Add star solo component

src/star/star_solo/argument_groups_solo.yaml

@@ -0,0 +1,230 @@
+argument_groups:
+- name: STARsolo (single cell RNA-seq) parameters
+  arguments:
+  - name: --soloType
+    type: string
+    description: |-
+      type of single-cell RNA-seq
+
+      - CB_UMI_Simple   ... (a.k.a. Droplet) one UMI and one Cell Barcode of fixed length in read2, e.g. Drop-seq and 10X Chromium.
+      - CB_UMI_Complex  ... multiple Cell Barcodes of varying length, one UMI of fixed length and one adapter sequence of fixed length are allowed in read2 only (e.g. inDrop, ddSeq).
+      - CB_samTagOut    ... output Cell Barcode as CR and/or CB SAm tag. No UMI counting. --readFilesIn cDNA_read1 [cDNA_read2 if paired-end] CellBarcode_read . Requires --outSAMtype BAM Unsorted [and/or SortedByCoordinate]
+      - SmartSeq        ... Smart-seq: each cell in a separate FASTQ (paired- or single-end), barcodes are corresponding read-groups, no UMI sequences, alignments deduplicated according to alignment start and end (after extending soft-clipped bases)
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloCBtype
+    type: string
+    description: |-
+      cell barcode type
+
+      Sequence: cell barcode is a sequence (standard option)
+      String: cell barcode is an arbitrary string
+    example: Sequence
+  - name: --soloCBwhitelist
+    type: string
+    description: |-
+      file(s) with whitelist(s) of cell barcodes. Only --soloType CB_UMI_Complex allows more than one whitelist file.
+
+      - None            ... no whitelist: all cell barcodes are allowed
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloCBstart
+    type: integer
+    description: cell barcode start base
+    example: 1
+  - name: --soloCBlen
+    type: integer
+    description: cell barcode length
+    example: 16
+  - name: --soloUMIstart
+    type: integer
+    description: UMI start base
+    example: 17
+  - name: --soloUMIlen
+    type: integer
+    description: UMI length
+    example: 10
+  - name: --soloBarcodeReadLength
+    type: integer
+    description: |-
+      length of the barcode read
+
+      - 1   ... equal to sum of soloCBlen+soloUMIlen
+      - 0   ... not defined, do not check
+    example: 1
+  - name: --soloBarcodeMate
+    type: integer
+    description: |-
+      identifies which read mate contains the barcode (CB+UMI) sequence
+
+      - 0   ... barcode sequence is on separate read, which should always be the last file in the --readFilesIn listed
+      - 1   ... barcode sequence is a part of mate 1
+      - 2   ... barcode sequence is a part of mate 2
+    example: 0
+  - name: --soloCBposition
+    type: string
+    description: |-
+      position of Cell Barcode(s) on the barcode read.
+
+      Presently only works with --soloType CB_UMI_Complex, and barcodes are assumed to be on Read2.
+      Format for each barcode: startAnchor_startPosition_endAnchor_endPosition
+      start(end)Anchor defines the Anchor Base for the CB: 0: read start; 1: read end; 2: adapter start; 3: adapter end
+      start(end)Position is the 0-based position with of the CB start(end) with respect to the Anchor Base
+      String for different barcodes are separated by space.
+      Example: inDrop (Zilionis et al, Nat. Protocols, 2017):
+      --soloCBposition  0_0_2_-1  3_1_3_8
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloUMIposition
+    type: string
+    description: |-
+      position of the UMI on the barcode read, same as soloCBposition
+
+      Example: inDrop (Zilionis et al, Nat. Protocols, 2017):
+      --soloCBposition  3_9_3_14
+  - name: --soloAdapterSequence
+    type: string
+    description: adapter sequence to anchor barcodes. Only one adapter sequence is
+      allowed.
+  - name: --soloAdapterMismatchesNmax
+    type: integer
+    description: maximum number of mismatches allowed in adapter sequence.
+    example: 1
+  - name: --soloCBmatchWLtype
+    type: string
+    description: |-
+      matching the Cell Barcodes to the WhiteList
+
+      - Exact                           ... only exact matches allowed
+      - 1MM                             ... only one match in whitelist with 1 mismatched base allowed. Allowed CBs have to have at least one read with exact match.
+      - 1MM_multi                       ... multiple matches in whitelist with 1 mismatched base allowed, posterior probability calculation is used choose one of the matches.
+      Allowed CBs have to have at least one read with exact match. This option matches best with CellRanger 2.2.0
+      - 1MM_multi_pseudocounts          ... same as 1MM_Multi, but pseudocounts of 1 are added to all whitelist barcodes.
+      - 1MM_multi_Nbase_pseudocounts    ... same as 1MM_multi_pseudocounts, multimatching to WL is allowed for CBs with N-bases. This option matches best with CellRanger >= 3.0.0
+      - EditDist_2                    ... allow up to edit distance of 3 fpr each of the barcodes. May include one deletion + one insertion. Only works with --soloType CB_UMI_Complex. Matches to multiple passlist barcdoes are not allowed. Similar to ParseBio Split-seq pipeline.
+    example: 1MM_multi
+  - name: --soloInputSAMattrBarcodeSeq
+    type: string
+    description: |-
+      when inputting reads from a SAM file (--readsFileType SAM SE/PE), these SAM attributes mark the barcode sequence (in proper order).
+
+      For instance, for 10X CellRanger or STARsolo BAMs, use --soloInputSAMattrBarcodeSeq CR UR .
+      This parameter is required when running STARsolo with input from SAM.
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloInputSAMattrBarcodeQual
+    type: string
+    description: |-
+      when inputting reads from a SAM file (--readsFileType SAM SE/PE), these SAM attributes mark the barcode qualities (in proper order).
+
+      For instance, for 10X CellRanger or STARsolo BAMs, use --soloInputSAMattrBarcodeQual CY UY .
+      If this parameter is '-' (default), the quality 'H' will be assigned to all bases.
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloStrand
+    type: string
+    description: |-
+      strandedness of the solo libraries:
+
+      - Unstranded  ... no strand information
+      - Forward     ... read strand same as the original RNA molecule
+      - Reverse     ... read strand opposite to the original RNA molecule
+    example: Forward
+  - name: --soloFeatures
+    type: string
+    description: |-
+      genomic features for which the UMI counts per Cell Barcode are collected
+
+      - Gene            ... genes: reads match the gene transcript
+      - SJ              ... splice junctions: reported in SJ.out.tab
+      - GeneFull        ... full gene (pre-mRNA): count all reads overlapping genes' exons and introns
+      - GeneFull_ExonOverIntron ... full gene (pre-mRNA): count all reads overlapping genes' exons and introns: prioritize 100% overlap with exons
+      - GeneFull_Ex50pAS        ... full gene (pre-RNA): count all reads overlapping genes' exons and introns: prioritize >50% overlap with exons. Do not count reads with 100% exonic overlap in the antisense direction.
+    example: Gene
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloMultiMappers
+    type: string
+    description: |-
+      counting method for reads mapping to multiple genes
+
+      - Unique     ... count only reads that map to unique genes
+      - Uniform    ... uniformly distribute multi-genic UMIs to all genes
+      - Rescue     ... distribute UMIs proportionally to unique+uniform counts (~ first iteration of EM)
+      - PropUnique ... distribute UMIs proportionally to unique mappers, if present, and uniformly if not.
+      - EM         ... multi-gene UMIs are distributed using Expectation Maximization algorithm
+    example: Unique
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloUMIdedup
+    type: string
+    description: |-
+      type of UMI deduplication (collapsing) algorithm
+
+      - 1MM_All                     ... all UMIs with 1 mismatch distance to each other are collapsed (i.e. counted once).
+      - 1MM_Directional_UMItools    ... follows the "directional" method from the UMI-tools by Smith, Heger and Sudbery (Genome Research 2017).
+      - 1MM_Directional             ... same as 1MM_Directional_UMItools, but with more stringent criteria for duplicate UMIs
+      - Exact                       ... only exactly matching UMIs are collapsed.
+      - NoDedup                     ... no deduplication of UMIs, count all reads.
+      - 1MM_CR                      ... CellRanger2-4 algorithm for 1MM UMI collapsing.
+    example: 1MM_All
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloUMIfiltering
+    type: string
+    description: |-
+      type of UMI filtering (for reads uniquely mapping to genes)
+
+      - -                  ... basic filtering: remove UMIs with N and homopolymers (similar to CellRanger 2.2.0).
+      - MultiGeneUMI       ... basic + remove lower-count UMIs that map to more than one gene.
+      - MultiGeneUMI_All   ... basic + remove all UMIs that map to more than one gene.
+      - MultiGeneUMI_CR    ... basic + remove lower-count UMIs that map to more than one gene, matching CellRanger > 3.0.0 .
+      Only works with --soloUMIdedup 1MM_CR
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloOutFileNames
+    type: string
+    description: |-
+      file names for STARsolo output:
+
+      file_name_prefix   gene_names   barcode_sequences   cell_feature_count_matrix
+    example:
+    - Solo.out/
+    - features.tsv
+    - barcodes.tsv
+    - matrix.mtx
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloCellFilter
+    type: string
+    description: |-
+      cell filtering type and parameters
+
+      - None            ... do not output filtered cells
+      - TopCells        ... only report top cells by UMI count, followed by the exact number of cells
+      - CellRanger2.2   ... simple filtering of CellRanger 2.2.
+      Can be followed by numbers: number of expected cells, robust maximum percentile for UMI count, maximum to minimum ratio for UMI count
+      The harcoded values are from CellRanger: nExpectedCells=3000;  maxPercentile=0.99;  maxMinRatio=10
+      - EmptyDrops_CR   ... EmptyDrops filtering in CellRanger flavor. Please cite the original EmptyDrops paper: A.T.L Lun et al, Genome Biology, 20, 63 (2019): https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1662-y
+      Can be followed by 10 numeric parameters:  nExpectedCells   maxPercentile   maxMinRatio   indMin   indMax   umiMin   umiMinFracMedian   candMaxN   FDR   simN
+      The harcoded values are from CellRanger:             3000            0.99            10    45000    90000      500               0.01      20000  0.01  10000
+    example:
+    - CellRanger2.2
+    - '3000'
+    - '0.99'
+    - '10'
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloOutFormatFeaturesGeneField3
+    type: string
+    description: field 3 in the Gene features.tsv file. If "-", then no 3rd field
+      is output.
+    example: Gene Expression
+    multiple: yes
+    multiple_sep: ;
+  - name: --soloCellReadStats
+    type: string
+    description: |-
+      Output reads statistics for each CB
+
+      - Standard    ... standard output

src/star/star_solo/config.vsh.yaml

@@ -0,0 +1,115 @@
+name: star_solo
+namespace: star
+description: |
+  Aligns reads to a reference genome using STAR.
+keywords: [align, fasta, genome]
+links:
+  repository: https://github.com/alexdobin/STAR
+  documentation: https://github.com/alexdobin/STAR/blob/master/doc/STARmanual.pdf
+references:
+  doi: 10.1093/bioinformatics/bts635
+license: MIT
+requirements:
+  commands: [ STAR, python, ps, zcat, bzcat ]
+# manually taking care of the main input and output arguments
+argument_groups:
+  - name: Inputs
+    arguments:
+      - type: file
+        name: --input
+        alternatives: --readFilesIn
+        required: true
+        description: The single-end or paired-end R1 FastQ files to be processed.
+        example: [ mysample_S1_L001_R1_001.fastq.gz ]
+        multiple: true
+      - type: file
+        name: --input_r2
+        required: false
+        description: The paired-end R2 FastQ files to be processed. Only required if --input is a paired-end R1 file.
+        example: [ mysample_S1_L001_R2_001.fastq.gz ]
+        multiple: true
+  - name: Outputs
+    arguments:
+      - type: file
+        name: --aligned_reads
+        required: true
+        description: The output file containing the aligned reads.
+        direction: output
+        example: aligned_reads.bam
+      - type: file
+        name: --reads_per_gene
+        required: false
+        description: The output file containing the number of reads per gene.
+        direction: output
+        example: reads_per_gene.tsv
+      - type: file
+        name: --unmapped
+        required: false
+        description: The output file containing the unmapped reads.
+        direction: output
+        example: unmapped.fastq
+      - type: file
+        name: --unmapped_r2
+        required: false
+        description: The output file containing the unmapped R2 reads.
+        direction: output
+        example: unmapped_r2.fastq
+      - type: file
+        name: --chimeric_junctions
+        required: false
+        description: The output file containing the chimeric junctions.
+        direction: output
+        example: chimeric_junctions.tsv
+      - type: file
+        name: --log
+        required: false
+        description: The output file containing the log of the alignment process.
+        direction: output
+        example: log.txt
+      - type: file
+        name: --splice_junctions
+        required: false
+        description: The output file containing the splice junctions.
+        direction: output
+        example: splice_junctions.tsv
+# other arguments are defined in a separate file
+__merge__: [../star_align_reads/argument_groups.yaml, argument_groups_solo.yaml]
+resources:
+  - type: python_script
+    path: script.py
+test_resources:
+  - type: bash_script
+    path: test.sh
+engines:
+  - type: docker
+    image: python:3.12-slim
+    setup:
+      - type: apt
+        packages:
+          - procps
+          - gzip
+          - bzip2
+      # setup derived from https://github.com/alexdobin/STAR/blob/master/extras/docker/Dockerfile
+      - type: docker
+        env: 
+          - STAR_VERSION 2.7.11b
+          - PACKAGES gcc g++ make wget zlib1g-dev unzip xxd
+        run: |
+          apt-get update && \
+            apt-get install -y --no-install-recommends ${PACKAGES} && \
+            cd /tmp && \
+            wget --no-check-certificate https://github.com/alexdobin/STAR/archive/refs/tags/${STAR_VERSION}.zip && \
+            unzip ${STAR_VERSION}.zip && \
+            cd STAR-${STAR_VERSION}/source && \
+            make STARstatic CXXFLAGS_SIMD=-std=c++11 && \
+            cp STAR /usr/local/bin && \
+            cd / && \
+            rm -rf /tmp/STAR-${STAR_VERSION} /tmp/${STAR_VERSION}.zip && \
+            apt-get --purge autoremove -y ${PACKAGES} && \
+            apt-get clean
+      - type: docker
+        run: |
+          STAR --version | sed 's#\(.*\)#star: "\1"#' > /var/software_versions.txt
+runners:
+  - type: executable
+  - type: nextflow