Merge pull request #211 from nf-core/136-implement-psirc-for-isoform-detection

Implement isoform detection methods

Author: nictru

conf/full.config

@@ -12,6 +12,6 @@
 */
 
 params {
-    tools                      = 'circexplorer2,ciriquant,find_circ,circrna_finder,mapsplice,dcc,segemehl'
-    min_tools                  = 2
+    tools     = 'psirc,circexplorer2,ciri,find_circ,circrna_finder,mapsplice,circtools,segemehl'
+    min_tools = 2
 }

conf/modules.config

@@ -66,6 +66,12 @@
                         "git_sha": "15a93581f7f81d05c04b828954004a089360ea9b",
                         "installed_by": ["modules"]
                     },
+                    "bwa/mem": {
+                        "branch": "master",
+                        "git_sha": "a29f18660f5e3748d44d6f716241e70c942c065d",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/bwa/mem/bwa-mem.diff"
+                    },
                     "cat/cat": {
                         "branch": "master",
                         "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
@@ -111,11 +117,21 @@
                         "git_sha": "49f4e50534fe4b64101e62ea41d5dc43b1324358",
                         "installed_by": ["modules"]
                     },
+                    "fastp": {
+                        "branch": "master",
+                        "git_sha": "d082103d7976a2804f21225446cc110cbd822f4c",
+                        "installed_by": ["modules"]
+                    },
                     "fastqc": {
                         "branch": "master",
                         "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
                         "installed_by": ["modules"]
                     },
+                    "filtlong": {
+                        "branch": "master",
+                        "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
+                        "installed_by": ["modules"]
+                    },
                     "gawk": {
                         "branch": "master",
                         "git_sha": "27be1be5a87724096b51e1fe579ecbd773f53f1b",
@@ -201,6 +217,16 @@
                         "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
                         "installed_by": ["modules"]
                     },
+                    "seqkit/fx2tab": {
+                        "branch": "master",
+                        "git_sha": "05954dab2ff481bcb999f24455da29a5828af08d",
+                        "installed_by": ["modules"]
+                    },
+                    "seqkit/stats": {
+                        "branch": "master",
+                        "git_sha": "9fe7867a4f012db581d7bd560228ded1074eb0e5",
+                        "installed_by": ["modules"]
+                    },
                     "star/align": {
                         "branch": "master",
                         "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
@@ -221,6 +247,11 @@
                         "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",
                         "installed_by": ["modules"]
                     },
+                    "trinity": {
+                        "branch": "master",
+                        "git_sha": "05954dab2ff481bcb999f24455da29a5828af08d",
+                        "installed_by": ["modules"]
+                    },
                     "tximeta/tximport": {
                         "branch": "master",
                         "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",

modules.json

@@ -4,6 +4,7 @@
 import yaml
 
 import polars as pl
+import yaml
 
 # Versions
 
@@ -17,8 +18,6 @@
 with open("versions.yml", "w") as f:
     f.write(yaml.dump(versions))
 
-# Main
-
 exons_only = bool("${exons_only}")
 
 columns = ['chr', 'start', 'end', 'name', 'score', 'strand',
@@ -41,8 +40,8 @@
 
 if exons_only:
     df_exons = df.with_columns(
-        exonSizes = pl.col('exonSizes').str.split(','),
-        exonStarts = pl.col('exonStarts').str.split(',')
+        exonSizes = pl.col('exonSizes').cast(pl.Utf8).str.split(','),
+        exonStarts = pl.col('exonStarts').cast(pl.Utf8).str.split(',')
     ).explode('exonSizes', 'exonStarts')
     df_exons = df_exons.with_columns(
         type = pl.lit('exon'),

modules/local/annotation/bed2gtf/templates/bed2gtf.py

@@ -0,0 +1,6 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::gtfparse=2.5.0
+  - conda-forge::pyyaml=6.0.2

modules/local/circtools/annotation/environment.yml

@@ -0,0 +1,20 @@
+process CIRCTOOLS_ANNOTATION {
+    tag "${meta.id}"
+    label 'process_single'
+
+    conda "environment.yml"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'oras://community.wave.seqera.io/library/gtfparse_pyyaml:e3b66ef529a096e7'
+        : 'community.wave.seqera.io/library/gtfparse_pyyaml:508c7607beb17f69'}"
+
+    input:
+    tuple val(meta), path(gtf)
+
+    output:
+    tuple val(meta), path("${prefix}.bed"), emit: bed
+    path "versions.yml"        , emit: versions
+
+    script:
+    prefix = task.ext.prefix ?: "${meta.id}"
+    template 'annotation.py'
+}

modules/local/circtools/annotation/main.nf

@@ -0,0 +1,65 @@
+#! /usr/bin/env python3
+
+import platform
+
+import gtfparse
+import polars as pl
+import yaml
+
+# Read GTF file
+df_gtf = gtfparse.read_gtf("${gtf}")
+
+# Filter for exon features only
+exons = df_gtf.filter(pl.col("feature") == "exon")
+
+# Convert to polars DataFrame for better performance
+exons_pl = pl.DataFrame(exons)
+
+# Add 0-based start for BED format
+exons_pl = exons_pl.with_columns(
+    start_0based=pl.col("start") - 1
+)
+
+# Number exons within each gene
+exons_pl = (
+    exons_pl
+    .sort(["gene_id", "start"])
+    .with_columns([
+        pl.col("gene_id").cumcount().over("gene_id").alias("exon_number")
+    ])
+)
+
+# Create name column in the required format
+exons_pl = exons_pl.with_columns([
+    (
+        pl.col("gene_id") + "_exon_" +
+        pl.col("exon_number").cast(pl.Utf8) + "_0_chr" +
+        pl.col("seqname") + "_" +
+        (pl.col("start")).cast(pl.Utf8) + "_" +
+        pl.when(pl.col("strand") == "+").then(pl.lit("f")).otherwise(pl.lit("r"))
+    ).alias("name")
+])
+
+# Select and rename columns for BED format
+bed_df = exons_pl.select([
+    pl.col("seqname").alias("chrom"),
+    pl.col("start_0based").alias("start"),
+    pl.col("end"),
+    pl.col("name"),
+    pl.lit(0).alias("score"),
+    pl.col("strand")
+])
+
+# Write to BED file
+bed_df.write_csv("${prefix}.bed", separator="\\t", include_header=False)
+
+# Log versions
+versions = {
+    "${task.process}": {
+        "python": platform.python_version(),
+        "polars": pl.__version__
+    }
+}
+
+with open("versions.yml", "w") as f:
+    yaml.dump(versions, f)

modules/local/circtools/annotation/templates/annotation.py

@@ -0,0 +1,5 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::circtools=2.0

modules/local/circtools/detect/environment.yml

@@ -1,8 +1,8 @@
-process DCC {
+process CIRCTOOLS_DETECT {
     tag "${meta.id}"
     label 'process_high'
 
-    conda "bioconda::circtools=2.0"
+    conda "environment.yml"
     container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
         ? 'https://depot.galaxyproject.org/singularity/circtools:2.0--pyhdfd78af_0'
         : 'biocontainers/circtools:2.0--pyhdfd78af_0'}"
@@ -19,9 +19,6 @@ process DCC {
 
     path "versions.yml", emit: versions
 
-    when:
-    task.ext.when == null || task.ext.when
-
     script:
     def args = task.ext.args ?: ''
     prefix = task.ext.prefix ?: "${meta.id}"

modules/local/dcc/dcc/main.nf modules/local/circtools/detect/main.nfmodules/local/dcc/dcc/main.nf renamed to modules/local/circtools/detect/main.nf

@@ -0,0 +1,9 @@
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::bedtools=2.31.1
+  - bioconda::circtools=2.0.1
+  - bioconda::nanofilt=2.8.0
+  - bioconda::pblat=2.5.1
+  - bioconda::samtools=1.22