bug fix name fastq files + bug fix memory of CMA + del ShelharRetinaD…

…ata reference for CMA
gustaveroussy · Sep 3, 2021 · 1eae588 · 1eae588
1 parent 9ca037f
commit 1eae588
Show file tree

Hide file tree

Showing 8 changed files with 13 additions and 12 deletions.
diff --git a/Snakefile b/Snakefile
@@ -50,7 +50,8 @@ if "Alignment_countTable_GE" in STEPS:
     for i in range(0,len(ALIGN_SAMPLE_NAME_GE_RAW),1):
         #check samples names and add "_GE" if needed
         ALIGN_SAMPLE_NAME_GE.append(ALIGN_SAMPLE_NAME_GE_RAW[i] + "_GE") if (ALIGN_SAMPLE_NAME_GE_RAW[i][len(ALIGN_SAMPLE_NAME_GE_RAW[i])-3:] != "_GE") else ALIGN_SAMPLE_NAME_GE.append(ALIGN_SAMPLE_NAME_GE_RAW[i])
-        ORIG_FILES = glob.glob(os.path.join(ALIGN_INPUT_DIR_GE_RAW, str(ALIGN_SAMPLE_NAME_GE_RAW[i]) + "*_R1_*.f*q*")) + glob.glob(os.path.join(ALIGN_INPUT_DIR_GE_RAW, str(ALIGN_SAMPLE_NAME_GE_RAW[i]) + "*_R2_*.f*q*"))
+        #ORIG_FILES = glob.glob(os.path.join(ALIGN_INPUT_DIR_GE_RAW, str(ALIGN_SAMPLE_NAME_GE_RAW[i]) + "*_R1_*.f*q*")) + glob.glob(os.path.join(ALIGN_INPUT_DIR_GE_RAW, str(ALIGN_SAMPLE_NAME_GE_RAW[i]) + "*_R2_*.f*q*"))
+        ORIG_FILES = glob.glob(os.path.join(ALIGN_INPUT_DIR_GE_RAW, str(ALIGN_SAMPLE_NAME_GE_RAW[i]) + "_[1-4]_S*_R1_*.f*q*")) + glob.glob(os.path.join(ALIGN_INPUT_DIR_GE_RAW, str(ALIGN_SAMPLE_NAME_GE_RAW[i]) + "_S[0-9]*_R1_*.f*q*")) + glob.glob(os.path.join(ALIGN_INPUT_DIR_GE_RAW, str(ALIGN_SAMPLE_NAME_GE_RAW[i]) + "_[1-4]_S*_R2_*.f*q*")) + glob.glob(os.path.join(ALIGN_INPUT_DIR_GE_RAW, str(ALIGN_SAMPLE_NAME_GE_RAW[i]) + "_S[0-9]*_R2_*.f*q*"))
         #files with path and extention
         ALIGN_SYMLINK_FILES_GE = ALIGN_SYMLINK_FILES_GE + [ os.path.normpath(ALIGN_INPUT_DIR_GE + "/" + os.path.basename(file).replace(ALIGN_SAMPLE_NAME_GE_RAW[i], ALIGN_SAMPLE_NAME_GE[i])) for file in ORIG_FILES]
     #files without path and extention

diff --git a/rules/Cerebro.smk b/rules/Cerebro.smk
@@ -42,7 +42,7 @@ rule cerebro:
     threads:
         1
     resources:
-        mem_mb = (lambda wildcards, attempt: min(5120 * attempt , 51200)),
+        mem_mb = (lambda wildcards, attempt: min(5120 * attempt , 102400)),
         time_min = (lambda wildcards, attempt: min(attempt * 60, 200))
     shell:
         """

diff --git a/rules/Clust_Markers_Annot_GE.smk b/rules/Clust_Markers_Annot_GE.smk
@@ -58,13 +58,13 @@ rule clust_markers_annot_ge:
     threads:
         1
     resources:
-        mem_mb = (lambda wildcards, attempt: min(3072 + attempt * 3072, 20480)),
+        mem_mb = (lambda wildcards, attempt: min(10240 + attempt * 5120, 81920)),
         time_min = (lambda wildcards, attempt: min(attempt * 60, 200))
     shell:
         """
         export TMPDIR={GLOBAL_TMP}
         TMP_DIR=$(mktemp -d -t sc_pipeline-XXXXXXXXXX) && \
-        singularity exec --no-home -B $TMP_DIR:/tmp -B $TMP_DIR:/home/$USER {params.sing_bind} \
+        singularity exec --no-home -B $TMP_DIR:/tmp -B $TMP_DIR:$HOME {params.sing_bind} \
         {SINGULARITY_ENV} \
         Rscript {params.pipeline_folder}/scripts/pipeline_part4.R \
         --input.rda.ge {params.input_rda} \

diff --git a/rules/Grp_Clust_Markers_Annot_GE.smk b/rules/Grp_Clust_Markers_Annot_GE.smk
@@ -58,7 +58,7 @@ rule grp_clust_markers_annot_ge:
     threads:
         1
     resources:
-        mem_mb = (lambda wildcards, attempt: min(5120 + attempt * 3072, 20480)),
+        mem_mb = (lambda wildcards, attempt: min(10240 + attempt * 5120, 102400)),
         time_min = (lambda wildcards, attempt: min(attempt * 120, 200))
     shell:
         """

diff --git a/rules/Int_Clust_Markers_Annot_GE.smk b/rules/Int_Clust_Markers_Annot_GE.smk
@@ -59,7 +59,7 @@ rule int_clust_markers_annot_ge:
     threads:
         1
     resources:
-        mem_mb = (lambda wildcards, attempt: min(5120 + attempt * 3072, 20480)),
+        mem_mb = (lambda wildcards, attempt: min(10240 + attempt * 5120, 102400)),
         time_min = (lambda wildcards, attempt: min(attempt * 120, 200))
     shell:
         """

diff --git a/scripts/Grouped_analysis_part2.R b/scripts/Grouped_analysis_part2.R
@@ -122,12 +122,12 @@ if (species == "homo_sapiens") {
 if (species == "mus_musculus") {
   singler.setnames <- c("MouseRNAseqData", "ImmGenData")
   clustifyr.setnames <- c("ref_MCA", "ref_tabula_muris_drop", "ref_tabula_muris_facs", "ref_moca_main", "ref_immgen", "ref_mouse.rnaseq")
-  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ShekharRetinaData","ZeiselBrainData")
+  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ZeiselBrainData") #,"ShekharRetinaData"
 }
 if (species == "rattus_norvegicus") {
   singler.setnames <- c("MouseRNAseqData", "ImmGenData")
   clustifyr.setnames <- c("ref_MCA", "ref_tabula_muris_drop", "ref_tabula_muris_facs", "ref_moca_main", "ref_immgen", "ref_mouse.rnaseq")
-  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ShekharRetinaData","ZeiselBrainData")
+  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ZeiselBrainData") #,"ShekharRetinaData"
 }
 
 #### Fixed parameters ####

diff --git a/scripts/Integration_part2.R b/scripts/Integration_part2.R
@@ -130,12 +130,12 @@ if (species == "homo_sapiens") {
 if (species == "mus_musculus") {
   singler.setnames <- c("MouseRNAseqData", "ImmGenData")
   clustifyr.setnames <- c("ref_MCA", "ref_tabula_muris_drop", "ref_tabula_muris_facs", "ref_moca_main", "ref_immgen", "ref_mouse.rnaseq")
-  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ShekharRetinaData","ZeiselBrainData")
+  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ZeiselBrainData") #,"ShekharRetinaData"
 }
 if (species == "rattus_norvegicus") {
   singler.setnames <- c("MouseRNAseqData", "ImmGenData")
   clustifyr.setnames <- c("ref_MCA", "ref_tabula_muris_drop", "ref_tabula_muris_facs", "ref_moca_main", "ref_immgen", "ref_mouse.rnaseq")
-  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ShekharRetinaData","ZeiselBrainData")
+  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ZeiselBrainData") #,"ShekharRetinaData"
 }
 
 #### Fixed parameters ####

diff --git a/scripts/pipeline_part4.R b/scripts/pipeline_part4.R
@@ -119,12 +119,12 @@ if (species == "homo_sapiens") {
 if (species == "mus_musculus") {
   singler.setnames <- c("MouseRNAseqData", "ImmGenData")
   clustifyr.setnames <- c("ref_MCA", "ref_tabula_muris_drop", "ref_tabula_muris_facs", "ref_moca_main", "ref_immgen", "ref_mouse.rnaseq")
-  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ShekharRetinaData","ZeiselBrainData")
+  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ZeiselBrainData") #,"ShekharRetinaData"
 }
 if (species == "rattus_norvegicus") {
   singler.setnames <- c("MouseRNAseqData", "ImmGenData")
   clustifyr.setnames <- c("ref_MCA", "ref_tabula_muris_drop", "ref_tabula_muris_facs", "ref_moca_main", "ref_immgen", "ref_mouse.rnaseq")
-  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ShekharRetinaData","ZeiselBrainData")
+  scrnaseq.setnames <- c("BaronPancreasData(mouse)","ZeiselBrainData") #,"ShekharRetinaData"
 }
 
 #### Fixed parameters ####