Update feature_counts

workflow/rules/feature_counts

+#########################################################################
+# RNAflow: an automated pipeline to analyse transcriptomic data         #
+#                                                                       #
+# Authors: Rachel Legendre                                              #
+# Copyright (c) 2021-2022  Institut Pasteur (Paris).                    #
+#                                                                       #
+# This file is part of RNAflow workflow.                                #
+#                                                                       #
+# RNAflow is free software: you can redistribute it and/or modify       #
+# it under the terms of the GNU General Public License as published by  #
+# the Free Software Foundation, either version 3 of the License, or     #
+# (at your option) any later version.                                   #
+#                                                                       #
+# RNAflow is distributed in the hope that it will be useful,            #
+# but WITHOUT ANY WARRANTY; without even the implied warranty of        #
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the          #
+# GNU General Public License for more details .                         #
+#                                                                       #
+# You should have received a copy of the GNU General Public License     #
+# along with RNAflow (LICENSE).                                         #
+# If not, see <https://www.gnu.org/licenses/>.                          #
+#########################################################################
 
+
+rule feature_counts:
+    """
+    Feature counts (subread) is a highly efficient general-purpose read summarization program that counts mapped reads for genomic features such as genes, exons, promoter, gene bodies, genomic bins and chromosomal locations.
+    :reference: http://bioinf.wehi.edu.au/featureCounts/
+
+    Required input:
+         __feature_counts__input: sorted bam file
+
+    Required output:
+        __feature_counts__output_count: output tabulated-delimited file
+        __feature_counts__output_gene_count: output formatted tab-delimited file
+
+    Config:
+
+        .. code-block:: yaml
+
+            feature_counts:
+                gff: " "       #path to the GFF/GTF annotation file
+                options:  " "  #options for featureCounts you want use
+    """
+
+
+    input:
+        bam = __feature_counts__input
+    output:
+        count = __feature_counts__output_count,
+        gene_count = __feature_counts__output_gene_count
+    params:
+        gff = __feature_counts__gff,
+        mapp = config['feature_counts']["options"]  # -t exon
+    log:
+        __feature_counts__log
+    threads:
+        config['feature_counts']['threads']
+    run:
+        shell("""featureCounts -T {threads} {params.mapp} \
+                 -a {params.gff} -o {output.count} {input.bam} 2> {log}""")
+
+        shell("""cut -f 1,7- {output.count} | sed '2d' > {output.gene_count}""")