changes for version 1.3.4

config.py.sample

@@ -161,5 +161,5 @@ other_files = {
     "infusion_cfg": "/path/to/infusion_index/infusion.cfg",
     "soapfuse_cfg": "/path/to/soapfuse_config/config_h<release>.txt",
     "soapfuse_cfg_mm10": "/path/to/soapfuse_config/config_m<release>.txt",
-    "easyfuse_model": os.path.join(module_dir, "data", "model", "Fusion_modeling_FFPE_deploy_v01.model_full_data.EasyFuse_model.rds")
+    "easyfuse_model": os.path.join(module_dir, "data", "model", "Fusion_modeling_FFPE_train_v32.random_forest.model_full_data.EF_full.rds")
 }

fetchdata.py

@@ -15,6 +15,7 @@
 import os.path
 import math
 import argparse
+import subprocess
 import misc.queueing as Queueing
 from misc.samples import SamplesDB
 from misc.logger import Logger
@@ -62,7 +63,8 @@ def get_input_read_count_from_star(star_out_bam):
     @staticmethod
     def get_input_read_count_from_fastq(fastq):
         """Parses input FASTQ to get read count"""
-        result = subprocess.getoutput("zcat {} | wc -l".format(fastq))
+        ps = subprocess.Popen(("zcat", fastq), stdout=subprocess.PIPE)
+        result = subprocess.check_output(("wc", "-l"), stdin=ps.stdout)
         return int(result) / 4
 
     def run(self, fusion_support, fq1, fq2):

processing.py

@@ -134,8 +134,8 @@ def execute_pipeline(self, fq1, fq2, sample_id, ref_genome, ref_trans, tool_num_
         infusion_path = os.path.join(fusion_path, "infusion")
         soapfuse_path = os.path.join(fusion_path, "soapfuse")
         fetchdata_path = os.path.join(self.working_dir, "Sample_{}".format(sample_id), "fetchdata")
-        fastqc_1 = os.path.join(qc_path, sample_id + "_R1_fastqc", "fastqc_data.txt")
-        fastqc_2 = os.path.join(qc_path, sample_id + "_R2_fastqc", "fastqc_data.txt")
+        fastqc_1 = os.path.join(qc_path, os.path.basename(fq1).rstrip(".fastq.gz") + "_fastqc", "fastqc_data.txt")
+        fastqc_2 = os.path.join(qc_path, os.path.basename(fq2).rstrip(".fastq.gz") + "_fastqc", "fastqc_data.txt")
 
 
         for folder in [
@@ -199,7 +199,7 @@ def execute_pipeline(self, fq1, fq2, sample_id, ref_genome, ref_trans, tool_num_
         cmd_extr_fastq1 = "gunzip --keep {0}".format(fq1)
         cmd_extr_fastq2 = "gunzip --keep {0}".format(fq2)
         # Added python interpreter to circumvent external hardcoded shell script
-        cmd_mapsplice = "python {0} --chromosome-dir {1} -x {2} -1 {3} -2 {4} --threads waiting_for_cpu_number --output {5} --qual-scale phred33 --bam --seglen 20 --min-map-len 40 --gene-gtf {6} --fusion".format(cmds["mapsplice"], genome_chrs_path, bowtie_index_path, fq1[:-3], fq2[:-3], mapsplice_path, genes_gtf_path)
+        cmd_mapsplice = "{0} --chromosome-dir {1} -x {2} -1 {3} -2 {4} --threads waiting_for_cpu_number --output {5} --qual-scale phred33 --bam --seglen 20 --min-map-len 40 --gene-gtf {6} --fusion".format(cmds["mapsplice"], genome_chrs_path, bowtie_index_path, fq1[:-3], fq2[:-3], mapsplice_path, genes_gtf_path)
         # (4) Fusiocatcher
         cmd_fusioncatcher = "{0} --input {1} --data {2} --output {3} -p waiting_for_cpu_number".format(cmds["fusioncatcher"], ",".join([fq1, fq2]), fusioncatcher_index_path, fusioncatcher_path)
         # star-fusion and star-chip can be run upon a previous star run (this MUST NOT be the star_filter run, but the star_expression run)