Merge pull request #103 from Plant-Food-Research-Open/feat/sratools

Added sra-tools for RNASeq data download

CHANGELOG.md

@@ -18,6 +18,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 9. Now skipping FastQC by default [#98](https://github.com/Plant-Food-Research-Open/genepal/issues/98)
 10. Added an HTML report [#44](https://github.com/Plant-Food-Research-Open/genepal/issues/44)
 11. Added content type as text/html for the MultiQC and genepal reports
+12. Added sra-tools for RNASeq data download [#102](https://github.com/Plant-Food-Research-Open/genepal/issues/102)
 
 ### `Fixed`
 

README.md

@@ -21,6 +21,7 @@
 - [fasta_validator](https://github.com/linsalrob/fasta_validator): Validate genome FASTA
 - [RepeatModeler](https://github.com/Dfam-consortium/RepeatModeler) or [EDTA](https://github.com/oushujun/EDTA): Create TE library
 - [RepeatMasker](https://github.com/rmhubley/RepeatMasker): Soft mask the genome fasta
+- [sra-tools](https://github.com/ncbi/sra-tools): RNASeq data download from SRA
 - [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc), [fastp](https://github.com/OpenGene/fastp), [SortMeRNA](https://github.com/sortmerna/sortmerna): QC, trim and filter RNASeq evidence
 - [STAR](https://github.com/alexdobin/STAR): RNASeq alignment
   - Directly provided BAM files should be `--outSAMstrandField intronMotif` compliant

assets/schema_rna.json

@@ -14,8 +14,8 @@
             },
             "file_1": {
                 "type": "string",
-                "pattern": "^\\S+\\.(f(ast)?q\\.gz|bam)$",
-                "errorMessage": "FASTQ file for reads 1 or BAM file containing mapped reads must be provided, cannot contain spaces and must have extension '.fq.gz', '.fastq.gz' or '.bam'"
+                "pattern": "^SRR\\w+$|^\\S+\\.(f(ast)?q\\.gz|bam)$",
+                "errorMessage": "SRA ID that begins with SRR or FASTQ file for reads 1 or BAM file containing mapped reads must be provided. Files cannot contain spaces and must have extension '.fq.gz', '.fastq.gz' or '.bam'"
             },
             "file_2": {
                 "errorMessage": "FASTQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'",

docs/output.md

@@ -188,7 +188,7 @@ The final annotation files are saved in GFF3 format validated with [GENOMETOOLS]
 
 </details>
 
-The completeness of the annotations is checked with [BUSCO](https://gitlab.com/ezlab/busco). TO provide a comparative baseline, the completeness of the genomes is also checked. Moreover, the canonical/non-canonical splicing of the introns is also assessed by the pipeline.
+The completeness of the annotations is checked with [BUSCO](https://gitlab.com/ezlab/busco). To provide a comparative baseline, the completeness of the genomes is also checked. Moreover, the canonical/non-canonical splicing of the introns is also assessed by the pipeline.
 
 ### Reports
 

docs/usage.md

@@ -69,7 +69,7 @@ With these two parameters, the pipeline has sufficient inputs to execute the [BR
 RNASeq evidence must be provided through a samplesheet in CSV format which has the following columns,
 
 - `sample:` A sample identifier. The `sample` identifiers have to be the same when you have re-sequenced the same sample more than once e.g. to increase sequencing depth. The pipeline will concatenate the raw reads before performing any downstream analysis.
-- `file_1:` A FASTQ or BAM file
+- `file_1:` A SRA ID for paired-end reads or FASTQ or BAM file
 - `file_2:` A FASTQ file if `file_1` is also a FASTQ file and provides paired samples.
 - `target_assemblies:` A semicolon `;` separated list of assembly tags from the [assemblysheet input](#assemblysheet-input). If `file_1` points to a BAM file, only a single assembly can be listed under `target_assemblies` for that sample. FASTQ data from `file_1` and `file_2` is aligned against each target assembly. BAM data from `file_1` is considered already aligned against the target assembly and is directly fed to BRAKER.
 

main.nf

@@ -36,8 +36,8 @@ workflow PLANTFOODRESEARCHOPEN_GENEPAL {
     ch_braker_annotation
     ch_braker_ex_asm_str
     ch_benchmark_gff
+    ch_rna_sra
     ch_rna_fq
-    ch_rna_bam
     ch_rna_bam_by_assembly
     ch_sortmerna_fastas
     ch_ext_prot_fastas
@@ -58,8 +58,8 @@ workflow PLANTFOODRESEARCHOPEN_GENEPAL {
         ch_braker_annotation,
         ch_braker_ex_asm_str,
         ch_benchmark_gff,
+        ch_rna_sra,
         ch_rna_fq,
-        ch_rna_bam,
         ch_rna_bam_by_assembly,
         ch_sortmerna_fastas,
         ch_ext_prot_fastas,
@@ -105,8 +105,8 @@ workflow {
         PIPELINE_INITIALISATION.out.braker_annotation,
         PIPELINE_INITIALISATION.out.braker_ex_asm_str,
         PIPELINE_INITIALISATION.out.benchmark_gff,
+        PIPELINE_INITIALISATION.out.rna_sra,
         PIPELINE_INITIALISATION.out.rna_fq,
-        PIPELINE_INITIALISATION.out.rna_bam,
         PIPELINE_INITIALISATION.out.rna_bam_by_assembly,
         PIPELINE_INITIALISATION.out.sortmerna_fastas,
         PIPELINE_INITIALISATION.out.ext_prot_fastas,

modules.json

@@ -150,6 +150,11 @@
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     },
+                    "custom/sratoolsncbisettings": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["fastq_download_prefetch_fasterqdump_sratools"]
+                    },
                     "diamond/makedb": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
@@ -235,6 +240,16 @@
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     },
+                    "sratools/fasterqdump": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["fastq_download_prefetch_fasterqdump_sratools"]
+                    },
+                    "sratools/prefetch": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["fastq_download_prefetch_fasterqdump_sratools"]
+                    },
                     "star/align": {
                         "branch": "master",
                         "git_sha": "3aa0aec1d52d492fe241919f0c6100ebf0074082",
@@ -264,6 +279,11 @@
             },
             "subworkflows": {
                 "nf-core": {
+                    "fastq_download_prefetch_fasterqdump_sratools": {
+                        "branch": "master",
+                        "git_sha": "1fc29f92e439d5631fdf34b8ac4687297d70f5ec",
+                        "installed_by": ["subworkflows"]
+                    },
                     "fastq_fastqc_umitools_fastp": {
                         "branch": "master",
                         "git_sha": "4026bab16a91b1b0b18d80ff465819ca725f33fd",