first commit

README.md

@@ -0,0 +1,12 @@
+# RNA count exp generate from gtf Pipeline
+
+> Author:  Li Zhihui
+>
+> E-mail：18210700119@fudan.edu.cn
+>
+> Git: 
+>
+> Last Updates: 2020/08/23
+
+## 安装指南
+

conf/fastq_screen.conf

@@ -0,0 +1,94 @@
+# This is an example configuration file for FastQ Screen
+
+############################
+## Bowtie, Bowtie 2 or BWA #
+############################
+## If the Bowtie, Bowtie 2 or BWA binary is not in your PATH, you can set 
+## this value to tell the program where to find your chosen aligner.  Uncomment 
+## the relevant line below and set the appropriate location.  Please note, 
+## this path should INCLUDE the executable filename.
+
+#BOWTIE	/usr/local/bin/bowtie/bowtie
+#BOWTIE2 /usr/local/bowtie2/bowtie2
+#BWA /usr/local/bwa/bwa
+
+
+
+############################################
+## Bismark (for bisulfite sequencing only) #
+############################################
+## If the Bismark binary is not in your PATH then you can set this value to 
+## tell the program where to find it.  Uncomment the line below and set the 
+## appropriate location. Please note, this path should INCLUDE the executable 
+## filename.
+
+#BISMARK	/usr/local/bin/bismark/bismark
+
+
+
+############
+## Threads #
+############
+## Genome aligners can be made to run across multiple CPU cores to speed up 
+## searches.  Set this value to the number of cores you want for mapping reads.
+
+THREADS		32
+
+
+
+##############
+## DATABASES #
+##############
+## This section enables you to configure multiple genomes databases (aligner index 
+## files) to search against in your screen.  For each genome you need to provide a 
+## database name (which can't contain spaces) and the location of the aligner index 
+## files.
+##
+## The path to the index files SHOULD INCLUDE THE BASENAME of the index, e.g:
+## /data/public/Genomes/Human_Bowtie/GRCh37/Homo_sapiens.GRCh37
+## Thus, the index files (Homo_sapiens.GRCh37.1.bt2, Homo_sapiens.GRCh37.2.bt2, etc.) 
+## are found in a folder named 'GRCh37'.
+##
+## If, for example, the Bowtie, Bowtie2 and BWA indices of a given genome reside in 
+## the SAME FOLDER, a SINLGE path may be provided to ALL the of indices.  The index 
+## used will be the one compatible with the chosen aligner (as specified using the 
+## --aligner flag).  
+##
+## The entries shown below are only suggested examples, you can add as many DATABASE 
+## sections as required, and you can comment out or remove as many of the existing 
+## entries as desired.  We suggest including genomes and sequences that may be sources 
+## of contamination either because they where run on your sequencer previously, or may 
+## have contaminated your sample during the library preparation step.
+##
+## Human - sequences available from
+## ftp://ftp.ensembl.org/pub/current/fasta/homo_sapiens/dna/
+#DATABASE	Human	/data/public/Genomes/Human_Bowtie/GRCh37/Homo_sapiens.GRCh37
+##
+## Mouse - sequence available from
+## ftp://ftp.ensembl.org/pub/current/fasta/mus_musculus/dna/
+#DATABASE	Mouse	/data/public/Genomes/Mouse/NCBIM37/Mus_musculus.NCBIM37
+##
+## Ecoli- sequence available from EMBL accession U00096.2
+#DATABASE	Ecoli	/data/public/Genomes/Ecoli/Ecoli
+##
+## PhiX - sequence available from Refseq accession NC_001422.1
+#DATABASE	PhiX	/data/public/Genomes/PhiX/phi_plus_SNPs
+##
+## Adapters - sequence derived from the FastQC contaminats file found at: www.bioinformatics.babraham.ac.uk/projects/fastqc
+#DATABASE	Adapters	/data/public/Genomes/Contaminants/Contaminants
+##
+## Vector - Sequence taken from the UniVec database
+## http://www.ncbi.nlm.nih.gov/VecScreen/UniVec.html
+#DATABASE	Vectors		/data/public/Genomes/Vectors/Vectors
+
+DATABASE	Human	/cromwell_root/tmp/fastq_screen_reference/genome
+DATABASE	Mouse	/cromwell_root/tmp/fastq_screen_reference/mouse
+DATABASE	ERCC	/cromwell_root/tmp/fastq_screen_reference/ERCC
+DATABASE	EColi	/cromwell_root/tmp/fastq_screen_reference/ecoli
+DATABASE	Adapter	/cromwell_root/tmp/fastq_screen_reference/adapters
+DATABASE	Vector	/cromwell_root/tmp/fastq_screen_reference/vector
+DATABASE	rRNA	/cromwell_root/tmp/fastq_screen_reference/rRNARef
+DATABASE	Virus	/cromwell_root/tmp/fastq_screen_reference/viral
+DATABASE	Yeast	/cromwell_root/tmp/fastq_screen_reference/GCF_000146045.2_R64_genomic_modify
+DATABASE	Mitoch	/cromwell_root/tmp/fastq_screen_reference/Human_mitoch
+DATABASE	Phix	/cromwell_root/tmp/fastq_screen_reference/phix

defaults

@@ -0,0 +1,5 @@
+{   
+    "count_docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/count:v1.0",
+    "count_cluster": "OnDemand bcs.a2.large img-ubuntu-vpc",
+    "count_length": "150"
+    }

inputs

@@ -0,0 +1,8 @@
+{
+	"{{ project_name }}.sample_id": "{{ sample_id }}",
+	"{{ project_name }}.gtf": "{{ gtf }}",
+	"{{ project_name }}.count_docker": "{{ count_docker }}",
+	"{{ project_name }}.count_cluster": "{{ count_cluster }}",
+	"{{ project_name }}.count_length": "{{ count_length }}"
+	"{{ project_name }}.disk_size": "{{ disk_size if disk_size != '' else 200}}"
+	}

tasks/count.wdl

@@ -0,0 +1,26 @@
+task count {
+    File gtf
+    String sample_id
+    String docker
+    String cluster
+    String disk_size
+    Int count_length
+
+    command <<<
+      mkdir -p /cromwell_root/tmp/ballgown/${sample_id}
+      cp -r ${gtf} /cromwell_root/tmp/ballgown/${sample_id}
+      count -i /cromwell_root/tmp/ballgown -l ${count_length} -g ${sample_id}_gene_count_matrix.csv -t ${sample_id}_transcript_count_matrix.csv
+    >>>
+    
+    runtime {
+      docker: docker
+      cluster: cluster
+      systemDisk: "cloud_ssd 40"
+      dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+    
+    output {
+      File mat_expression_genecount = "${sample_id}_gene_count_matrix.csv"
+      File mat_expression_transcriptcount = "${sample_id}_transcript_count_matrix.csv"
+    }
+}

workflow.wdl

@@ -0,0 +1,19 @@
+import "./tasks/count.wdl" as count
+
+workflow {{ project_name }} {
+	File gtf
+	Int count_length
+	String disk_size
+	String count_docker
+	String count_cluster
+
+	call count.count as count {
+		input: 
+		sample_id = sample_id,
+		docker = count_docker,
+		cluster = count_cluster,
+		gtf = gtf,
+		disk_size = disk_size,
+		count_length = count_length
+	} 
+}