Umi tools dedup

CHANGELOG.md

@@ -60,6 +60,9 @@
 
 * `falco`: A C++ drop-in replacement of FastQC to assess the quality of sequence read data (PR #43).
 
+* `umitools`:
+    - `umitools_dedup`: Deduplicate reads based on the mapping co-ordinate and the UMI attached to the read (PR #54).
+
 * `bedtools`:
     - `bedtools_getfasta`: extract sequences from a FASTA file for each of the
                            intervals defined in a BED/GFF/VCF file (PR #59).

src/umi_tools/umi_tools_dedup/config.vsh.yaml

@@ -0,0 +1,320 @@
+name: umi_tools_dedup
+namespace: umi_tools
+description: |
+  Deduplicate reads based on the mapping co-ordinate and the UMI attached to the read.
+keywords: [umi_tools, deduplication, dedup]
+links:
+  homepage: https://umi-tools.readthedocs.io/en/latest/
+  documentation: https://umi-tools.readthedocs.io/en/latest/reference/dedup.html
+  repository: https://github.com/CGATOxford/UMI-tools
+references: 
+  doi: 10.1101/gr.209601.116
+license: MIT
+
+argument_groups:
+  - name: Inputs
+    arguments:
+      - name: --input
+        alternatives: --stdin
+        type: file
+        description: Input BAM or SAM file. Use --in_sam to specify SAM format.
+        required: true
+      - name: --in_sam
+        type: boolean_true
+        description: |
+          By default, inputs are assumed to be in BAM format. Use this options 
+          to specify the use of SAM format for input.
+      - name: --bai
+        type: file
+        description: BAM index
+      - name: --random_seed
+        type: integer
+        description: |
+          Random seed to initialize number generator with.
+
+  - name: Outputs
+    arguments:
+      - name: --output
+        alternatives: --stdout
+        type: file
+        description: Deduplicated BAM file
+        required: true
+        direction: output
+      - name: --out_sam
+        type: boolean_true
+        description: |
+          By default, outputa are written in BAM format. Use this options to 
+          specify the use of SAM format for output.
+      - name: --paired
+        type: boolean_true
+        description: |
+          BAM is paired end - output both read pairs. This will also force the
+          use of the template length to determine reads with the same mapping
+          coordinates.
+      - name: --output_stats
+        type: string
+        description: |
+          Generate files containing UMI based deduplication statistics files with this prefix
+          in the file names.
+      - name: --extract_umi_method
+        type: string
+        choices: [read_id, tag, umis]
+        description: |
+          Specify the method by which the barcodes were encoded in the read.
+          The options are:
+            * read_id (default) 
+            * tag
+            * umis
+        example: "read_id"
+      - name: --umi_tag
+        type: string
+        description: |
+          The tag containing the UMI sequence. 
+          This is only required if the extract_umi_method is set to tag.
+      - name: --umi_separator
+        type: string
+        description: |
+          The separator used to separate the UMI from the read sequence. 
+          This is only required if the extract_umi_method is set to id_read. [_]
+        example: '_'
+      - name: --umi_tag_split
+        type: string
+        description: |
+          Separate the UMI in tag by <SPLIT> and take the first element.
+      - name: --umi_tag_delimiter
+        type: string
+        description: |
+          Separate the UMI in by <DELIMITER> and concatenate the elements
+      - name: --cell_tag
+        type: string
+        description: |
+          The tag containing the cell barcode sequence. 
+          This is only required if the extract_umi_method is set to tag.
+      - name: --cell_tag_split
+        type: string
+        description: |
+          Separate the cell barcode in tag by <SPLIT> and take the first element.
+      - name: --cell_tag_delimiter
+        type: string
+        description: |
+          Separate the cell barcode in by <DELIMITER> and concatenate the elements
+
+  - name: Grouping Options
+    arguments:    
+      - name: --method
+        type: string
+        choices: [unique, percentile, cluster, adjacency, directional]
+        description: |
+          The method to use for grouping reads. 
+          The options are: 
+            * unique
+            * percentile
+            * cluster
+            * adjacency
+            * directional (default)
+        example: "directional"
+      - name: --edit_distance_threshold
+        type: integer
+        description: |
+          For the adjacency and cluster methods the threshold for the edit 
+          distance to connect two UMIs in the network can be increased. The 
+          default value of 1 works best unless the UMI is very long (>14bp). [1]
+        example: 1
+      - name: --spliced_is_unique
+        type: boolean_true
+        description: |
+          Causes two reads that start in the same position on the same strand
+          and having the same UMI to be considered unique if one is spliced 
+          and the other is not. (Uses the 'N' cigar operation to test for splicing).
+      - name: --soft_clip_threshold
+        type: integer
+        description: |
+          Mappers that soft clip will sometimes do so rather than mapping a
+          spliced read if there is only a small overhang over the exon junction.
+          By setting this option, you can treat reads with at least this many
+          bases soft-clipped at the 3' end as spliced. [4]
+        example: 4
+      - name: --multimapping_detection_method
+        type: string
+        description: |
+          If the sam/bam contains tags to identify multimapping reads, you can
+          specify for use when selecting the best read at a given loci. Supported
+          tags are "NH", "X0" and "XT". If not specified, the read with the highest
+          mapping quality will be selected.
+      - name: --read_length
+        type: boolean_true
+        description: |
+          Use the read length as a criteria when deduping, for e.g sRNA-Seq.
+
+  - name: Single-cell RNA-Seq Options
+    arguments:
+      - name: --per_gene
+        type: boolean_true
+        description: |
+          Reads will be grouped together if they have the same gene. This is useful
+          if your library prep generates PCR duplicates with non identical alignment
+          positions such as CEL-Seq. Note this option is hardcoded to be on with the
+          count command. I.e counting is always performed per-gene. Must be combined
+          with either --gene_tag or --per_contig option.
+      - name: --gene_tag
+        type: string
+        description: |
+          Deduplicate per gene. The gene information is encoded in the bam read tag
+          specified.
+      - name: --assigned_status_tag
+        type: string
+        description: |
+          BAM tag which describes whether a read is assigned to a gene. Defaults to
+          the same value as given for --gene_tag.
+      - name: --skip_tags_regex
+        type: string
+        description: |
+          Use in conjunction with the --assigned_status_tag option to skip any reads
+          where the tag matches this regex. Default ("^[__|Unassigned]") matches
+          anything which starts with "__" or "Unassigned".
+      - name: --per_contig
+        type: boolean_true
+        description: |
+          Deduplicate per contig (field 3 in BAM; RNAME). All reads with the same
+          contig will be considered to have the same alignment position. This is
+          useful if you have aligned to a reference transcriptome with one
+          transcript per gene. If you have aligned to a transcriptome with more
+          than one transcript per gene, you can supply a map between transcripts
+          and gene using the --gene_transcript_map option.
+      - name: --gene_transcript_map
+        type: file
+        description: |
+          A file containing a mapping between gene names and transcript names.
+          The file should be tab separated with the gene name in the first column
+          and the transcript name in the second column.
+      - name: --per_cell
+        type: boolean_true
+        description: |
+          Reads will only be grouped together if they have the same cell barcode.
+          Can be combined with --per_gene.
+
+  - name: SAM/BAM Options
+    arguments:
+      - name: --mapping_quality
+        type: integer
+        description: |
+          Minimium mapping quality (MAPQ) for a read to be retained. [0]
+        example: 0
+      - name: --unmapped_reads
+        type: string
+        description: |
+          How unmapped reads should be handled. 
+          The options are:
+            * "discard": Discard all unmapped reads. (default)
+            * "use":     If read2 is unmapped, deduplicate using read1 only. Requires --paired.
+            * "output":  Output unmapped reads/read pairs without UMI grouping/deduplication. Only available in umi_tools group.
+        example: "discard"
+      - name: --chimeric_pairs
+        type: string
+        choices: [discard, use, output]
+        description: |
+          How chimeric pairs should be handled. 
+          The options are:
+            * "discard": Discard all chimeric read pairs.
+            * "use":     Deduplicate using read1 only. (default)
+            * "output":  Output chimeric pairs without UMI grouping/deduplication. Only available in umi_tools group.
+        example: "use"
+      - name: --unpaired_reads
+        type: string
+        choices: [discard, use, output]
+        description: |
+          How unpaired reads should be handled. 
+          The options are: 
+            * "discard": Discard all unmapped reads.
+            * "use": If read2 is unmapped, deduplicate using read1 only. Requires --paired. (default)
+            * "output":  Output unmapped reads/read pairs without UMI grouping/deduplication. Only available in umi_tools group.
+        example: "use"
+      - name: --ignore_umi
+        type: boolean_true
+        description: |
+          Ignore the UMI and group reads using mapping coordinates only.
+      - name: --subset
+        type: double
+        description: |
+          Only consider a fraction of the reads, chosen at random. This is useful
+          for doing saturation analyses.
+      - name: --chrom
+        type: string
+        description: |
+          Only consider a single chromosome. This is useful for debugging/testing 
+          purposes.
+
+  - name: Group/Dedup Options
+    arguments:
+      - name: --no_sort_output
+        type: boolean_true
+        description: |
+          By default, output is sorted. This involves the use of a temporary unsorted
+          file (saved in --temp_dir). Use this option to turn off sorting.
+      - name: --buffer_whole_contig
+        type: boolean_true
+        description: |
+          Forces dedup to parse an entire contig before yielding any reads for
+          deduplication. This is the only way to absolutely guarantee that all reads
+          with the same start position are grouped together for deduplication since
+          dedup uses the start position of the read, not the alignment coordinate on
+          which the reads are sorted. However, by default, dedup reads for another
+          1000bp before outputting read groups which will avoid any reads being missed
+          with short read sequencing (<1000bp).
+
+  - name: Common UMI-tools Options
+    arguments:
+      - name: --log
+        alternatives: -L
+        type: file
+        description: File with logging information.
+      - name: --log2stderr
+        type: boolean_true
+        description: Send logging information to stderr.
+      - name: --verbose
+        alternatives: -v
+        type: integer
+        description: Log level. The higher, the more output. [0]
+        example: 0
+      - name: --error
+        alternatives: -E
+        type: file
+        description: File with error information.
+      - name: --temp_dir
+        type: string
+        description: |
+          Directory for temporary files. If not set, the bash environmental variable TMPDIR is used.
+      - name: --compresslevel
+        type: integer
+        description: |
+          Level of Gzip compression to use. Default=6 matches GNU gzip rather than python gzip default. [6]
+        example: 6
+      - name: --timeit
+        type: file
+        description: Store timing information in file.
+      - name: --timeit_name
+        type: string
+        description: Name in timing file for this class of jobs. [all]
+        example: "all"
+      - name: --timeit_header
+        type: string
+        description: Add header for timing information.
+
+resources:
+  - type: bash_script
+    path: script.sh
+test_resources:
+  - type: bash_script
+    path: test.sh
+  - type: file
+    path: test_data
+engines:
+  - type: docker
+    image: quay.io/biocontainers/umi_tools:1.1.5--py39hf95cd2a_1
+    setup:
+      - type: docker
+        run: |
+            umi_tools -v | sed 's/ version//g' > /var/software_versions.txt
+runners:
+- type: executable
+- type: nextflow