
+            ext.prefix = { "salmon.merged.gene" }
+        }
+        withName: '.*:QUANTIFY_STAR_SALMON:SE_GENE_LENGTH_SCALED' {
+            ext.prefix = { "salmon.merged.gene.length_scaled" }
+        }
+        withName: '.*:QUANTIFY_STAR_SALMON:SE_GENE_SCALED' {
+            ext.prefix = { "salmon.merged.gene.scaled" }
+        }
+        withName: '.*:QUANTIFY_STAR_SALMON:SE_TRANSCRIPT' {
+            ext.prefix = { "salmon.merged.transcript" }
+        }
     }
 
     if (params.with_umi) {

diff --git a/docs/output.md b/docs/output.md
@@ -280,6 +280,43 @@ Read distribution metrics around annotated protein coding regions or based on al
   - `*_psite_offsets.txt`: If the P-site offsets are not provided, txt file containing the derived relative offsets.
   </details>
 
+## Quantification
+
+Quantification is done by passing transcriptome-level alignment BAM files to Salmon, producing the following outputs:
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `quantification/`
+  - `tx2gene.tsv`: Tab-delimited file containing gene to transcripts ids mappings.
+- `quantification/salmon/`
+  - salmon.merged.gene_counts.tsv`: Matrix of gene-level raw counts across all samples.
+  - salmon.merged.gene_tpm.tsv`: Matrix of gene-level TPM values across all samples.
+  - salmon.merged.gene.rds`: RDS object that can be loaded in R that contains a [SummarizedExperiment](https://bioconductor.org/packages/release/bioc/html/SummarizedExperiment.html) container with the TPM (`abundance`), estimated counts (`counts`) and transcript length (`length`) in the assays slot for genes.
+  - salmon.merged.gene_counts_scaled.tsv`: Matrix of gene-level library size-scaled counts across all samples.
+  - salmon.merged.gene\_\_scaled.rds`: RDS object that can be loaded in R that contains a [SummarizedExperiment](https://bioconductor.org/packages/release/bioc/html/SummarizedExperiment.html) container with the TPM (`abundance`), estimated library size-scaled counts (`counts`) and transcript length (`length`) in the assays slot for genes.
+  - salmon.merged.gene_counts_length_scaled.tsv`: Matrix of gene-level length-scaled counts across all samples.
+  - salmon.merged.gene_length_scaled.rds`: RDS object that can be loaded in R that contains a [SummarizedExperiment](https://bioconductor.org/packages/release/bioc/html/SummarizedExperiment.html) container with the TPM (`abundance`), estimated length-scaled counts (`counts`) and transcript length (`length`) in the assays slot for genes.
+  - salmon.merged.transcript_counts.tsv`: Matrix of isoform-level raw counts across all samples.
+  - salmon.merged.transcript_tpm.tsv`: Matrix of isoform-level TPM values across all samples.
+  - salmon.merged.transcript.rds`: RDS object that can be loaded in R that contains a [SummarizedExperiment](https://bioconductor.org/packages/release/bioc/html/SummarizedExperiment.html) container with the TPM (`abundance`), estimated isoform-level raw counts (`counts`) and transcript length (`length`) in the assays slot for transcripts.
+  </details>
+
+Raw outputs from Salmon are available for each sample:
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `quantification/salmon/<SAMPLE>/`
+  - `aux_info/`: Auxiliary info e.g. versions and number of mapped reads.
+  - `cmd_info.json`: Information about the Salmon quantification command, version and options.
+  - `lib_format_counts.json`: Number of fragments assigned, unassigned and incompatible.
+  - `libParams/`: Contains the file `flenDist.txt` for the fragment length distribution.
+  - `logs/`: Contains the file `salmon_quant.log` giving a record of Salmon's quantification.
+  - `quant.genes.sf`: Salmon _gene_-level quantification of the sample, including feature length, effective length, TPM, and number of reads.
+  - `quant.sf`: Salmon _transcript_-level quantification of the sample, including feature length, effective length, TPM, and number of reads.
+  </details>
+
 ### MultiQC
 
 <details markdown="1">

diff --git a/modules.json b/modules.json
@@ -25,6 +25,11 @@
                         "git_sha": "1b0ffa4e5aed5b7e3cd4311af31bd3b2c8345051",
                         "installed_by": ["modules"]
                     },
+                    "custom/tx2gene": {
+                        "branch": "master",
+                        "git_sha": "ec155021a9104441bf6a9bae3b55d1b5b0bfdb3a",
+                        "installed_by": ["quantify_pseudo_alignment"]
+                    },
                     "cutadapt": {
                         "branch": "master",
                         "git_sha": "6618151ed69274863dc6fe6d2920afa90abaca1f",
@@ -70,6 +75,11 @@
                         "git_sha": "de5811dd9ca15af1e131806001bcaae909e42021",
                         "installed_by": ["modules"]
                     },
+                    "kallisto/quant": {
+                        "branch": "master",
+                        "git_sha": "de5811dd9ca15af1e131806001bcaae909e42021",
+                        "installed_by": ["quantify_pseudo_alignment"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",
@@ -108,7 +118,7 @@
                     "salmon/quant": {
                         "branch": "master",
                         "git_sha": "03a8562231d575c313266c193a980594b941e3ea",
-                        "installed_by": ["fastq_subsample_fq_salmon"]
+                        "installed_by": ["fastq_subsample_fq_salmon", "quantify_pseudo_alignment"]
                     },
                     "samtools/flagstat": {
                         "branch": "master",
@@ -150,11 +160,21 @@
                         "git_sha": "a21faa6a3481af92a343a10926f59c189a2c16c9",
                         "installed_by": ["modules"]
                     },
+                    "summarizedexperiment/summarizedexperiment": {
+                        "branch": "master",
+                        "git_sha": "31751460f9ce9552846e13fdeec6953dcb47132d",
+                        "installed_by": ["quantify_pseudo_alignment"]
+                    },
                     "trimgalore": {
                         "branch": "master",
                         "git_sha": "d2c5e76f291379f3dd403e48e46ed7e6ba5da744",
                         "installed_by": ["fastq_fastqc_umitools_trimgalore"]
                     },
+                    "tximeta/tximport": {
+                        "branch": "master",
+                        "git_sha": "c275c3baac6df8f0c7c500760a0cf014ce7b525d",
+                        "installed_by": ["quantify_pseudo_alignment"]
+                    },
                     "umitools/dedup": {
                         "branch": "master",
                         "git_sha": "3bd4f34e3093c2a16e6a8eefc22242b9b94641db",
@@ -219,6 +239,11 @@
                         "git_sha": "8aa7040ca55a511ee4bc079803a8446db00f34c8",
                         "installed_by": ["subworkflows"]
                     },
+                    "quantify_pseudo_alignment": {
+                        "branch": "master",
+                        "git_sha": "bca4985339b3ba879f457565806deb2377873b83",
+                        "installed_by": ["subworkflows"]
+                    },
                     "utils_nextflow_pipeline": {
                         "branch": "master",
                         "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa",

diff --git a/modules/nf-core/custom/tx2gene/environment.yml b/modules/nf-core/custom/tx2gene/environment.yml
diff --git a/modules/nf-core/custom/tx2gene/main.nf b/modules/nf-core/custom/tx2gene/main.nf
diff --git a/modules/nf-core/custom/tx2gene/meta.yml b/modules/nf-core/custom/tx2gene/meta.yml