def dnaseq_to_proteindb(ctx, config_file, input_fasta, translation_table,
num_orfs, num_orfs_complement, output_proteindb,
var_prefix, skip_including_all_cds, include_biotypes,
exclude_biotypes, biotype_str, expression_str,
expression_thresh):
if input_fasta is None:
print_help()
pipeline_arguments = {}
pipeline_arguments[
EnsemblDataService.TRANSLATION_TABLE] = translation_table
pipeline_arguments[EnsemblDataService.PROTEIN_DB_OUTPUT] = output_proteindb
pipeline_arguments[EnsemblDataService.HEADER_VAR_PREFIX] = var_prefix
pipeline_arguments[EnsemblDataService.EXCLUDE_BIOTYPES] = exclude_biotypes
pipeline_arguments[
EnsemblDataService.SKIP_INCLUDING_ALL_CDS] = skip_including_all_cds
pipeline_arguments[EnsemblDataService.INCLUDE_BIOTYPES] = include_biotypes
pipeline_arguments[EnsemblDataService.BIOTYPE_STR] = biotype_str
pipeline_arguments[EnsemblDataService.NUM_ORFS] = num_orfs
pipeline_arguments[
EnsemblDataService.NUM_ORFS_COMPLEMENT] = num_orfs_complement
pipeline_arguments[EnsemblDataService.EXPRESSION_STR] = expression_str
pipeline_arguments[
EnsemblDataService.EXPRESSION_THRESH] = expression_thresh
ensembl_data_service = EnsemblDataService(config_file, pipeline_arguments)
ensembl_data_service.dnaseq_to_proteindb(input_fasta)
def vcf_to_proteindb(ctx, config_file, input_fasta, vcf, gene_annotations_gtf,
translation_table, mito_translation_table, var_prefix,
report_ref_seq, output_proteindb, annotation_field_name,
af_field, af_threshold, transcript_index,
consequence_index, exclude_consequences,
skip_including_all_cds, include_consequences,
ignore_filters, accepted_filters):
if input_fasta is None or vcf is None or gene_annotations_gtf is None:
print_help()
pipeline_arguments = {
EnsemblDataService.MITO_TRANSLATION_TABLE: mito_translation_table,
EnsemblDataService.TRANSLATION_TABLE: translation_table,
EnsemblDataService.HEADER_VAR_PREFIX: var_prefix,
EnsemblDataService.REPORT_REFERENCE_SEQ: report_ref_seq,
EnsemblDataService.PROTEIN_DB_OUTPUT: output_proteindb,
EnsemblDataService.ANNOTATION_FIELD_NAME: annotation_field_name,
EnsemblDataService.AF_FIELD: af_field,
EnsemblDataService.AF_THRESHOLD: af_threshold,
EnsemblDataService.TRANSCRIPT_INDEX: transcript_index,
EnsemblDataService.CONSEQUENCE_INDEX: consequence_index,
EnsemblDataService.EXCLUDE_CONSEQUENCES: exclude_consequences,
EnsemblDataService.SKIP_INCLUDING_ALL_CDS: skip_including_all_cds,
EnsemblDataService.INCLUDE_CONSEQUENCES: include_consequences,
EnsemblDataService.IGNORE_FILTERS: ignore_filters,
EnsemblDataService.ACCEPTED_FILTERS: accepted_filters
}
ensembl_data_service = EnsemblDataService(config_file, pipeline_arguments)
ensembl_data_service.vcf_to_proteindb(vcf, input_fasta,
gene_annotations_gtf)
def ensembl_check(ctx, config_file, input_fasta, output, add_stop_codons, num_aa):
if input_fasta is None:
print_help()
pipeline_arguments = {EnsemblDataService.PROTEIN_DB_OUTPUT: output}
ensembl_data_service = EnsemblDataService(config_file, pipeline_arguments)
ensembl_data_service.check_proteindb(input_fasta, add_stop_codons, num_aa)
def threeframe_translation(ctx, config_file, input_fasta, translation_table, output):
if input_fasta is None:
print_help()
pipeline_arguments = {EnsemblDataService.TRANSLATION_TABLE: translation_table,
EnsemblDataService.PROTEIN_DB_OUTPUT: output}
ensembl_data_service = EnsemblDataService(config_file, pipeline_arguments)
ensembl_data_service.three_frame_translation(input_fasta)
def cosmic_to_proteindb(ctx, config_file, input_mutation, input_genes, output_db, tissue_type, split_by_tissue_type):
if input_mutation is None or input_genes is None or output_db is None:
print_help()
pipeline_arguments = {CancerGenomesService.CONFIG_CANCER_GENOMES_MUTATION_FILE: input_mutation,
CancerGenomesService.CONFIG_COMPLETE_GENES_FILE: input_genes,
CancerGenomesService.CONFIG_OUTPUT_FILE: output_db,
CancerGenomesService.TISSUE_TYPE: tissue_type,
CancerGenomesService.SPLIT_BY_TISSUE_TYPE: split_by_tissue_type}
cosmic_to_proteindb_service = CancerGenomesService(config_file, pipeline_arguments)
cosmic_to_proteindb_service.cosmic_to_proteindb()
def cosmic_to_proteindb(ctx, config_file, input_mutation, input_genes,
output_db, filter_column, accepted_values,
split_by_filter_column):
if input_mutation is None or input_genes is None or output_db is None:
print_help()
pipeline_arguments = {
CancerGenomesService.CONFIG_CANCER_GENOMES_MUTATION_FILE:
input_mutation,
CancerGenomesService.CONFIG_COMPLETE_GENES_FILE: input_genes,
CancerGenomesService.CONFIG_OUTPUT_FILE: output_db,
CancerGenomesService.FILTER_COLUMN: filter_column,
CancerGenomesService.ACCEPTED_VALUES: accepted_values,
CancerGenomesService.SPLIT_BY_FILTER_COLUMN: split_by_filter_column
}
cosmic_to_proteindb_service = CancerGenomesService(config_file,
pipeline_arguments)
cosmic_to_proteindb_service.cosmic_to_proteindb()
def vcf_to_proteindb(
ctx, config_file, input_fasta, vep_annotated_vcf, gene_annotations_gtf,
translation_table, mito_translation_table, var_prefix, report_ref_seq,
output_proteindb, annotation_field_name, af_field, af_threshold,
transcript_index, consequence_index, exclude_biotypes,
exclude_consequences, skip_including_all_cds, include_biotypes,
include_consequences, biotype_str, ignore_filters, accepted_filters):
if input_fasta is None or vep_annotated_vcf is None or gene_annotations_gtf is None:
print_help()
pipeline_arguments = {}
pipeline_arguments[
EnsemblDataService.MITO_TRANSLATION_TABLE] = mito_translation_table
pipeline_arguments[
EnsemblDataService.TRANSLATION_TABLE] = translation_table
pipeline_arguments[EnsemblDataService.HEADER_VAR_PREFIX] = var_prefix
pipeline_arguments[
EnsemblDataService.REPORT_REFERENCE_SEQ] = report_ref_seq
pipeline_arguments[EnsemblDataService.PROTEIN_DB_OUTPUT] = output_proteindb
pipeline_arguments[
EnsemblDataService.ANNOTATION_FIELD_NAME] = annotation_field_name
pipeline_arguments[EnsemblDataService.AF_FIELD] = af_field
pipeline_arguments[EnsemblDataService.AF_THRESHOLD] = af_threshold
pipeline_arguments[EnsemblDataService.TRANSCRIPT_INDEX] = transcript_index
pipeline_arguments[
EnsemblDataService.CONSEQUENCE_INDEX] = consequence_index
pipeline_arguments[EnsemblDataService.EXCLUDE_BIOTYPES] = exclude_biotypes
pipeline_arguments[
EnsemblDataService.EXCLUDE_CONSEQUENCES] = exclude_consequences
pipeline_arguments[
EnsemblDataService.SKIP_INCLUDING_ALL_CDS] = skip_including_all_cds
pipeline_arguments[EnsemblDataService.INCLUDE_BIOTYPES] = include_biotypes
pipeline_arguments[
EnsemblDataService.INCLUDE_CONSEQUENCES] = include_consequences
pipeline_arguments[EnsemblDataService.BIOTYPE_STR] = biotype_str
pipeline_arguments[EnsemblDataService.IGNORE_FILTERS] = ignore_filters
pipeline_arguments[EnsemblDataService.ACCEPTED_FILTERS] = accepted_filters
ensembl_data_service = EnsemblDataService(config_file, pipeline_arguments)
ensembl_data_service.vcf_to_proteindb(vep_annotated_vcf, input_fasta,
gene_annotations_gtf)