first commit

README.md

+### APP简介
+
+本app用于从FASTQ文件中随机抽取N条read，生成down-sample后的FASTQ文件。
+
+app仅接受以***.fastq.gz***或***.fq.gz***为结尾的文件，输出文件为GZIP压缩后的FASTQ文件（后缀名为.fastq.gz）
+
+> 注意：
+>
+> 本app使用***seqkit sample***进行downsample，根据官方文件说明，downsample后的FASTQ文件的read数不一定严格等于down_to的目标。如：down_to=1000 时，可能最终获得的fastq中仅有991条read。
+>
+> 对此不能接受者，请不要使用本app。
+
+
+
+### 安装指南
+
+```
+# 激活choppy环境
+source activate choppy-pipe-0.3.8.dev0
+
+# 安装 app
+choppy install chenziyin/downsample
+```
+
+
+
+
+
+### 快速使用
+
+1. 准备样本描述文件：samples.csv
+
+   需要包括3列：
+
+   - sample_id：每个样本唯一的ID
+   - fastq：原始fastq地址
+   - down_to：downsample后目标read数
+
+   样表如下：
+
+   | sample_id | Fastq                                                        | down_to |
+   | --------- | ------------------------------------------------------------ | ------- |
+   | Test1     | oss://choppy-app-example-data/miRNAseq/test_10k_NEXTflex.fastq.gz | 1000    |
+
+   
+
+2. 批量提交任务
+
+```bash
+choppy batch chenziyin/downsample-latest <SAMPLES_CSV> --project-name <PROJECT_NAME> 
+```
+
+
+
+### 使用的软件及版本：
+
+- Seqkit: 0.12.0
+
+
+
+
+
+
+
+
+
+

defaults

+{
+    "cluster_config": "OnDemand ecs.sn1.medium img-ubuntu-vpc",
+    "disk_size": "200"
+}

inputs

+{
+    "{{ project_name }}.sample_id": "{{ sample_id }}",
+    "{{ project_name }}.in_fastq": "{{ fastq }}",
+    "{{ project_name }}.N": "{{ down_to }}",
+    "{{ project_name }}.docker_seqkit": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/seqkit:0.12.0",
+    "{{ project_name }}.cluster_config": "{{ cluster_config }}",
+    "{{ project_name }}.disk_size": "{{ disk_size }}"
+}
+

tasks/DownSample.wdl

+task DownSample {
+    File    in_fastq
+    Int     N
+    String  docker
+    String  cluster_config
+    String  disk_size
+
+    command <<<
+        set -o pipefail
+        set -e
+        out_fastq=$(echo "$(basename ${in_fastq})" | sed "s/.\(fastq\|fq\).gz/_downTo${N}.fastq.gz/")
+        seqkit sample -n ${N} ${in_fastq} -o $out_fastq
+        echo "$out_fastq"
+    >>>
+
+    runtime {
+        docker: docker
+        cluster: cluster_config
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+    output {
+        File out_fastq = sub(basename(in_fastq), "\\.(fastq|fq)\\.gz$", "_downTo${N}.fastq.gz")
+    }
+
+}

workflow.wdl

+import "./tasks/DownSample.wdl" as DownSample
+
+workflow {{ project_name }} {
+    String  sample_id
+    File    in_fastq
+
+    Int     N
+
+    String docker_seqkit
+	String cluster_config
+	String disk_size
+
+    call DownSample.DownSample as DownSample {
+        input:
+            in_fastq=in_fastq, N=N, docker=docker_seqkit, cluster_config=cluster_config, disk_size=disk_size
+    }
+}