Add StableLift - sSNV (#239)

* Add StableLift as submodule * Add StableLift module * Update template to support stablelift * Allow StableLift as selectable pipeline * Update methods to handle StableLiftsSNV * Update StableLift name to StableLiftsSNV * Update name to StableLiftsSNV * Add StableLiftsSNV to pipeline selector * Update params to input StableLift rf models * Add stablelift version to log * Add calls to stablelift in metapipeline_DNA * Add default.config * Add module to create StableLift YAML * Update type for param * Add mode saving for StableLift * Rename StableLift workflow * Add StableLift process * Add workflow for StableLift * Add renaming to tool name * Simulate param expansion from StableLift for validation * Add exception to remove BCFtools-Intersect output from StableLift * Output additional params needed for Stablelift * Update params in Stablelift process * Add placeholder NFTest case * Update batch test to include StableLift * Update CHANGELOG * Remove release date from unreleased section * Remove commented code
uclahs-cds · Jan 28, 2025 · 668815f · 668815f
1 parent 16035db
commit 668815f
Show file tree

Hide file tree

Showing 17 changed files with 414 additions and 7 deletions.
diff --git a/.gitmodules b/.gitmodules
@@ -64,3 +64,6 @@
 [submodule "external/pipeline-call-SRC"]
 	path = external/pipeline-call-SRC
 	url = [email protected]:uclahs-cds/pipeline-call-SRC.git
+[submodule "external/pipeline-StableLift"]
+	path = external/pipeline-StableLift
+	url = [email protected]:uclahs-cds/pipeline-StableLift.git
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -6,6 +6,12 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Added
+
+- StableLift for sSNV liftover
+
 ## [6.2.0] - 2024-11-22
 
 ### Changed

diff --git a/config/custom_schema_types.config b/config/custom_schema_types.config
@@ -11,6 +11,21 @@ custom_schema_types {
         'CRAM'
     ]
 
+    expected_stablelift_types = [
+        'GRCh37ToGRCh38',
+        'GRCh38ToGRCh37'
+    ]
+
+    expected_stablelift_models = [
+        'HaplotypeCaller',
+        'Muse2',
+        'Mutect2',
+        'SomaticSniper',
+        'Strelka2',
+        'Delly2-gSV',
+        'Delly2-sSV'
+    ]
+
     /**
     * Check that input types are in allowed list
     */
@@ -117,12 +132,28 @@ custom_schema_types {
         }
     }
 
+    /**
+    * Check proper readable models were given for StableLift
+    */
+    check_stablelift_models = { Map options, String name, Map properties ->
+        custom_schema_types.check_if_namespace(options[name], name)
+
+        for (expected_type in custom_schema_types.expected_stablelift_types) {
+            assert options[name].containsKey(expected_type) : "`${expected_type}` must be included in the StableLift models param: `${name}`"
+            for (expected_model in custom_schema_types.expected_stablelift_models) {
+                assert options[name][expected_type].containsKey(expected_model) : "Model must be provided for `${expected_model}` for type `${expected_type}`"
+                schema.check_path(options[name][expected_type][expected_model] as String, 'r')
+            }
+        }
+    }
+
     types = [
         'InputNamespace': custom_schema_types.check_input_namespace,
         'PatientNamespace': custom_schema_types.check_patient_namespace,
         'SampleNamespace': custom_schema_types.check_sample_namespace,
         'EntryList': custom_schema_types.check_entry_list,
         'LaneType': custom_schema_types.check_lane_type,
-        'EmailAddress': custom_schema_types.check_email_address
+        'EmailAddress': custom_schema_types.check_email_address,
+        'StableLiftModels': custom_schema_types.check_stablelift_models
     ]
 }
diff --git a/config/default.config b/config/default.config
@@ -16,6 +16,33 @@ params {
     src_snv_tool = 'BCFtools-Intersect'
     src_cna_tool = 'Battenberg'
 
+    // StableLift model definition
+    test_base = "/hot/project/method/AlgorithmEvaluation/BNCH-000142-GRCh37v38/publish"
+    model_37_38 = "${test_base}/model/GRCh37-to-GRCh38/RF-model_GRCh37-to-GRCh38"
+    model_38_37 = "${test_base}/model/GRCh38-to-GRCh37/RF-model_GRCh38-to-GRCh37"
+
+    stablelift_models = [
+        GRCh37ToGRCh38: [
+            HaplotypeCaller: "${model_37_38}_gSNP_HaplotypeCaller.Rds",
+            Muse2:           "${model_37_38}_sSNV_Muse2.Rds",
+            Mutect2:         "${model_37_38}_sSNV_Mutect2.Rds",
+            SomaticSniper:   "${model_37_38}_sSNV_SomaticSniper.Rds",
+            Strelka2:        "${model_37_38}_sSNV_Strelka2.Rds",
+            "Delly2-gSV":    "${model_37_38}_gSV_Delly2-gSV.Rds",
+            "Delly2-sSV":    "${model_37_38}_sSV_Delly2-sSV.Rds"
+        ],
+        GRCh38ToGRCh37: [
+            HaplotypeCaller: "${model_38_37}_gSNP_HaplotypeCaller.Rds",
+            Muse2:           "${model_38_37}_sSNV_Muse2.Rds",
+            Mutect2:         "${model_38_37}_sSNV_Mutect2.Rds",
+            SomaticSniper:   "${model_38_37}_sSNV_SomaticSniper.Rds",
+            Strelka2:        "${model_38_37}_sSNV_Strelka2.Rds",
+            "Delly2-gSV":    "${model_38_37}_gSV_Delly2-gSV.Rds",
+            "Delly2-sSV":    "${model_38_37}_sSV_Delly2-sSV.Rds"
+        ]
+    ]
+
+
     // TO-DO: Support option below to run call-SRC on all combinations of sSNV tools and sCNA tools
     src_run_all_combinations = false
 

diff --git a/config/methods.config b/config/methods.config
@@ -4,6 +4,8 @@ includeConfig "${projectDir}/external/pipeline-Nextflow-config/config/methods/co
 includeConfig "${projectDir}/config/pipeline_selector.config"
 includeConfig "${projectDir}/config/input_handler.config"
 
+import nextflow.Nextflow
+
 def get_submodule_version(submodule) {
     def manifest_locations = [new File("${projectDir}/external/${submodule}/nextflow.config"), new File("${projectDir}/external/${submodule}/pipeline/nextflow.config")]
     def submodule_manifest = null
@@ -206,6 +208,7 @@ methods {
         params.version_call_sCNA        = get_submodule_version('pipeline-call-sCNA')
         params.version_generate_SQC_BAM = get_submodule_version('pipeline-generate-SQC-BAM')
         params.version_call_SRC         = get_submodule_version('pipeline-call-SRC')
+        params.version_StableLift       = get_submodule_version('pipeline-StableLift')
         }
 
     set_env = {
@@ -264,7 +267,8 @@ methods {
             'pipeline-call-sCNA': ['dataset_id', 'patient_id', 'sample_id', 'output_dir', 'input'],
             'pipeline-generate-SQC-BAM': ['dataset_id', 'patient_id', 'sample_id', 'output_dir', 'input'],
             'pipeline-calculate-targeted-coverage': ['dataset_id', 'patient_id', 'sample_id', 'output_dir', 'input'],
-            'pipeline-call-SRC': ['dataset_id', 'patient_id', 'sample_id', 'output_dir', 'input']
+            'pipeline-call-SRC': ['dataset_id', 'patient_id', 'sample_id', 'output_dir', 'input'],
+            'pipeline-StableLift': ['sample_id', 'output_dir', 'input', 'rf_model', 'variant_caller']
         ]
 
         pipeline_param_exclusion.each { pipeline, to_exclude ->
@@ -305,7 +309,21 @@ methods {
     generate_pipeline_arg_strings = {
         def params_exclude_from_all = ['output_dir', 'input_csv', 'work_dir', 'sample_id', 'patient_id', 'dataset_id', 'input']
         def specific_params_to_exclude = [
-            'call_sSNV': ['algorithm']
+            'call_sSNV': ['algorithm'],
+            'StableLift': [
+                'src_fasta_id',
+                'src_fasta_ref',
+                'src_fasta_fai',
+                'src_fasta_dict',
+                'dest_fasta_id',
+                'dest_fasta_ref',
+                'dest_fasta_fai',
+                'dest_fasta_dict',
+                'chain_file',
+                'repeat_bed',
+                'header_contigs',
+                'gnomad_rds'
+            ]
         ]
         def specific_params_allowed_empty = [
             'calculate_targeted_coverage': ['bait_bed', 'target_interval_list', 'bait_interval_list']
@@ -344,6 +362,67 @@ methods {
         schema.validate_specific(pipeline_params_schema, params, []);
     }
 
+    expand_stablelift_params = {
+        // Make sure the user didn't set any of the advanced parameters
+        def advanced_parameters = [
+            'src_fasta_id',
+            'src_fasta_ref',
+            'src_fasta_fai',
+            'src_fasta_dict',
+            'dest_fasta_id',
+            'dest_fasta_ref',
+            'dest_fasta_fai',
+            'dest_fasta_dict',
+            'chain_file',
+            'repeat_bed',
+            'header_contigs',
+            'gnomad_rds'
+        ]
+
+        for (key in advanced_parameters) {
+            if (params.pipeline_params["StableLift"].containsKey(key)) {
+                throw new Exception("Do not directly set params.${key} - the value will be inferred from params.liftover_direction")
+            }
+        }
+
+        def liftover_direction  = params.pipeline_params["StableLift"].getOrDefault('liftover_direction', null)
+
+        def forward  = "GRCh37ToGRCh38"
+        def backward = "GRCh38ToGRCh37"
+
+        if (liftover_direction in [forward, backward]) {
+            if (liftover_direction == forward) {
+                params.pipeline_params["StableLift"].src_fasta_id = 'GRCh37'
+                params.pipeline_params["StableLift"].src_fasta_ref = params.pipeline_params["StableLift"].fasta_ref_37
+
+                params.pipeline_params["StableLift"].dest_fasta_id = 'GRCh38'
+                params.pipeline_params["StableLift"].dest_fasta_ref = params.pipeline_params["StableLift"].fasta_ref_38
+
+                params.pipeline_params["StableLift"].chain_file = params.pipeline_params["StableLift"].resource_bundle_path + "/hg19ToHg38.over.chain"
+                params.pipeline_params["StableLift"].repeat_bed = params.pipeline_params["StableLift"].resource_bundle_path + "/GRCh38_RepeatMasker-intervals.bed"
+                params.pipeline_params["StableLift"].header_contigs = params.pipeline_params["StableLift"].resource_bundle_path + "/GRCh38_VCF-header-contigs.txt"
+            } else {
+                params.pipeline_params["StableLift"].src_fasta_id = 'GRCh38'
+                params.pipeline_params["StableLift"].src_fasta_ref = params.pipeline_params["StableLift"].fasta_ref_38
+
+                params.pipeline_params["StableLift"].dest_fasta_id = 'GRCh37'
+                params.pipeline_params["StableLift"].dest_fasta_ref = params.pipeline_params["StableLift"].fasta_ref_37
+
+                params.pipeline_params["StableLift"].chain_file = params.pipeline_params["StableLift"].resource_bundle_path + "/hg38ToHg19.over.chain"
+                params.pipeline_params["StableLift"].repeat_bed = params.pipeline_params["StableLift"].resource_bundle_path + "/GRCh37_RepeatMasker-intervals.bed"
+                params.pipeline_params["StableLift"].header_contigs = params.pipeline_params["StableLift"].resource_bundle_path + "/GRCh37_VCF-header-contigs.txt"
+            }
+
+            params.pipeline_params["StableLift"].src_fasta_fai = params.pipeline_params["StableLift"].src_fasta_ref + ".fai"
+            params.pipeline_params["StableLift"].dest_fasta_fai = params.pipeline_params["StableLift"].dest_fasta_ref + ".fai"
+
+            params.pipeline_params["StableLift"].src_fasta_dict = Nextflow.file(params.pipeline_params["StableLift"].src_fasta_ref).resolveSibling(Nextflow.file(params.pipeline_params["StableLift"].src_fasta_ref).getBaseName() + '.dict').toString()
+            params.pipeline_params["StableLift"].dest_fasta_dict = Nextflow.file(params.pipeline_params["StableLift"].dest_fasta_ref).resolveSibling(Nextflow.file(params.pipeline_params["StableLift"].dest_fasta_ref).getBaseName() + '.dict').toString()
+
+            params.pipeline_params["StableLift"].gnomad_rds = params.pipeline_params["StableLift"].resource_bundle_path + "/gnomad.v4.0.sv.Rds"
+        }
+    }
+
     set_up = {
         input_handler.convert_csv_inputs()
         schema.load_custom_types("${projectDir}/config/custom_schema_types.config")
@@ -355,6 +434,9 @@ methods {
         methods.set_submodule_versions()
         methods.set_env()
         pipeline_selector.handle_pipeline_selection()
+        if (params.pipeline_params["StableLift"].is_pipeline_enabled) {
+            methods.expand_stablelift_params()
+        }
         methods.generate_pipeline_interval_params()
         methods.set_pipeline_cpus()
         methods.generate_pipeline_arg_strings()

diff --git a/config/pipeline_selector.config b/config/pipeline_selector.config
@@ -25,7 +25,8 @@ pipeline_selector {
             'call-gSV': ['recalibrate-BAM'],
             'call-sSV': ['recalibrate-BAM'],
             'call-sCNA': ['recalibrate-BAM'],
-            'call-SRC': ['call-sSNV', 'call-sCNA']
+            'call-SRC': ['call-sSNV', 'call-sCNA'],
+            'StableLiftsSNV': ['call-sSNV']
             ]
 
         if (input_type == 'BAM') {
@@ -135,7 +136,8 @@ pipeline_selector {
             'call_gSV': 'call-gSV',
             'call_sSV': 'call-sSV',
             'call_sCNA': 'call-sCNA',
-            'call_SRC': 'call-SRC'
+            'call_SRC': 'call-SRC',
+            'StableLift': 'StableLiftsSNV'
         ];
 
         pipeline_name_map.each { pipeline_key, pipeline ->
@@ -144,6 +146,14 @@ pipeline_selector {
             }
 
             params.pipeline_params[pipeline_key].is_pipeline_enabled = pipelines.contains(pipeline);
+
+            if (pipeline_key == 'StableLift' && pipelines.contains(pipeline)) {
+                if (!params.pipeline_params[pipeline_key].containsKey('lift_modes')) {
+                    params.pipeline_params[pipeline_key]['lift_modes'] = []
+                }
+
+                params.pipeline_params[pipeline_key]['lift_modes'] << pipeline
+            }
         }
     }
 

diff --git a/config/schema.yaml b/config/schema.yaml
@@ -125,6 +125,7 @@ requested_pipelines:
     - call-sSV
     - call-sCNA
     - call-SRC
+    - StableLiftsSNV
   help: 'List of pipelines to run'
 override_realignment:
   type: 'Bool'
@@ -171,6 +172,10 @@ global_job_submission_sbatch:
   required: true
   allow_empty: true
   help: 'Sbatch command for submitting metapipeline job'
+stablelift_models:
+  type: 'StableLiftModels'
+  required: true
+  help: 'Map of paths to StableLift models'
 pipeline_params:
   type: 'Namespace'
   required: true
@@ -220,6 +225,10 @@ pipeline_params:
       type: 'Namespace'
       required: true
       help: 'Parameters for generate-SQC-BAM'
+    StableLift:
+      type: 'Namespace'
+      required: true
+      help: 'Parameters for StableLift'
 input:
   type: 'InputNamespace'
   required: true

diff --git a/config/template.config b/config/template.config
@@ -27,7 +27,7 @@ params {
 
     sample_mode = 'paired' // Choose from: 'single', 'paired', 'multi'
 
-    // Select pipeline(s) to run. Choices: 'align-DNA', 'recalibrate-BAM', 'generate-SQC-BAM', 'calculate-targeted-coverage', 'call-gSNP', 'call-mtSNV', 'call-sSNV', 'call-sSV', 'call-gSV', 'call-sCNA'
+    // Select pipeline(s) to run. Choices: 'align-DNA', 'recalibrate-BAM', 'generate-SQC-BAM', 'calculate-targeted-coverage', 'call-gSNP', 'call-mtSNV', 'call-sSNV', 'call-sSV', 'call-gSV', 'call-sCNA', 'StableLiftsSNV'
     requested_pipelines = ['align-DNA', 'recalibrate-BAM', 'generate-SQC-BAM', 'call-gSNP', 'call-mtSNV', 'call-sSNV', 'call-sSV', 'call-gSV', 'call-sCNA']
 
     // Override conversion to FASTQ and re-alignment with BAM input
@@ -143,6 +143,17 @@ params {
                 ]
             ]
         }
+
+        StableLift {
+            liftover_direction = "GRCh37ToGRCh38"
+
+            stablelift_models = params.stablelift_models
+
+            fasta_ref_37 = "/hot/resource/reference-genome/GRCh37-EBI-hs37d5/hs37d5.fa"
+            fasta_ref_38 = "/hot/resource/reference-genome/GRCh38-BI-20160721/Homo_sapiens_assembly38.fasta"
+            resource_bundle_path = "/hot/project/method/AlgorithmEvaluation/BNCH-000142-GRCh37v38/publish/resource"
+            funcotator_data_source = "/hot/project/method/AlgorithmEvaluation/BNCH-000142-GRCh37v38/publish/resource/funcotator_dataSources.v1.7.20200521s_StableLift"
+        }
     }
 }
 

diff --git a/external/pipeline-StableLift b/external/pipeline-StableLift
diff --git a/main.nf b/main.nf
@@ -45,6 +45,7 @@ log.info """\
         uclahs-cds/pipeline-call-sCNA: ${params.version_call_sCNA}
         uclahs-cds/pipeline-calculate-targeted-coverage: ${params.version_calculate_targeted_coverage}
         uclahs-cds/pipeline-generate-SQC-BAM: ${params.version_generate_SQC_BAM}
+        uclahs-cds/pipeline-StableLift: ${params.version_StableLift}
 
     ------------------------------------
     Starting workflow...

diff --git a/module/StableLift/create_YAML_StableLift.nf b/module/StableLift/create_YAML_StableLift.nf
@@ -0,0 +1,40 @@
+import org.yaml.snakeyaml.Yaml
+import org.yaml.snakeyaml.Yaml
+/*
+* Create input YAML file for the StableLift pipeline.
+*
+* Input:
+*   sample_info: A Map object containing sample information
+*
+* Output:
+*   @return A tuple of 4 items, inlcuding the sample_id and input_yaml and rf model and tool
+*/
+process create_YAML_StableLift {
+    publishDir "${params.output_dir}/intermediate/${task.process.replace(':', '/')}-${params.patient}/${sample_id}",
+        pattern: 'stablelift_input.yaml',
+        mode: 'copy'
+
+    input:
+        val(sample_info)
+
+    output:
+        tuple val(sample_id), path(input_yaml), val(run_model), val(sample_info.tool), emit: stablelift_input
+
+    exec:
+    input_yaml = 'stablelift_input.yaml'
+
+    sample_id = "${sample_info.sample}-${sample_info.tool}" as String
+
+    input_map = [
+        'sample_id': sample_id,
+        'input': [
+            'vcf': sample_info.path
+        ]
+    ]
+
+    Map all_models = params["StableLift"].stablelift_models
+    run_model = all_models[params["StableLift"].liftover_direction][sample_info.tool]
+
+    Yaml yaml = new Yaml()
+    yaml.dump(input_map, new FileWriter("${task.workDir}/${input_yaml}"))
+}
diff --git a/module/StableLift/default.config b/module/StableLift/default.config
@@ -0,0 +1,14 @@
+// EXECUTION SETTINGS AND GLOBAL DEFAULTS
+
+// External config files import. DO NOT MODIFY THESE LINES!
+includeConfig "${projectDir}/config/default.config"
+includeConfig "${projectDir}/config/methods.config"
+includeConfig "${projectDir}/nextflow.config"
+
+// Inputs/parameters of the pipeline
+params {
+
+}
+
+// Setup the pipeline config. DO NOT REMOVE THIS LINE!
+methods.setup()