Merge branches 'development' and 'master' of https://github.com/kirch…

…erlab/MPRAsnakeflow into development

workflow/rules/assigned_counts.smk

@@ -211,23 +211,10 @@ rule assigned_counts_combine_replicates_barcode_output:
         thresh=lambda wc: config["experiments"][wc.project]["configs"][wc.config][
             "filter"
         ]["bc_threshold"],
-        replicates=lambda wc: " ".join(
-            [
-                "--replicate %s" % r
-                for r in getReplicatesOfCondition(wc.project, wc.condition)
-            ]
-        ),
         bc_counts=lambda wc: " ".join(
             [
-                "--counts %s" % c
-                for c in expand(
-                    "results/experiments/{project}/assigned_counts/{assignment}/{config}/{condition}_{replicate}_barcode_assigned_counts.tsv.gz",
-                    replicate=getReplicatesOfCondition(wc.project, wc.condition),
-                    project=wc.project,
-                    condition=wc.condition,
-                    assignment=wc.assignment,
-                    config=wc.config,
-                )
+                "--counts %s results/experiments/%s/assigned_counts/%s/%s/%s_%s_barcode_assigned_counts.tsv.gz" % (rep, wc.project, wc.assignment, wc.config, wc.condition, rep)
+                for rep in getReplicatesOfCondition(wc.project, wc.condition)
             ]
         ),
     log:
@@ -236,9 +223,9 @@ rule assigned_counts_combine_replicates_barcode_output:
         ),
     shell:
         """
-        python {input.script} {params.bc_counts} \
+        python {input.script} \
+        {params.bc_counts} \
         --threshold {params.thresh} \
-        {params.replicates}  \
         --output-threshold {output.bc_merged_thresh} \
         --output {output.bc_merged_all} &> {log}
         """

workflow/rules/common.smk

@@ -536,9 +536,9 @@ def withoutZeros(project, conf):
 
 
 def getSplitNumber():
-    splits = []
+    splits = [1]
 
-    for assignment in config["assignments"]:
+    for assignment in getAssignments():
         splits += [config["assignments"][assignment]["alignment_tool"]["split_number"]]
 
     return max(splits)

workflow/rules/qc_report.smk

@@ -49,18 +49,18 @@ rule qc_report_assoc:
             cp {input.quarto_script} {output.quarto_file};
             cd `dirname {output.quarto_file}`;
             quarto render `basename {output.quarto_file}` --output `basename {output.assi_file}` \
-            -P assignment:{wildcards.assignment} \
-            -P bc_length:{params.bc_length} \
-            -P fw:{params.fw} \
-            -P rev:{params.rev} \
-            -P bc:{params.bc} \
-            -P workdir:{params.workdir} \
-            -P design_file:{input.design_file} \
-            -P design_file_checked:{input.design_file_checked} \
-            -P configs:{wildcards.assignment_config} \
-            -P plot_file:{input.plot} \
-            -P statistic_filter_file:{input.statistic_filter} \
-            -P statistic_all_file:{input.statistic_all}
+            -P "assignment:{wildcards.assignment}" \
+            -P "bc_length:{params.bc_length}" \
+            -P "fw:{params.fw}" \
+            -P "rev:{params.rev}" \
+            -P "bc:{params.bc}" \
+            -P "workdir:{params.workdir}" \
+            -P "design_file:{input.design_file}" \
+            -P "design_file_checked:{input.design_file_checked}" \
+            -P "configs:{wildcards.assignment_config}" \
+            -P "plot_file:{input.plot}" \
+            -P "statistic_filter_file:{input.statistic_filter}" \
+            -P "statistic_all_file:{input.statistic_all}"
         ) &> {log}
         """
 
@@ -110,25 +110,25 @@ rule qc_report_count:
             cp {input.quarto_script} {output.quarto_file};
             cd `dirname {output.quarto_file}`;
             quarto render `basename {output.quarto_file}` --output `basename {output.count_file}` \
-            -P assignment:{wildcards.assignment} \
-            -P project:{wildcards.project} \
-            -P dna_over_rna_plot:{input.dna_over_rna} \
-            -P dna_over_rna_thresh_plot:{input.dna_over_rna_thresh} \
-            -P dna_oligo_coor_min_thre_plot:{input.dna_oligo_coor_min_thre_plot} \
-            -P rna_oligo_coor_min_thre_plot:{input.rna_oligo_coor_min_thre_plot} \
-            -P dna_oligo_coor_plot:{input.dna_oligo_coor_plot} \
-            -P rna_oligo_coor_plot:{input.rna_oligo_coor_plot} \
-            -P ratio_oligo_coor_plot:{input.ratio_oligo_coor_plot} \
-            -P ratio_oligo_min_thre_plot:{input.ratio_oligo_min_thre_plot} \
-            -P statistics_all_merged:{input.statistics_all_merged} \
-            -P counts_per_oligo_dna:{input.counts_per_oligo_dna} \
-            -P counts_per_oligo_rna:{input.counts_per_oligo_rna} \
-            -P statistics_all_single:{input.statistics_all_single} \
-            -P activity_all:{input.activity_all} \
-            -P activity_thresh:{input.activity_thresh} \
-            -P statistics_all_oligo_cor_all:{input.statistics_all_oligo_cor_all} \
-            -P statistics_all_oligo_cor_thresh:{input.statistics_all_oligo_cor_thresh} \
-            -P thresh:{params.thresh} \
-            -P workdir:{params.workdir}
+            -P "assignment:{wildcards.assignment}" \
+            -P "project:{wildcards.project}" \
+            -P "dna_over_rna_plot:{input.dna_over_rna}" \
+            -P "dna_over_rna_thresh_plot:{input.dna_over_rna_thresh}" \
+            -P "dna_oligo_coor_min_thre_plot:{input.dna_oligo_coor_min_thre_plot}" \
+            -P "rna_oligo_coor_min_thre_plot:{input.rna_oligo_coor_min_thre_plot}" \
+            -P "dna_oligo_coor_plot:{input.dna_oligo_coor_plot}" \
+            -P "rna_oligo_coor_plot:{input.rna_oligo_coor_plot}" \
+            -P "ratio_oligo_coor_plot:{input.ratio_oligo_coor_plot}" \
+            -P "ratio_oligo_min_thre_plot:{input.ratio_oligo_min_thre_plot}" \
+            -P "statistics_all_merged:{input.statistics_all_merged}" \
+            -P "counts_per_oligo_dna:{input.counts_per_oligo_dna}" \
+            -P "counts_per_oligo_rna:{input.counts_per_oligo_rna}" \
+            -P "statistics_all_single:{input.statistics_all_single}" \
+            -P "activity_all:{input.activity_all}" \
+            -P "activity_thresh:{input.activity_thresh}" \
+            -P "statistics_all_oligo_cor_all:{input.statistics_all_oligo_cor_all}" \
+            -P "statistics_all_oligo_cor_thresh:{input.statistics_all_oligo_cor_thresh}" \
+            -P "thresh:{params.thresh}" \
+            -P "workdir:{params.workdir}"
         ) &> {log}
         """

workflow/scripts/count/merge_replicates_barcode_counts.py

@@ -8,8 +8,8 @@
     "counts_files",
     required=True,
     multiple=True,
-    type=click.Path(exists=True, readable=True),
-    help="Assigned barcode count file",
+    type=(str,click.Path(exists=True, readable=True)),
+    help="Replicate name and assigned barcode count file",
 )
 @click.option(
     "--threshold",
@@ -19,14 +19,6 @@
     type=int,
     help="Number of required barcodes (default 10)",
 )
-@click.option(
-    "--replicate",
-    "replicates",
-    multiple=True,
-    type=str,
-    help="replicate name",
-    required=True,
-)
 @click.option(
     "--output",
     "output_threshold_file",
@@ -41,39 +33,18 @@
     type=click.Path(writable=True),
     help="Output file.",
 )
-def cli(counts_files, bc_thresh, replicates, output_threshold_file, output_file):
+def cli(counts_files, bc_thresh, output_threshold_file, output_file):
     """
     Merge the associated barcode count files of all replicates.
     """
 
-    # ensure there are as many replicates as there are files
-    if len(replicates) != len(counts_files):
-        raise (
-            click.BadParameter(
-                "Number of replicates ({}) doesn't equal the number of files ({}).".format(
-                    len(replicates), len(counts_files)
-                )
-            )
-        )
-
-    # check if every file exists
-    for file in counts_files:
-        if not os.path.exists(file):
-            raise (click.BadParameter("{}: file not found".format(file)))
-
     all_reps = []
-    for file in counts_files:
-        curr_rep = -1
-        # find the replicate name of the current file
-        for rep in replicates:
-            if rep in os.path.basename(file).split("_")[1]:
-                curr_rep = rep
-                break
-        if curr_rep == -1:
-            raise (click.BadParameter("{}: incorrect file".format(file)))
+    replicates = []
+    for rep, file in counts_files:
         df = pd.read_csv(file, sep="\t")
-        df['replicate'] = curr_rep
+        df['replicate'] = rep
         all_reps.append(df)
+        replicates.append(rep)
 
     df = pd.concat(all_reps)
     df = df[df["oligo_name"] != "no_BC"]

workflow/scripts/variants/correlateVariantTables.py

@@ -57,7 +57,7 @@ def filterOnThreshold(variants, threshold):
                 variants_2 = filterOnThreshold(variants_2, bc_threshold)
 
             click.echo("Join variants file...")
-            variants_join = variants_1.join(variants_2, how="inner", lsuffix='_A', rsuffix='_B')[["log2_expression_A", "log2_expression_B"]]
+            variants_join = variants_1.join(variants_2, how="inner", lsuffix='_A', rsuffix='_B')[["log2FoldChange_expression_A", "log2FoldChange_expression_B"]]
 
             output = pd.concat([output, pd.DataFrame([[condition, rep_1, rep_2, variants_join.shape[0], bc_threshold, variants_join.corr(method="pearson").iloc[0,1],variants_join.corr(method="spearman").iloc[0,1]]])], ignore_index=True)