Merge pull request #10 from TRON-Bioinformatics/release_1.3.5

Release 1.3.5

Author: ibn-salem

Dockerfile renamed to Docker/Dockerfile

@@ -1,7 +1,7 @@
 from ubuntu:20.04
 
 RUN apt-get update -y --fix-missing
-RUN DEBIAN_FRONTEND="noninteractive" apt-get install -y software-properties-common python python3 python3-pip emacs curl wget zip unzip tar zlib1g-dev liblzo2-dev libcurl4-openssl-dev libssl-dev libncurses5 tzdata
+RUN DEBIAN_FRONTEND="noninteractive" apt-get install -y software-properties-common git python python3 python3-pip emacs curl wget zip unzip tar zlib1g-dev liblzo2-dev libcurl4-openssl-dev libssl-dev libncurses5 tzdata
 
 RUN curl -O https://repo.anaconda.com/miniconda/Miniconda2-latest-Linux-x86_64.sh
 RUN bash Miniconda2-latest-Linux-x86_64.sh -b -p /root/miniconda2
@@ -35,6 +35,15 @@ RUN R --slave -e 'remotes::install_version("tidyverse", "1.2.1")'
 RUN R --slave -e 'remotes::install_version("XML", "3.99-0.9")'
 RUN R --slave -e 'remotes::install_version("randomForest", "4.6-14")'
 
-
 COPY ./code/ /code/
+
+# After release 1.3.5 these lines can be used to automate docker image creation process further
+#RUN wget https://github.com/TRON-Bioinformatics/EasyFuse/archive/refs/tags/v1.3.5.tar.gz && \
+#tar xvfz v1.3.5.tar.gz && \
+#mv EasyFuse-1.3.5/ /code/easyfuse/ && \
+#cd /code/easyfuse/ && \
+#mv config.ini.docker config.ini && \
+#mv build_env.sh.sample build_env.sh && \
+#mv blacklist.txt.sample blacklist.txt
+
 ENV PERL5LIB "$PERL5LIB:/code/SOAPfuse/1.27/source/bin/perl_module/"

Docker/build_docker_img_test.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+docker build \
+--rm \
+-t docker.io/tronbioinformatics/easyfuse:latest \
+.

Docker/run_docker_img_interactive.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+docker run \
+--name test_easyfuse_container \
+-v /scratch/info/data/easyfuse/easyfuse_ref:/ref \
+-it docker.io/tronbioinformatics/easyfuse:1.3.5 \
+/bin/bash

Docker/run_docker_img_test.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+docker run \
+--name test_easyfuse_container \
+-v /scratch/info/data/easyfuse/easyfuse_ref:/ref \
+-v /scratch/info/data/easyfuse/easyfuse_data:/data \
+--rm \
+-it docker.io/tronbioinformatics/easyfuse:latest \
+python /code/easyfuse/processing.py -i /data/input_fastqs -o /data/results/

Docker/run_singularity_img_test.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+
+singularity exec \
+-W ./ \
+--bind /scratch/info/data/easyfuse/easyfuse_ref:/ref \
+--bind /scratch/info/data/easyfuse/easyfuse_data:/data \
+docker://docker.io/tronbioinformatics/easyfuse:latest \
+python /code/easyfuse/processing.py -i /data/input_fastqs -o /data/results/
+

README.md

@@ -21,7 +21,7 @@ We recommend using EasyFuse with the Docker container.
 The Docker image can be downloaded from [dockerhub](https://hub.docker.com/r/tronbioinformatics/easyfuse) using the following command:
 
 ```
-docker pull tronbioinformatics/easyfuse:1.3.4
+docker pull tronbioinformatics/easyfuse:latest
 ```
 
 ### Download reference data
@@ -56,8 +56,8 @@ docker run \
   -v </path/to/data>:/data \
   -v </path/to/output>:/output \
   --rm \
-  -it easyfuse:1.3.4 \
-  python /code/easyfuse-1.3.4/processing.py -i /data -o /output
+  -it easyfuse:latest \
+  python /code/easyfuse/processing.py -i /data -o /output
 ```
 
 
@@ -68,7 +68,7 @@ The output can be found in `</path/to/output>/results/`. The Output format is de
 The EasyFuse pipeline depends on multiple external fusion prediction tools and other dependencies. For example:
 
   - [STAR](https://github.com/alexdobin/STAR) (2.6.1d) 
-  - [STAR-Fusion](https://github.com/STAR-Fusion/STAR-Fusion/wiki) (2.6.1d) 
+  - [STAR-Fusion](https://github.com/STAR-Fusion/STAR-Fusion/wiki) (1.5.0) 
   - [Fusioncatcher](https://github.com/ndaniel/fusioncatcher)(1.00)
   - [MapSplice2](https://github.com/davidroberson/MapSplice2) (2.2.1)
   - [InFusion](https://bitbucket.org/kokonech/infusion/src/master/) (0.8)

config.ini.docker

@@ -0,0 +1,88 @@
+# Required user input:
+# 1) Which fusion prediction tools should be executed (tools)
+# 2) Which post-processing steps should be executed (fd_tools)
+# 3) Which reference data shall be used (ref_trans_version & ref_genome_build)
+# 4) To whom shall slurm mails be sent to (receiver)
+
+[general]
+version = 1.3.5
+pipeline_name = EasyFuse
+tools = QC,Readfilter,Fusioncatcher,Star,Starfusion,Infusion,Mapsplice,Soapfuse,Fetchdata,Summary
+fusiontools = Fusioncatcher,Starfusion,Infusion,Mapsplice,Soapfuse
+fd_tools = Fusiongrep,Contextseq,Starindex,ReadFilter2,ReadFilter2b,StaralignBest,BamindexBest,RequantifyBest
+sender = [email protected]
+receiver = [email protected]
+min_read_len_perc = 0.75
+max_dist_proper_pair = 200000
+cis_near_distance = 1000000
+model_pred_threshold = 0.5
+tsl_filter = 4,5,NA
+requant_mode = best
+context_seq_len = 400
+ref_genome_build = hg38
+ref_trans_version = ensembl
+queueing_system = none
+time_limit = 30-00:00:0
+partition = Compute
+user = sorn
+module_dir = /code/easyfuse/
+
+# Define ressource usage (cpu (number of threads), mem (ram in Gb)):
+[resources]
+qc = 6,10
+readfilter = 6,50
+star = 6,40
+mapsplice = 6,30
+fusioncatcher = 6,30
+starchip = 12,30
+starfusion = 6,30
+infusion = 6,30
+soapfuse = 6,20
+classification = 1,16
+fetchdata = 12,50
+summary = 1,16
+
+
+# execution command for individual programs (what you write here should be identical to what is typed in the console)
+[commands]
+# for qc
+fastqc = fastqc
+skewer = /code/skewer-0.2.2/skewer
+# for processing
+mapsplice = mapsplice.py
+fusioncatcher = /code/fusioncatcher/1.0/bin/fusioncatcher
+starfusion = STAR-Fusion
+infusion = /code/InFusion-0.8/infusion
+soapfuse = /code/SOAPfuse/1.27/SOAPfuse-RUN.pl
+# for processing and fetch data
+star = STAR
+samtools = samtools
+# for liftover
+crossmap = test
+
+
+# full path to reference files
+[references]
+genome_fasta = /ref/Homo_sapiens.GRCh38.dna.primary_assembly.fa
+genome_fastadir = /ref/fasta
+genome_sizes = /ref/STAR_idx/chrNameLength.txt
+genes_fasta = /ref/Homo_sapiens.GRCh38.cdna.all.fa
+genes_gtf = /ref/Homo_sapiens.GRCh38.86.gtf
+genes_adb = /ref/Homo_sapiens.GRCh38.86.gff3.db
+genes_tsl = /ref/Homo_sapiens.GRCh38.86.gtf.tsl
+
+
+
+# full path to program indices
+[indices]
+star = /ref/star_index/
+bowtie = /ref/bowtie_index/hg38
+starfusion = /ref/starfusion_index/
+fusioncatcher = /ref/fusioncatcher_index/
+
+
+# full path to program specific config files (these are just general files which need no user modification)
+[other_files]
+infusion_cfg = /ref/infusion.cfg
+soapfuse_cfg = /ref/soapfuse.cfg
+easyfuse_model = /code/easyfuse/data/model/Fusion_modeling_FFPE_train_v33.random_forest.model_full_data.EF_full.rds

data/model/Fusion_modeling_FFPE_train_v32.random_forest.model_full_data.EF_full.rds

@@ -53,7 +53,6 @@ def __init__(self, scratch_path, fetchdata_path, sample_id, cfg_file):
         if cfg_file.endswith("ini"):
             self.cfg = ConfigParser()
             self.cfg.read(cfg_file)
-            print(self.cfg)
         elif cfg_file.endswith("json"):
             with open(cfg_file) as config_file:
                 self.cfg = json.load(config_file)

data/model/Fusion_modeling_FFPE_train_v32.random_forest.model_full_data.EF_full_rep.rds

@@ -572,8 +572,8 @@ def lookup_fusions_in_prediction(self, dict_of_fusion_dicts):
                     #       eg: fusion with gene1 "AB1" and gene2 "AB2" will match to fusion "AB11"-"AB22"
                     #if uniq_fusion_id_split[0] in fusion_id_split and uniq_fusion_id_split[2] in fusion_id_split:
                     # urla: possible solution:
-                    print(fusion_id_split)
-                    print(uniq_fusion_id_split)
+                    #print(fusion_id_split)
+                    #print(uniq_fusion_id_split)
                     if ((uniq_fusion_id_split[0] == fusion_id_split[0] and uniq_fusion_id_split[1] == fusion_id_split[1]) or
                             (uniq_fusion_id_split[0] == fusion_id_split[1] and uniq_fusion_id_split[1] == fusion_id_split[0])):
                         found_fusion = True
@@ -601,7 +601,7 @@ def run(self):
             self.logger.debug("Generating Detected Fusions table")
 
             fusion_result_dict, results_with_errors_dict = self.concatenate_fusion_results(tool_state_path, self.fusion_output_path)
-            print(len(fusion_result_dict))
+            #print(len(fusion_result_dict))
             if sum(results_with_errors_dict.values()) == len(fusion_result_dict):
                 self.logger.error("Fusion parsing failed completely. Revision required. Aborting.")
                 sys.exit(1)

data/model/Fusion_modeling_FFPE_train_v33.random_forest.model_full_data.EF_full.rds

@@ -54,7 +54,7 @@ def __init__(self, bam, output, context_file):
 
         self.coord_dict = {}
         self.get_ranges(context_file)
-        print(self.coord_dict)
+        #print(self.coord_dict)
 
     def get_ranges(self, context_file):
         """ vlkfh """

data/model/Fusion_modeling_FFPE_train_v33.random_forest.model_full_data.EF_full_rep.rds

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+rm -rf test_out_ini
+
+python processing.py \
+    -i test_case/SRR1659960_05pc_R1.fastq.gz \
+    test_case/SRR1659960_05pc_R2.fastq.gz \
+    -o test_out_ini/ \
+    -c config.ini \
+    -p 30448