Gdc Tools

Configuration File: gdc_tools.json Tool Type: Local Tools Count: 9

This page contains all tools defined in the gdc_tools.json configuration file.

Available Tools

GDC_get_clinical_data (Type: GDCClinicalDataTool)

Get detailed clinical data for cancer cases from NCI GDC/TCGA. Returns demographics (gender, race…

GDC_get_clinical_data tool specification

Tool Information:

  • Name: GDC_get_clinical_data

  • Type: GDCClinicalDataTool

  • Description: Get detailed clinical data for cancer cases from NCI GDC/TCGA. Returns demographics (gender, race, vital_status, age_at_index), diagnoses (primary_diagnosis, tumor_stage, age_at_diagnosis, days_to_last_follow_up), and treatments (therapeutic_agents, treatment_type). Filter by project, primary_site, disease_type, or vital_status.

Parameters:

  • project_id (string) (optional) GDC project identifier (e.g., ‘TCGA-BRCA’, ‘TCGA-LUAD’, ‘TARGET-AML’)

  • primary_site (string) (optional) Primary anatomical site (e.g., ‘Breast’, ‘Lung’, ‘Brain’)

  • disease_type (string) (optional) Disease type filter (e.g., ‘Ductal and Lobular Neoplasms’)

  • vital_status (string) (optional) Vital status filter: ‘Alive’ or ‘Dead’

  • gender (string) (optional) Gender filter: ‘female’ or ‘male’

  • size (integer) (optional) Number of cases to return (1-100)

  • offset (integer) (optional) Pagination offset (0-based)

Example Usage:

query = {
    "name": "GDC_get_clinical_data",
    "arguments": {
    }
}
result = tu.run(query)

GDC_get_cnv_data (Type: GDCCNVTool)

Query copy number variation (CNV) files from GDC/TCGA projects. Returns CNV segment and gene-leve…

GDC_get_cnv_data tool specification

Tool Information:

  • Name: GDC_get_cnv_data

  • Type: GDCCNVTool

  • Description: Query copy number variation (CNV) files from GDC/TCGA projects. Returns CNV segment and gene-level copy number files. Use for amplification/deletion analysis.

Parameters:

  • project_id (string) (required) GDC project (e.g., ‘TCGA-BRCA’)

  • gene_symbol (string) (optional) Optional: Gene symbol to focus analysis

  • size (integer) (optional) Number of results

Example Usage:

query = {
    "name": "GDC_get_cnv_data",
    "arguments": {
        "project_id": "example_value"
    }
}
result = tu.run(query)

GDC_get_gene_expression (Type: GDCGeneExpressionTool)

Query RNA-Seq gene expression files from GDC/TCGA projects. Returns file metadata for expression …

GDC_get_gene_expression tool specification

Tool Information:

  • Name: GDC_get_gene_expression

  • Type: GDCGeneExpressionTool

  • Description: Query RNA-Seq gene expression files from GDC/TCGA projects. Returns file metadata for expression quantification data. Use to find expression data for downstream analysis.

Parameters:

  • project_id (string) (required) GDC project (e.g., ‘TCGA-BRCA’, ‘TCGA-LUAD’, ‘TCGA-GBM’)

  • gene_id (string) (optional) Optional: Ensembl gene ID (e.g., ‘ENSG00000141510’ for TP53)

  • size (integer) (optional) Number of results

Example Usage:

query = {
    "name": "GDC_get_gene_expression",
    "arguments": {
        "project_id": "example_value"
    }
}
result = tu.run(query)

GDC_get_mutation_frequency (Type: GDCMutationFrequencyTool)

Get pan-cancer mutation frequency statistics for a gene across all TCGA/GDC cancer projects. Retu…

GDC_get_mutation_frequency tool specification

Tool Information:

  • Name: GDC_get_mutation_frequency

  • Type: GDCMutationFrequencyTool

  • Description: Get pan-cancer mutation frequency statistics for a gene across all TCGA/GDC cancer projects. Returns total SSM occurrence count (no per-project breakdown — use GDC_get_ssm_by_gene with project_id for cancer-specific data). Answers ‘How often is this gene mutated across all cancers?’

Parameters:

  • gene_symbol (string) (required) Gene symbol (e.g., ‘TP53’, ‘KRAS’, ‘EGFR’)

  • gene (string) (optional) Gene symbol alias — alternative to gene_symbol

Example Usage:

query = {
    "name": "GDC_get_mutation_frequency",
    "arguments": {
        "gene_symbol": "example_value"
    }
}
result = tu.run(query)

GDC_get_ssm_by_gene (Type: GDCSSMTool)

Get somatic mutations (SSMs) for a gene across TCGA/GDC projects. Returns mutation type, genomic …

GDC_get_ssm_by_gene tool specification

Tool Information:

  • Name: GDC_get_ssm_by_gene

  • Type: GDCSSMTool

  • Description: Get somatic mutations (SSMs) for a gene across TCGA/GDC projects. Returns mutation type, genomic coordinates, and amino acid changes. Essential for pan-cancer mutation analysis.

Parameters:

  • gene_symbol (string) (required) Gene symbol (e.g., ‘TP53’, ‘EGFR’, ‘BRAF’, ‘KRAS’)

  • project_id (string) (optional) Optional: Filter by project (e.g., ‘TCGA-BRCA’, ‘TCGA-LUAD’)

  • size (integer) (optional) Number of results (1–100)

Example Usage:

query = {
    "name": "GDC_get_ssm_by_gene",
    "arguments": {
        "gene_symbol": "example_value"
    }
}
result = tu.run(query)

GDC_get_survival (Type: GDCSurvivalTool)

Get Kaplan-Meier survival data for a GDC/TCGA cancer cohort. Returns time-to-event data with cens…

GDC_get_survival tool specification

Tool Information:

  • Name: GDC_get_survival

  • Type: GDCSurvivalTool

  • Description: Get Kaplan-Meier survival data for a GDC/TCGA cancer cohort. Returns time-to-event data with censoring status and survival estimates for each patient. Filter by project and optionally by gene mutation status. Use for overall survival analysis of TCGA cancer types.

Parameters:

  • project_id (string) (required) GDC project identifier (e.g., ‘TCGA-BRCA’, ‘TCGA-LUAD’, ‘TCGA-GBM’)

  • gene_symbol (string) (optional) Optional: gene symbol to filter cases with mutations in this gene (e.g., ‘TP53’, ‘KRAS’)

Example Usage:

query = {
    "name": "GDC_get_survival",
    "arguments": {
        "project_id": "example_value"
    }
}
result = tu.run(query)

GDC_list_files (Type: GDCFilesTool)

List GDC files filtered by data_type and other fields. Use to identify downloadable artifacts (e….

GDC_list_files tool specification

Tool Information:

  • Name: GDC_list_files

  • Type: GDCFilesTool

  • Description: List GDC files filtered by data_type and other fields. Use to identify downloadable artifacts (e.g., expression quantification) for analysis pipelines.

Parameters:

  • data_type (string) (optional) Data type filter (e.g., ‘Gene Expression Quantification’).

  • size (integer) (optional) Number of results (1–100).

  • offset (integer) (optional) Offset for pagination (0-based).

Example Usage:

query = {
    "name": "GDC_list_files",
    "arguments": {
    }
}
result = tu.run(query)

GDC_list_projects (Type: GDCProjectsTool)

List GDC projects (TCGA, TARGET, etc.) with case/file counts. Use to discover available cancer co…

GDC_list_projects tool specification

Tool Information:

  • Name: GDC_list_projects

  • Type: GDCProjectsTool

  • Description: List GDC projects (TCGA, TARGET, etc.) with case/file counts. Use to discover available cancer cohorts and their data volume. Filter by program (TCGA, TARGET, CGCI, etc.).

Parameters:

  • program (string) (optional) Filter by program name (e.g., ‘TCGA’, ‘TARGET’)

  • size (integer) (optional) Number of results (1–100)

Example Usage:

query = {
    "name": "GDC_list_projects",
    "arguments": {
    }
}
result = tu.run(query)

GDC_search_cases (Type: GDCCasesTool)

Search cancer cohort cases in NCI GDC by project and filters. Use to retrieve case-level metadata…

GDC_search_cases tool specification

Tool Information:

  • Name: GDC_search_cases

  • Type: GDCCasesTool

  • Description: Search cancer cohort cases in NCI GDC by project and filters. Use to retrieve case-level metadata for cohort construction and downstream file queries.

Parameters:

  • project_id (string) (optional) GDC project identifier (e.g., ‘TCGA-BRCA’).

  • size (integer) (optional) Number of results (1–100).

  • offset (integer) (optional) Offset for pagination (0-based).

Example Usage:

query = {
    "name": "GDC_search_cases",
    "arguments": {
    }
}
result = tu.run(query)