Merge branch 'master' into squeezemeta

raw_inputs/raw_hisat2_index.py

+import os
+import re
+import sys
+
+def raw_hisat2_index(results_dir,  hisat2_index):
+    out = dict()
+    from os import listdir
+    from os.path import isfile, join
+    onlyfiles = [join( hisat2_index, f) for f in listdir(hisat2_index) if isfile(join(hisat2_index, f))]
+    out["hisat2_index"] = onlyfiles
+
+    return(out)
+
+#print(raw_hisat2_index(sys.argv[1],sys.argv[2])
\ No newline at end of file

raw_inputs/raw_hisat2_index.yaml

+{
+  name: raw_hisat2_index,
+  function_call: "raw_hisat2_index(config['results_dir'], config['hisat2_index'])",
+  options: [
+    {
+      name: "hisat2_index",
+      type: "input_dir",
+      value: "/Data",
+      label: "Directory containing the hisat2 index files: ",
+      volumes:  [Data: "/Data", Results: "/Results"]
+    }
+  ]
+}
\ No newline at end of file

tools/deseq2/deseq2.script.R

@@ -141,6 +141,7 @@ speciesData = snakemake@params[["biomaRtDataset"]]
 
 
  #what if we have tarnscript ID or not ENSEMBL ID instead of gene ID ?????????
+ if we know speciesData make a blast
 if (speciesData != "None") {
   # Add annotation with biomaRt
   library(biomaRt)
@@ -175,7 +176,8 @@ if (speciesData != "None") {
                   user_threshold = 0.05, correction_method = "g_SCS", 
                   domain_scope = "annotated", custom_bg = NULL, 
                   numeric_ns = "", sources = sources, as_short_link = FALSE)
-
+  if ( nrow(gostres$result) > 1) # we have some results
+  {
   png(filename = paste0(snakemake@params[["outDir"]],"/gprofiler2_plot_mqc.png"), height=800, width=800)
     p <- gostplot(gostres, capped = FALSE, interactive = FALSE)
     print(p  + ggtitle("gprofiler2 enrichment analysis for top genes to find over-representation of terms from Gene Ontology"))
@@ -188,7 +190,7 @@ if (speciesData != "None") {
   ttable = cbind(1:nrow(gostres$result), gostres$result[,-14])
   colnames(ttable)[1]="id"
   write.table(ttable, paste0(snakemake@params[["outDir"]],"/gprofiler2_mqc.tsv"), sep="\t",row.names =FALSE, quote = FALSE)
-
+  }
 }
 
 

tools/deseq2/deseq2.yaml

@@ -62,7 +62,7 @@
                 Mus musculus: "mmusculus_gene_ensembl",
                 Homo sapiens: "hsapiens_gene_ensembl",
                 Nile tilapia: "oniloticus_gene_ensembl",
-                oniloticus_gene_ensembl: "dmelanogaster_gene_ensembl"
+                Drosophila melanogaster: "dmelanogaster_gene_ensembl"
               ],
               value: "None",
               label: "Species"

tools/fastp/fastp.rule.snakefile

@@ -11,7 +11,7 @@ if config["SeOrPe"] == "PE":
         params:
             command = config["<step_name>__fastp_PE_command"],
             complexity_threshold = config["<step_name>__fastp_complexity_threshold"],
-            report_title = config["<step_name>__fastp_report_title"]+" : "+{sample},
+            report_title = config["<step_name>__fastp_report_title"]+" : {sample}",
             detect_adapter_for_pe = "--detect_adapter_for_pe" if config["<step_name>__fastp_adapter_detection_PE"] == True else "",
             adapter_sequence = "--adapter_sequence "+config["<step_name>__fastp_adapter_sequence"] if config["<step_name>__fastp_adapter_sequence"] != "" else "",
             adapter_sequence_R2 = "--adapter_sequence_r2 " + config["<step_name>__fastp_adapter_sequence_R2_PE"] if config["<step_name>__fastp_adapter_sequence_R2_PE"] != "" else "",

tools/global.yaml

@@ -55,6 +55,7 @@ data: [
     {name: "bowtie_index", category: "index"},
     {name: "bowtie2_index", category: "index"},
     {name: "bwa_mem_index", category: "index"},
+    {name: "hisat2_index", category: "index"},
     {name: "bwa_mem_2_index", category: "index"},
     {name: "kallisto_index", category: "index"},
     {name: "salmon_index", category: "index"},

tools/hisat2/hisat2.rule.snakefile

@@ -14,15 +14,15 @@ if config["SeOrPe"] == "PE":
             #indexPrefix = config["<step_name>__hisat2_index_output_dir"]+"/index",
             #here we have index files  : from .1.ht2 to .8.ht2
             indexPrefix = lambda w, input: os.path.splitext(os.path.splitext([x for x in input.index ][0])[0])[0],
-            minins = config["<step_name>__hisat2_minins_PE"],
-            maxins = config["<step_name>__hisat2_maxins_PE"],
+            minins = "-I " + config["<step_name>__hisat2_minins_PE"] if config["<step_name>__hisat2_reads_type"] == "genome" else "",
+            maxins = "-X " + config["<step_name>__hisat2_maxins_PE"] if config["<step_name>__hisat2_reads_type"] == "genome" else "",
             orientation = config["<step_name>__hisat2_orientation_PE"],
         shell:
             "{params.command} --new-summary "
             "--threads {threads} "
             "-x {params.indexPrefix} "
-            "-I {params.minins} "
-            "-X {params.maxins} "
+            "{params.minins} "
+            "{params.maxins} "
             "{params.orientation} "
             "--rg-id ID:WAW --rg SM:{wildcards.sample} "
             #"-S "#output in sam format

tools/hisat2/hisat2.yaml

@@ -20,6 +20,17 @@
         outputs: [{ name: bam, type: "bams", file: "{sample}.bam", description: "Alignment files" }],
         options:
           [
+            {
+              name: hisat2_reads_type,
+              type: radio,
+              choices:
+                [
+                  genome: "genome",
+                  transcriptome: "transcriptome",
+                ],
+              value: "transcriptome",
+              label: "Type of reads sequences",
+            },
             {
               name: hisat2_threads,
               prefix: --threads,
@@ -30,6 +41,13 @@
               step: 1,
               label: "Number of threads to use to align reads",
             },
+            {
+              name: templatelen_adjustment,
+              prefix: --no-templatelen-adjustment,
+              type: "checkbox",
+              value: TRUE,
+              label: "Disables template length adjustment for RNA-seq reads",
+            },
             {
               name: hisat2_minins_PE,
               prefix: -I,