Simplify rose

conf/igenomes.config

@@ -24,7 +24,6 @@ params {
             macs_gsize  = "2.7e9"
             blacklist   = "${projectDir}/assets/blacklists/GRCh37-blacklist.bed"
             pwms        = "${projectDir}/assets/PWMs/Jaspar_Hocomoco_Kellis_human_PSEMs.txt"
-            rose_ucsc   = "https://raw.githubusercontent.com/stjude/ROSE/master/annotation/hg19_refseq.ucsc"
         }
         'GRCh38' {
             fasta       = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa"
@@ -38,7 +37,6 @@ params {
             macs_gsize  = "2.7e9"
             blacklist   = "${projectDir}/assets/blacklists/hg38-blacklist.bed"
             pwms        = "${projectDir}/assets/PWMs/Jaspar_Hocomoco_Kellis_human_PSEMs.txt"
-            rose_ucsc   = "https://raw.githubusercontent.com/stjude/ROSE/master/annotation/hg38_refseq.ucsc"
         }
         'CHM13' {
             fasta       = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa"
@@ -61,7 +59,6 @@ params {
             macs_gsize  = "1.87e9"
             blacklist   = "${projectDir}/assets/blacklists/GRCm38-blacklist.bed"
             pwms        = "${projectDir}/assets/PWMs/Jaspar_Hocomoco_Kellis_mouse_PSEMs.txt"
-            rose_ucsc   = "https://raw.githubusercontent.com/stjude/ROSE/master/annotation/mm10_refseq.ucsc"
         }
         'TAIR10' {
             fasta       = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa"
@@ -297,7 +294,6 @@ params {
             macs_gsize  = "2.7e9"
             blacklist   = "${projectDir}/assets/blacklists/hg38-blacklist.bed"
             pwms        = "${projectDir}/assets/PWMs/Jaspar_Hocomoco_Kellis_human_PSEMs.txt"
-            rose_ucsc   = "https://raw.githubusercontent.com/stjude/ROSE/master/annotation/hg38_refseq.ucsc"
         }
         'hg19' {
             fasta       = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa"
@@ -312,7 +308,6 @@ params {
             macs_gsize  = "2.7e9"
             blacklist   = "${projectDir}/assets/blacklists/hg19-blacklist.bed"
             pwms        = "${projectDir}/assets/PWMs/Jaspar_Hocomoco_Kellis_human_PSEMs.txt"
-            rose_ucsc   = "https://raw.githubusercontent.com/stjude/ROSE/master/annotation/hg19_refseq.ucsc"
         }
         'mm10' {
             fasta       = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa"
@@ -327,7 +322,6 @@ params {
             macs_gsize  = "1.87e9"
             blacklist   = "${projectDir}/assets/blacklists/mm10-blacklist.bed"
             pwms        = "${projectDir}/assets/PWMs/Jaspar_Hocomoco_Kellis_mouse_PSEMs.txt"
-            rose_ucsc   = "https://raw.githubusercontent.com/stjude/ROSE/master/annotation/mm10_refseq.ucsc"
         }
         'bosTau8' {
             fasta       = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/WholeGenomeFasta/genome.fa"

conf/modules.config

@@ -23,7 +23,7 @@ process {
     }
 
     withName: CLEAN_BED {
-        ext.args = {"'{print \$1 \"\\t\" \$2 \"\\t\" \$3}'"}
+        ext.args = {"'{print \$1 \"\\t\" \$2 \"\\t\" \$3 \"\\t\" \$4 \"\\t\" \$5 \"\\t\" \$6}'"}
         ext.prefix = {"${meta.id}.clean"}
         ext.suffix = "bed"
     }
@@ -62,22 +62,8 @@ process {
         ext.prefix = {"${meta.id}_control"}
     }
 
-    withName: BED_TO_GFF {
-        ext.args = {"'BEGIN{FS=\"\\t\";OFS=\"\\t\"} { print \$1, \"bed2gff\", \"region\", \$2+1, \$3, \".\", \".\", \".\", \".\"}'"}
-        ext.prefix = {"$meta.id"}
-        ext.suffix = "gff"
-    }
-
-    withName: REFORMAT_GFF {
-        ext.args = {"'BEGIN{FS=\"\\t\";OFS=\"\\t\"} {if(!match(\$1, /^chr/)) \$1=\"chr\"\$1; \$2=\"seq_\"NR; print \$1, \$2, \"\", \$4, \$5, \"\", \$7, \"\", \$2}'"}
-        ext.prefix = {"${meta.id}_reformatted"}
-        ext.suffix = "gff"
-    }
-
-    withName: ROSE_OUTPUT_TO_BED {
-        ext.args = {"'BEGIN{FS=\"\\t\";OFS=\"\\t\"} {print \$1, \$4-1, \$5}'"}
-        ext.prefix = {"$meta.id"}
-        ext.suffix = "bed"
+    withName: UCSC_GTFTOGENEPRED {
+        ext.args = "-genePredExt"
     }
 
     withName: ".*DYNAMITE:FILTER" {

main.nf

@@ -34,7 +34,6 @@ params.fasta     = getGenomeAttribute('fasta')
 params.gtf       = getGenomeAttribute('gtf')
 params.blacklist = getGenomeAttribute('blacklist')
 params.pwms      = getGenomeAttribute('pwms')
-params.rose_ucsc = getGenomeAttribute('rose_ucsc')
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -94,7 +93,6 @@ workflow NFCORE_TFACTIVITY {
         params.chromhmm_states,
         params.chromhmm_threshold,
         params.chromhmm_marks.split(','),
-        params.rose_ucsc,
         params.window_size,
         params.decay,
         params.merge_samples,

modules.json

@@ -59,6 +59,11 @@
                         "branch": "master",
                         "git_sha": "f4596fe0bdc096cf53ec4497e83defdb3a94ff62",
                         "installed_by": ["modules"]
+                    },
+                    "ucsc/gtftogenepred": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["modules"]
                     }
                 }
             },

modules/local/chromhmm/get_results/templates/get_results.py

@@ -10,20 +10,23 @@
 emissions = pd.read_csv("$emissions", sep = "\\t")[["State (Emission order)"] + marks].rename(columns={"State (Emission order)": "State"})
 
 
-# Read input bed file and remove unecessary columns
+# Read input bed file
 bed = pd.read_csv("$bed",
                   sep="\\t",
                   skiprows=1,
                   names=["chr", "start", "end", "state", "score", "strand", "start_1", "end_1", "rgb"]
-                 ).drop(columns=["strand", "score", "start_1", "end_1", "rgb"])
+                 )
 
 
 # Keep state if any of the marks is enriched > threshold for this state
-states = emissions[np.any([emissions[mark] >= $threshold for mark in marks], axis=0)]["State"].tolist()
+states = emissions[np.any([emissions[mark] >= float("$threshold") for mark in marks], axis=0)]["State"].tolist()
 
 
 # Subset bed file for selected states
-out_bed = bed[np.isin(bed["state"], states)].drop(columns=["state"])
+bed = bed[np.isin(bed["state"], states)].drop(columns=["state"])
+bed["name"] = bed["chr"] + ":" + bed["start"].astype(str) + "-" + bed["end"].astype(str)
+
+bed = bed[["chr", "start", "end", "name", "score", "strand"]]
 
 # Write output
-out_bed.to_csv("$output_file", index=False, sep="\\t", header=False)
+bed.to_csv("$output_file", index=False, sep="\\t", header=False)

modules/local/rose/main.nf

@@ -8,11 +8,12 @@ process ROSE {
         'biocontainers/mulled-v2-2076f4a3fb468a04063c9e6b7747a630abb457f6:fccb0c41a243c639e11dd1be7b74f563e624fcca-0' }"
 
     input:
-    tuple val(meta), path(gff)
-    path ucsc_file
+    tuple val(meta), path(bed)
+    tuple val(meta2), path(genepred)
 
     output:
-    tuple val(meta), path("${gff.baseName}_STITCHED.gff")
+    tuple val(meta), path("${meta.id}.rose.bed"), emit: stitched
+    path("versions.yml")                        , emit: versions
 
     script:
     stitch = 12500
@@ -21,6 +22,6 @@ process ROSE {
 
     stub:
     """
-    touch "${gff.baseName}_STITCHED.gff"
+    touch "${meta.id}.rose.bed"
     """
 }