AWSTemplateFormatVersion: 2010-09-09

Description: Setup Batch Job Definitions

Parameters:
  RoleStackName:
    Description: "Stack that deploys roles for genomic workflow"
    Type: String
  JobResultsBucket:
    Description: "Bucket that holds workflow job results"
    Type: String
  DefaultSampleName:
    Description: "A default sample name for parameters"
    Type: String
    Default: "NA12878"

Resources:
  IsaacJobDefinition:
    Type: AWS::Batch::JobDefinition
    Properties:
      JobDefinitionName: "Isaac"
      Type: container
      RetryStrategy:
        Attempts: 1
      Parameters:
        BAMS3FolderPath: !Sub "s3://${JobResultsBucket}/${DefaultSampleName}/bam"
        FastQ1S3Path: "s3://aws-batch-genomics-shared/secondary-analysis/example-files/fastq/SRR1919605_1.fastq.gz"
        FastQ2S3Path: "s3://aws-batch-genomics-shared/secondary-analysis/example-files/fastq/SRR1919605_2.fastq.gz"
        ReferenceS3Path: "s3://aws-batch-genomics-shared/secondary-analysis/reference/isaac/"
        WorkingDir: "/scratch"
      ContainerProperties:
        Image: !Sub "${AWS::AccountId}.dkr.ecr.us-east-1.amazonaws.com/isaac"
        Vcpus: 32
        Memory: 80000
        JobRoleArn:
          Fn::ImportValue: !Sub "${RoleStackName}:ECSTaskRole"
        Command:
          - "--bam_s3_folder_path"
          - "Ref::BAMS3FolderPath"
          - "--fastq1_s3_path"
          - "Ref::FastQ1S3Path"
          - "--fastq2_s3_path"
          - "Ref::FastQ2S3Path"
          - "--reference_s3_path"
          - "Ref::ReferenceS3Path"
          - "--working_dir"
          - "Ref::WorkingDir"
        MountPoints:
          - ContainerPath: "/scratch"
            ReadOnly: false
            SourceVolume: docker_scratch
        Volumes:
          - Name: docker_scratch
            Host:
              SourcePath: "/docker_scratch"

  StrelkaJobDefinition:
    Type: AWS::Batch::JobDefinition
    Properties:
      JobDefinitionName: "Strelka"
      Type: container
      RetryStrategy:
        Attempts: 1
      Parameters:
        BAMS3Path: !Sub "s3://${JobResultsBucket}/${DefaultSampleName}/bam/sorted.bam"
        BAIS3Path: !Sub "s3://${JobResultsBucket}/${DefaultSampleName}/bam/sorted.bam.bai"
        ReferenceS3Path: "s3://aws-batch-genomics-shared/secondary-analysis/reference/hg38.fa"
        ReferenceIndexS3Path: "s3://aws-batch-genomics-shared/secondary-analysis/reference/hg38.fa.fai"
        VCFS3Path: !Sub "s3://${JobResultsBucket}/${DefaultSampleName}/vcf"
        WorkingDir: "/scratch"
      ContainerProperties:
        Image: !Sub "${AWS::AccountId}.dkr.ecr.us-east-1.amazonaws.com/strelka"
        Vcpus: 32
        Memory: 32000
        JobRoleArn:
          Fn::ImportValue: !Sub "${RoleStackName}:ECSTaskRole"
        Command:
          - "--bam_s3_path"
          - "Ref::BAMS3Path"
          - "--bai_s3_path"
          - "Ref::BAIS3Path"
          - "--reference_s3_path"
          - "Ref::ReferenceS3Path"
          - "--reference_index_s3_path"
          - "Ref::ReferenceIndexS3Path"
          - "--vcf_s3_path"
          - "Ref::VCFS3Path"
          - "--working_dir"
          - "Ref::WorkingDir"
        MountPoints:
          - ContainerPath: "/scratch"
            ReadOnly: false
            SourceVolume: docker_scratch
        Volumes:
          - Name: docker_scratch
            Host:
              SourcePath: "/docker_scratch"

  SnpEffJobDefinition:
    Type: AWS::Batch::JobDefinition
    Properties:
      JobDefinitionName: "SNPEff"
      Type: container
      RetryStrategy:
        Attempts: 1
      Parameters:
        VCFS3Path: !Sub "s3://${JobResultsBucket}/${DefaultSampleName}/vcf/variants/genome.vcf.gz"
        AnnotatedVCFS3Path: !Sub "s3://${JobResultsBucket}/${DefaultSampleName}/vcf/genome.anno.vcf"
        CommandArgs: " -t hg38 "
        WorkingDir: "/scratch"
      ContainerProperties:
        Image: !Sub "${AWS::AccountId}.dkr.ecr.us-east-1.amazonaws.com/snpeff"
        Vcpus: 4
        Memory: 10000
        JobRoleArn:
          Fn::ImportValue: !Sub "${RoleStackName}:ECSTaskRole"
        Command:
          - "--annotated_vcf_s3_path"
          - "Ref::AnnotatedVCFS3Path"
          - "--vcf_s3_path"
          - "Ref::VCFS3Path"
          - "--cmd_args"
          - "Ref::CommandArgs"
          - "--working_dir"
          - "Ref::WorkingDir"
        MountPoints:
          - ContainerPath: "/scratch"
            ReadOnly: false
            SourceVolume: docker_scratch
        Volumes:
          - Name: docker_scratch
            Host:
              SourcePath: "/docker_scratch"

  SamtoolsStatsJobDefinition:
    Type: AWS::Batch::JobDefinition
    Properties:
      JobDefinitionName: "SamtoolsStats"
      Type: container
      RetryStrategy:
        Attempts: 1
      Parameters:
        ReferenceS3Path: "s3://aws-batch-genomics-shared/secondary-analysis/reference/hg38.fa"
        BAMS3Path: !Sub "s3://${JobResultsBucket}/${DefaultSampleName}/bam/sorted.bam"
        BAMStatsS3Path: !Sub "s3://${JobResultsBucket}/${DefaultSampleName}/bam/sorted.bam.stats"
        WorkingDir: "/scratch"
      ContainerProperties:
        Image: !Sub "${AWS::AccountId}.dkr.ecr.us-east-1.amazonaws.com/samtools-stats"
        Vcpus: 4
        Memory: 40000
        JobRoleArn:
          Fn::ImportValue: !Sub "${RoleStackName}:ECSTaskRole"
        Command:
          - "--bam_s3_path"
          - "Ref::BAMS3Path"
          - "--bam_stats_s3_path"
          - "Ref::BAMStatsS3Path"
          - "--reference_s3_path"
          - "Ref::ReferenceS3Path"
          - "--working_dir"
          - "Ref::WorkingDir"
        MountPoints:
          - ContainerPath: "/scratch"
            ReadOnly: false
            SourceVolume: docker_scratch
        Volumes:
          - Name: docker_scratch
            Host:
              SourcePath: "/docker_scratch"