first commit

README.md

@@ -0,0 +1,64 @@
+# BWA_DeepVariant
+
+![deepvariatn workflow](./picture/Screen Shot 2019-06-11 at 10.09.27 AM.png)
+
+DeepVariant was trained on 8 whole genome replicates of NA12878 sequenced under a variety of conditions related to library preparation. These conditions include loading concentration, library size selection, and laboratory technician. Then the trained model can be generalized to a variety of new datasets and call variants.
+
+Docker uploaded to Alibaba Cloud is downloaded from [dockerhub](<https://hub.docker.com/r/dajunluo/deepvariant>) (version r0.8.0).
+
+WGS training datasets v0.8 include 12 HG001 PCR-free, 2 HG005 PCR-free, 4 HG001 PCR+. Sequencing platforms are all Illumina Hiseq. For Illumina Novaseq, BGISEQ-500 and BGISEQ-2000, we probably need to train customized small variants callers, more information can be found in [Github](<https://github.com/google/deepvariant/blob/r0.8/docs/deepvariant-tpu-training-case-study.md>). 
+
+[CUSTOMIZED MODELS TO BE ADDED]
+
+DeepVariant pipeline consist of 3 steps:
+
+1. `make_examples` consumes reads and the refernece genome to create TensorFlow examples for evaluation with deep learning models. 
+2. `call_variants`  (Multiple-threads) consums TFRecord files of tf.Examples protos created by `make_examples` and a deep learning model checkpoint and evaluates the model on each example in the TFRecord. The output here is a TFRecord of CallVariantOutput protos. Multiple-threads
+3. `postprocess_variants` (Single-thread) reads all of the output TFRecord files from `call_variants`, it needs to see all of the outputs from `call_variants`for a single sample to merge into a final VCF. 
+
+
+
+**Some tips for DeepVariant:**
+
+1. Duplicate marking may be performed, there is almost no difference inaccuracy except lower (<20x) coverages.
+2. Authors recommend that you do not perform BQSR. Running BQSR has a small decrease on accuracy.
+3. It is not necessary to do any form of indel realignment, though there is not a difference in DeepVariant accuracy either way.
+
+
+You can run with one common using the `run_deepvariant.py` script
+
+```bash
+python run_deepvariant.py --model_type=WGS \
+--ref=../../data/"${REFERENCE_FILE}" \
+--reads=../../data/"${BAM_FILE}" \
+--regions "chr20:10,000,000-10,010,000" \
+--output_vcf=../output/output.vcf.gz \
+--output_gvcf=../output/output.g.vcf.gz
+```
+
+Four files are generated
+
+```bash
+output.vcf.gz
+output.vcf.gz.tbi
+output.g.vcf.gz
+output.g.vcf.gz.tbi
+```
+
+
+
+Command used in choppy app
+
+```bas
+python run_deepvariant.py --model_type=WGS \
+--ref=${ref_dir}/${fasta} \
+--reads=${Dedup.bam} \
+--output_vcf=${sample}_DP.vcf.gz
+```
+
+**Reference:**
+
+1. DeepVariant Github <https://github.com/google/deepvariant>
+
+2. DeepVariant paper  <https://www.nature.com/articles/nbt.4235>
+

defaults

@@ -0,0 +1,11 @@
+{
+  "Dedup_bam": "{{ Dedup_bam }}",
+  "fasta": "GRCh38.d1.vd1.fa",
+  "model_type": "WGS",
+  "disk_size": "500",
+  "DPdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/deepvariant:latest",
+  "cluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
+  "Dedup_bam_index": "{{ Dedup_bam_index }}",
+  "sample": "{{ sample }}",
+  "ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/"
+}

inputs

@@ -0,0 +1,11 @@
+{
+  "{{ project_name }}.Dedup_bam": "{{ Dedup_bam }}",
+  "{{ project_name }}.fasta": "{{ fasta }}",
+  "{{ project_name }}.model_type": "{{ model_type }}",
+  "{{ project_name }}.disk_size": "{{ disk_size }}",
+  "{{ project_name }}.DPdocker": "{{ DPdocker }}",
+  "{{ project_name }}.cluster_config": "{{ cluster_config }}",
+  "{{ project_name }}.Dedup_bam_index": "{{ Dedup_bam_index }}",
+  "{{ project_name }}.sample": "{{ sample }}",
+  "{{ project_name }}.ref_dir": "{{ ref_dir }}"
+}

tasks/Deepvariant.wdl

@@ -0,0 +1,36 @@
+task Deepvariant {
+
+    File ref_dir
+	String fasta
+
+	File Dedup_bam
+	File Dedup_bam_index
+	String sample
+	String model_type
+	String DPdocker
+	String cluster_config
+	String disk_size
+
+	command <<<
+		set -o pipefail
+		set -e	
+		nt=$(nproc)
+		python /opt/deepvariant/bin/run_deepvariant.py --model_type=${model_type} \
+		--ref=${ref_dir}/${fasta} \
+		--reads=${Dedup_bam} \
+		--num_shards=$nt \
+		--call_variants_extra_args="use_openvino=true" \
+		--output_vcf=${sample}_DP.vcf.gz
+	>>>
+
+	runtime {
+		docker:DPdocker
+    	cluster: cluster_config
+    	systemDisk: "cloud_ssd 40"
+    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+	output {
+		File vcf = "${sample}_DP.vcf.gz"
+		File vcf_index = "${sample}_DP.vcf.gz.tbi"
+	}
+}

workflow.wdl

@@ -0,0 +1,29 @@
+import "./tasks/Deepvariant.wdl" as Deepvariant
+
+
+workflow {{ project_name }} {
+    File ref_dir
+	String fasta
+
+	File Dedup_bam
+	File Dedup_bam_index
+	String model_type
+	String sample
+	String DPdocker
+	String cluster_config
+	String disk_size
+
+	call Deepvariant.Deepvariant as Deepvariant {
+		input:
+		fasta=fasta,
+		ref_dir=ref_dir,
+		Dedup_bam=Dedup_bam,
+		model_type=model_type,
+		Dedup_bam_index=Dedup_bam_index,
+		sample=sample,
+		DPdocker=DPdocker,
+		cluster_config=cluster_config,
+		disk_size=disk_size
+	}
+	}
+