luslab-umitools | Added single-cell RNA-seq options and grouping option

tools/umi_tools/dedup/main.nf

@@ -68,7 +68,81 @@ OUTPUT STATS OPTION -> --output-stats=[PREFIX]
 params.internal_output_stats = ''
 //Activate this option to use sample_id as the prefix -> e.g. sample1_edit_distance
 params.internal_output_stats_sampleid = true
+
+/*-----------------------------------------------------------------------------------------------------------------------------
+GROUPING METHOD OPTION -> --method=[method]
+-------------------------------------------------------------------------------------------------------------------------------*/
+//What method to use to identify group of reads with the same (or similar) UMI(s)
+//Default method is directional
+//Choose a grouping method: unique, percentile, cluster or adjacency
+
+//Reads group share the exact same UMI
+params.internal_grouping_unique = false
+
+//Reads group share the exact same UMI. UMIs with counts < 1% of the median counts for UMIs at the same position are ignored.
+params.internal_grouping_percentile = false
+
+//Identify clusters of connected UMIs (based on hamming distance threshold). Each network is a read group
+params.internal_grouping_cluster = false
+
+//Cluster UMIs as above. For each cluster, select the node (UMI) with the highest counts.
+params.internal_grouping_adjacency = false
+
 /*-----------------------------------------------------------------------------------------------------------------------------*/
+//Additional grouping method options
+
+//--edit-threshold-distance
+//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).
+params.internal_edit_threshold_distance = ''
+
+//--spliced-is-unique
+//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.
+params.internal_unique_spliced = false
+
+//--soft-clip-threshold
+//By setting this option, you can treat reads with at least this many bases soft-clipped at the 3’ end as spliced. Default=4
+params.internal_soft_clip_threshold = ''
+
+//--read-length
+//Use the read length as a criteria when deduping, for e.g sRNA-Seq.
+params.internal_read_length = true
+
+/*-----------------------------------------------------------------------------------------------------------------------------
+SINGLE-CELL RNA-SEQ OPTIONS 
+-------------------------------------------------------------------------------------------------------------------------------*/
+//--per-gene
+//Reads will be grouped together if they have the same gene.
+//MUST SUPPLY --per-contig OR --gene-tag
+params.internal_per_gene = false
+
+//--gene-tag
+//Deduplicate per gene. The gene information is encoded in the bam read tag specified
+// USE WITH --per-gene
+params.internal_gene_tag = false
+
+//--assigned-status-tag
+//BAM tag which describes whether a read is assigned to a gene. Defaults to the same value as given for --gene-tag
+params.internal_assign_status_tag = ''
+
+//--skip-tags-regex
+//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”:
+params.internal_skip_tags_regex = ''
+
+//--per-contig
+//Deduplicate per contig (field 3 in BAM; RNAME). All reads with the same contig will be considered to have the same alignment position. 
+params.internal_per_contig = false
+
+//--gene-transcript-map
+//File mapping genes to transcripts (tab separated)
+params.internal_gene_transcript_map = false
+
+//--per-cell
+//Reads will only be grouped together if they have the same cell barcode. Can be combined with --per-gene.
+params.internal_per_cell = false
+
+/*-----------------------------------------------------------------------------------------------------------------------------*/
+
 
 // dedup reusable component
 process dedup {
@@ -104,7 +178,6 @@ process dedup {
       }
     }
 
-
     //Output/ stdout option 
     if (params.internal_output_sampleid){
       dedup_post_args += "-S ${sample_id}.dedup.bam "
@@ -114,8 +187,58 @@ process dedup {
       }
     }
 
+    //Grouping method option 
+    if (params.internal_grouping_unique){
+      dedup_post_args += "--method=unique "
+    }
+    if (params.internal_grouping_percentile){
+      dedup_post_args += "--method=percentile "
+    }
+    if (params.internal_grouping_cluster){
+      dedup_post_args += "--method=cluster "
+    }
+    if (params.internal_grouping_adjacency){
+      dedup_post_args += "--method=adjacency "
+    }
 
-     // Displays the umi_tools command line to check for mistakes
+    //Additional grouping method options 
+    if (params.internal_edit_threshold_distance != ''){
+      dedup_post_args += "--edit-threshold-distance=$params.internal_edit_threshold_distance "
+    }
+    if (params.internal_unique_spliced){
+      dedup_post_args += "--spliced-is-unique "
+    }
+    if (params.internal_soft_clip_threshold != ''){
+      dedup_post_args += "--soft-clip-threshold=$params.internal_soft_clip_threshold "
+    }
+    if (params.internal_read_length){
+      dedup_post_args += "--read-length "
+    }
+
+    //Single-cell RNA-seq options
+    if (params.internal_per_gene){
+      dedup_post_args += "--per-gene "
+    }
+    if (params.internal_gene_tag){
+      dedup_post_args += "--gene-tag "
+    }
+    if (params.internal_assigned_status_tag != ''){
+      dedup_post_args += "--assigned-status-tag=$params.internal_assigned_status_tag "
+    }
+    if (params.internal_skip_tags_regex != ''){
+      dedup_post_args += "--skip-tags-regex=$params.internal_skip_tags_regex "
+    }
+    if (params.internal_per_contig){
+      dedup_post_args += "--per-contig "
+    }
+    if (params.internal_gene_transcript_map){
+      dedup_post_args += "--gene-transcript-map "
+    }
+    if (params.internal_per_cell){
+      dedup_post_args += "--per-cell "
+    }
+
+    // Displays the umi_tools command line to check for mistakes
     println dedup_pre_args
     println dedup_post_args