first commit

README.md

@@ -0,0 +1,51 @@
+# README.md
+
+> Author: Qingwang Chen
+>
+> Email: [qwch20@fudan.edu.cn](mailto:qwch20@fudan.edu.cn)
+>
+> Last Updates: 23/08/2021
+
+#### Brief Introduction
+
+For RNA-seq data, from bams to AS Information files.
+
+#### 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-single
+# 非第一次安装
+$ choppy install chenqingwang/spladder-single -f 
+
+# 查询已安装APP
+$ choppy apps
+```
+
+#### Quick Start
+
+```
+# 准备 samples.csv 文件
+$ choppy samples chenqingwang/spladder-single-latest > samples.csv
+# 准备无默认参数的samples.csv 文件
+choppy samples --no-default chenqingwang/spladder-single-latest > samples.csv
+
+# 提交任务
+$ choppy batch chenqingwang/spladder-single-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/
+```

defaults

@@ -0,0 +1,6 @@
+{   
+    "reference_gtf_file":"oss://pgx-reference-data/reference/spladder/SplAdder/data/reference/Homo_sapiens.GRCh38.103.gtf",
+    "spladder_docker":"registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/spladder:v2.4.2",
+    "spladder_cluster":"OnDemand bcs.a2.large img-ubuntu-vpc",
+    "disk_size":"200"
+    }

demo_samples/test_spladder_20210409.csv

@@ -0,0 +1,2 @@
+bam_file,sample_id
+oss://pgx-reference-data/reference/spladder/SplAdder/data/bams/test/Quartet_RNA_ILM_NovaSeq_RiboZero_WUX_D5_1_20200901.downsampled.bam,D5_1_Test

inputs

@@ -0,0 +1,9 @@
+{
+	"{{ project_name }}.sample_id": "{{ sample_id }}",
+	"{{ project_name }}.bam": "{{ bam }}",
+	"{{ project_name }}.bai": "{{ bai }}",
+	"{{ project_name }}.reference_gtf_file": "{{ reference_gtf_file }}",
+	"{{ project_name }}.spladder_docker": "{{ spladder_docker }}",
+	"{{ project_name }}.spladder_cluster": "{{ spladder_cluster }}",
+	"{{ project_name }}.disk_size": "{{ disk_size }}"
+}

tasks/spladder-single.wdl

@@ -0,0 +1,50 @@
+task spladder {
+    String sample_id
+    File bam
+    File bai
+    File reference_gtf_file
+    
+    String docker
+    String cluster
+    String disk_size
+
+
+    
+    command <<<
+        set -o pipefail
+        set -e
+
+        mkdir -p ${sample_id}/spladder_out
+
+        nt=$(nproc)
+
+        spladder build --bams ${bam} \
+                --annotation ${reference_gtf_file} \
+                --ignore-mismatches \
+                --verbose \
+                --confidence 2 \
+                --merge-strat single \
+                --readlen 150 \
+                --no-primary-only \
+                --sparse-bam
+                --parallel $nt \
+                --outdir ${sample_id}/spladder_out
+        
+        find . -depth > fileList.txt
+    >>>
+
+    runtime {
+        docker: docker
+        cluster: cluster
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+
+    output {
+        File fileList = "fileList.txt"
+        Array[File] AS_gff = glob("${sample_id}/spladder_out/*.gff3")
+        Array[File] AS_gz = glob("${sample_id}/spladder_out/*.txt.gz")
+        Array[File] spladder_out = glob("${sample_id}/spladder_out/*")
+        Array[File] spladder = glob("${sample_id}/spladder_out/spladder/*")
+    }
+}

workflow.wdl

@@ -0,0 +1,25 @@
+import "./tasks/spladder-single.wdl" as spladder-single
+
+
+workflow {{ project_name }} {
+    String sample_id
+    File bam
+    File bai
+    File reference_gtf_file
+    
+
+    String spladder_docker
+    String spladder_cluster
+    String disk_size	
+
+	call spladder-single.spladder-single as spladder-single {
+		input:
+		reference_gtf_file=reference_gtf_file,
+		sample_id=sample_id,
+		bam=bam,
+		bai=bai,
+		docker=spladder_docker,
+		cluster=spladder_cluster,
+		disk_size=disk_size
+	}
+}