first commit

README.md

@@ -0,0 +1,59 @@
+# README.md
+
+> Author: Qingwang Chen
+>
+> Email: [qwch20@fudan.edu.cn](mailto:qwch20@fudan.edu.cn)
+>
+> Last Updates: 24/08/2021
+
+#### Brief Introduction
+
+Collect the individual quantifications and aggregate them in a joint database. The the joint graph is fully quantified and we can move on to use it for downstream analyses, for instance to extract different AS events:
+
+--event-types exon_skip,intron_retention,alt_3prime,alt_5prime,mutex_exons,mult_exon_skip 
+
+#### Requirements
+
+- choppy
+- Ali-Cloud
+- Linux
+
+```
+# 激活choppy环境
+$ source activate choppy (open-choppy-env)
+
+# 第一次安装
+$ choppy install chenqingwang/SplAdder-quantification-merge
+# 非第一次安装
+$ choppy install chenqingwang/SplAdder-quantification-merge -f 
+
+# 查询已安装APP
+$ choppy apps
+```
+
+#### Quick Start
+
+```
+# 准备 samples.csv 文件
+$ choppy samples chenqingwang/SplAdder-quantification-merge-latest > samples.csv
+# 准备无默认参数的samples.csv 文件
+$ choppy samples --no-default chenqingwang/SplAdder-quantification-merge-latest > samples.csv
+
+# 提交任务
+$ choppy batch chenqingwang/SplAdder-quantification-merge-latest samples.csv -p Your_project_name -l Your_label
+
+# 查询任务运行状况
+$ choppy query -L Your_label | grep "status"
+
+# 查询失败任务
+$ choppy search -s Failed -p Your_project_name -u chenqingwang --short-format
+
+# 结果文件地址
+$ oss://choppy-cromwell-result/test-choppy/Your_project_name/
+```
+
+#### Description
+```
+# samples: The file names to be analyzed should be written line by line in this file, and the file should be uploaded to AliCloud.
+
+```

defaults

@@ -0,0 +1,9 @@
+{   
+    "reference_gtf_file":"oss://pgx-reference-data/reference/spladder/SplAdder/data/reference/Homo_sapiens.GRCh38.103.gtf",
+    "bam":"oss://pgx-source-data/CBCGA2020/RNA-seq/intermediate-results-temp/Alternative_Splicing/spladder/tmp_bam/",    
+    "pickle":"oss://pgx-source-data/CBCGA2020/RNA-seq/intermediate-results-temp/Alternative_Splicing/spladder/genes_graph_conf2_sorted_pickle/",
+    "count_hdf5":"oss://pgx-source-data/CBCGA2020/RNA-seq/intermediate-results-temp/Alternative_Splicing/spladder/conf2_count_hdf5/",
+    "spladder_docker":"registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/spladder:v2.4.2",
+    "spladder_cluster":"OnDemand bcs.a2.3xlarge img-ubuntu-vpc",
+    "disk_size":"500"
+    }

inputs

@@ -0,0 +1,12 @@
+{
+	"{{ project_name }}.sample_id": "{{ sample_id }}",
+	"{{ project_name }}.bam": "{{ bam }}",
+	"{{ project_name }}.pickle": "{{ pickle }}",
+	"{{ project_name }}.merge_graphs": "{{ merge_graphs }}",
+	"{{ project_name }}.count_hdf5": "{{ count_hdf5 }}",
+	"{{ project_name }}.reference_gtf_file": "{{ reference_gtf_file }}",
+	"{{ project_name }}.samples": "{{ samples }}",
+	"{{ project_name }}.spladder_docker": "{{ spladder_docker }}",
+	"{{ project_name }}.spladder_cluster": "{{ spladder_cluster }}",
+	"{{ project_name }}.disk_size": "{{ disk_size }}"
+}

tasks/spladder_quantification.wdl

@@ -0,0 +1,71 @@
+task spladder_quantification {
+    String sample_id
+    File bam
+    File pickle
+    File merge_graphs
+    File count_hdf5
+    File reference_gtf_file
+    File samples
+    
+
+    String docker
+    String cluster
+    String disk_size
+
+    
+    command <<<
+        set -o pipefail
+        set -e
+
+        mkdir -p ${sample_id}/spladder_out/spladder
+        
+        ln -s ${bam}/*.bam ./
+        cat ${samples} | while read a; do ls ./ | grep bam$ | grep $a; done > alignment.txt
+       
+        ln -s ${bam}/*.bai ./
+        cat ${samples} | while read a; do ls ./ | grep bai$ | grep $a; done > alignment_bai.txt
+
+        ln -s ${pickle}/*.pickle ${sample_id}/spladder_out/spladder/
+        cat ${samples} | while read a; do ls ${sample_id}/spladder_out/spladder/| grep pickle$| grep $a; done >> pickle.txt
+		
+        cp -r ${merge_graphs} ${sample_id}/spladder_out/spladder/
+
+        ln -s ${count_hdf5}/*.hdf5 ${sample_id}/spladder_out/spladder/
+        cat ${samples} | while read a; do ls ${sample_id}/spladder_out/spladder/| grep hdf5$| grep $a; done >> count_hdf5.txt
+
+
+        nt=$(nproc)
+		
+        spladder build -o ${sample_id}/spladder_out \
+          --annotation ${reference_gtf_file} \
+          --bams alignment.txt \
+          --confidence 2 \
+          --merge-strat merge_graphs \
+          --readlen 150 \
+          --parallel $nt \
+          --quantify-graph --qmode collect \
+          --event-types exon_skip,intron_retention,alt_3prime,alt_5prime,mutex_exons,mult_exon_skip 
+          
+          
+        find . -depth > fileList.txt
+    >>>
+
+    runtime {
+        docker: docker
+        cluster: cluster
+        systemDisk: "cloud_ssd 500"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+
+    output {
+        File fileList = "fileList.txt"
+        File alignment = "alignment.txt"
+        File alignment_bai = "alignment_bai.txt"
+        File pickle_txt = "pickle.txt"
+        File count_hdf5_txt = "count_hdf5.txt"
+        Array[File] AS_gff = glob("${sample_id}/spladder_out/*.gff3")
+        Array[File] AS_gz = glob("${sample_id}/spladder_out/*.gz")
+        Array[File] spladder_out = glob("${sample_id}/spladder_out/*")
+        Array[File] spladder = glob("${sample_id}/spladder_out/spladder/*")
+    }
+}

workflow.wdl

@@ -0,0 +1,30 @@
+import "./tasks/spladder_quantification.wdl" as spladder_quantification
+
+
+workflow {{ project_name }} {
+    String sample_id
+    File bam
+    File pickle
+    File merge_graphs
+    File count_hdf5
+    File reference_gtf_file
+    File samples
+
+    String spladder_docker
+    String spladder_cluster
+    String disk_size	
+
+	call spladder_quantification.spladder_quantification as spladder_quantification {
+		input:
+		reference_gtf_file=reference_gtf_file,
+		sample_id=sample_id,
+		bam=bam,
+		pickle=pickle,
+		merge_graphs=merge_graphs,
+		count_hdf5=count_hdf5,
+		samples=samples,
+		docker=spladder_docker,
+		cluster=spladder_cluster,
+		disk_size=disk_size
+	}
+}