add star

workflow/rules/feature_counts → workflow/rules/feature_counts.rules

@@ -23,41 +23,21 @@
 
 
 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,
+        full_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
+        err = __feature_counts__logs_err,
+        out = __feature_counts__logs_out
     threads:
         config['feature_counts']['threads']
     run:
         shell("""featureCounts -T {threads} {params.mapp} \
-                 -a {params.gff} -o {output.count} {input.bam} 2> {log}""")
+                 -a {params.gff} -o {output.full_count} {input.bam} > {log.out} 2> {log.err}""")
 
-        shell("""cut -f 1,7- {output.count} | sed '2d' > {output.gene_count}""")
+        shell("""cut -f 1,7- {output.full_count} | sed '2d' > {output.gene_count}""")

workflow/rules/star_index → workflow/rules/star_index.rules

@@ -24,9 +24,6 @@
 
 
 rule star_index:
-
-
-
     input:
        fasta =  __star_index__fasta
     output:

workflow/rules/star_mapping.rules

+#########################################################################
+# 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 star_mapping:
+    input:
+        fastq = __star_mapping__input,
+        index = __star_mapping__index_done
+    log:
+        __star_mapping__logs
+    output:
+        __star_mapping__sort
+    params:
+        prefix = temp(__star_mapping__output_prefix),
+        index = __star_mapping__index,
+        #read_groups = __star_mapping__read_groups,
+        kwargs = config['star_mapping']['options']
+    threads:
+        config['star_mapping']['threads']
+    shell:
+        """ 
+        STAR --genomeDir {params.index} \
+             --readFilesIn {input.fastq}  \
+             --runThreadN {threads} \
+             --genomeLoad NoSharedMemory \
+             --outSAMtype BAM SortedByCoordinate \
+             --readFilesCommand zcat \
+             --seedSearchStartLmax 20 \
+             --outFileNamePrefix {params.prefix1} \
+            {params.kwargs}  2> {log}
+
+
+        samtools index {params.prefix}Aligned.sortedByCoord.out.bam  2>> {log} 
+        """