Q (haiku): What is the most common cancer type in the MSK-CHORD Study based on sample count?

▶ clickhouse_list_tables
{}

◀ result
{"tables":[{"name":"allele_specific_copy_number"},{"name":"alteration_driver_annotation"},{"name":"cancer_study"},{"name":"cancer_study_query_preferences"},{"name":"cancer_study_tags"},{"name":"cbioportal_sequence_state"},{"name":"clinical_attribute_counts"},{"name":"clinical_attribute_meta"},{"name":"clinical_data_derived"},{"name":"clinical_event"},{"name":"clinical_event_data"},{"name":"clinical_event_data_derived"},{"name":"clinical_event_derived"},{"name":"clinical_patient"},{"name":"clinical_sample"},{"name":"cna_event"},{"name":"cna_panel_gene_coverage"},{"name":"cna_wes_coverage"},{"name":"co_altered_genes_in_study"},{"name":"copy_number_seg"},{"name":"copy_number_seg_file"},{"name":"gene"},{"name":"gene_alias"},{"name":"gene_alteration_frequency_by_cancer_type"},{"name":"gene_cna_distribution_in_study"},{"name":"gene_mutation_frequency_by_cancer_type"},{"name":"gene_mutation_frequency_in_studies"},{"name":"gene_mutation_frequency_in_study"},{"name":"gene_mutation_variants_in_study"},{"name":"gene_pair_coexpression"},{"name":"gene_panel"},{"name":"gene_panel_list"},{"name":"gene_panel_to_gene_derived"},{"name":"generic_assay_data_derived"},{"name":"generic_assay_meta_derived"},{"name":"generic_assay_profile_entity_derived"},{"name":"generic_entity_properties"},{"name":"geneset"},{"name":"geneset_gene"},{"name":"geneset_hierarchy_leaf"},{"name":"geneset_hierarchy_node"},{"name":"genetic_alteration"},{"name":"genetic_alteration_derived"},{"name":"genetic_entity"},{"name":"genetic_profile"},{"name":"genetic_profile_link"},{"name":"genetic_profile_samples"},{"name":"genomic_event_derived"},{"name":"gistic"},{"name":"gistic_to_gene"},{"name":"info"},{"name":"mut_sig"},{"name":"mutation"},{"name":"mutation_count_by_keyword"},{"name":"mutation_derived"},{"name":"mutation_event"},{"name":"mutation_panel_gene_coverage"},{"name":"mutation_wes_coverage"},{"name":"patient"},{"name":"reference_genome"},{"name":"reference_genome_gene"},{"name":"resource_definition"},{"name":"resource_patient"},{"name":"resource_sample"},{"name":"resource_study"},{"name":"sample"},{"name":"sample_cna_event"},{"name":"sample_derived"},{"name":"sample_list"},{"name":"sample_list_list"},{"name":"sample_profile"},{"name":"sample_to_gene_panel_derived"},{"name":"structural_variant"},{"name":"sv_panel_gene_coverage"},{"name":"sv_wes_coverage"},{"name":"top_cna_genes_in_study"},{"name":"top_mutated_genes_in_cohort"},{"name":"top_mutated_genes_in_study"},{"name":"top_sv_genes_in_study"},{"name":"treatment_counts_in_study"},{"name":"treatment_regimens_in_study"},{"name":"type_of_cancer"}]}

▶ clickhouse_run_select_query
{
 "query": "
SELECT 
    c.cancer_type_id,
    t.name as cancer_type_name,
    COUNT(DISTINCT s.stable_id) as sample_count
FROM cancer_study c
JOIN sample s ON c.cancer_study_id = s.cancer_study_id
LEFT JOIN type_of_cancer t ON c.type_of_cancer_id = t.type_of_cancer_id
WHERE c.cancer_study_identifier = 'msk_chord_2024'
GROUP BY c.cancer_type_id, t.name
ORDER BY sample_count DESC
LIMIT 10
",
 "max_rows": 100
}

◀ result
{"error_message":"Query execution failed: HTTPDriver for https://dl96orhu96.us-east-1.aws.clickhouse.cloud:8443 received ClickHouse error code 47\n Code: 47. DB::Exception: Identifier 's.cancer_study_id' cannot be resolved from table with name s. In scope SELECT c.cancer_type_id, t.name AS cancer_type_name, COUNTDistinct(s.stable_id) AS sample_count FROM cancer_study AS c INNER JOIN sample AS s ON c.cancer_study_id = s.cancer_study_id LEFT JOIN type_of_cancer AS t ON c.type_of_cancer_id = t.type_of_cancer_id WHERE c.cancer_study_identifier = 'msk_chord_2024' GROUP BY c.cancer_type_id, t.name ORDER BY sample_count DESC LIMIT 10. (UNKNOWN_IDENTIFIER) (version 26.4.1.2359 (official build))\n"}

▶ clickhouse_list_table_columns
{
 "table": "sample"
}

◀ result
{"columns":[{"name":"internal_id","type":"Int64","comment":"Primary key. Unique internal identifier for the sample."},{"name":"stable_id","type":"String","comment":"Stable identifier for the sample within the study. Combined with cancer_study_identifier forms sample_unique_id."},{"name":"patient_id","type":"Int64","comment":"Foreign key to patient.internal_id. Links sample to its patient."}]}

▶ clickhouse_list_table_columns
{
 "table": "sample_derived"
}

◀ result
{"columns":[{"name":"sample_unique_id","type":"String"},{"name":"sample_unique_id_base64","type":"String"},{"name":"sample_stable_id","type":"String"},{"name":"patient_unique_id","type":"String"},{"name":"patient_unique_id_base64","type":"String"},{"name":"patient_stable_id","type":"String"},{"name":"cancer_study_identifier","type":"LowCardinality(String)"},{"name":"internal_id","type":"Int32"},{"name":"patient_internal_id","type":"Int32"},{"name":"sample_type","type":"String"},{"name":"sequenced","type":"Int32"},{"name":"copy_number_segment_present","type":"Int32"}]}

▶ clickhouse_run_select_query
{
 "query": "
SELECT 
    attribute_value as cancer_type,
    COUNT(DISTINCT sample_unique_id) as sample_count
FROM clinical_data_derived
WHERE cancer_study_identifier = 'msk_chord_2024'
  AND attribute_name = 'CANCER_TYPE'
GROUP BY attribute_value
ORDER BY sample_count DESC
LIMIT 10
",
 "max_rows": 100
}

◀ result
{"rows":[{"cancer_type":"Non-Small Cell Lung Cancer","sample_count":7809},{"cancer_type":"Colorectal Cancer","sample_count":5543},{"cancer_type":"Breast Cancer","sample_count":5368},{"cancer_type":"Prostate Cancer","sample_count":3211},{"cancer_type":"Pancreatic Cancer","sample_count":3109}]}

▶ resolve_and_route
{
 "studyIds": [
  "msk_chord_2024"
 ]
}

◀ result
{"success":true,"message":"Found 1 study. Use the metadata to call the appropriate navigation tool(s).","data":{"totalCount":1,"studiesWithMetadata":[{"studyId":"msk_chord_2024","name":"MSK-CHORD (MSK, Nature 2024)","sampleCount":25040,"studyViewUrl":"https://www.cbioportal.org/study?id=msk_chord_2024","metadata":{"clinicalAttributeIds":["ADRENAL_GLANDS","BONE","CANCER_TYPE","CANCER_TYPE_DETAILED","CLINICAL_GROUP","CLINICAL_SUMMARY","CNS_BRAIN","CURRENT_AGE_DEID","DIAGNOSIS_DESCRIPTION","ETHNICITY","FRACTION_GENOME_ALTERED","GENDER","GENE_PANEL","GLEASON_FIRST_REPORTED","GLEASON_HIGHEST_REPORTED","GLEASON_SAMPLE_LEVEL","HER2","HISTORY_OF_PDL1","HR","ICD_O_HISTOLOGY_DESCRIPTION","INTRA_ABDOMINAL","LIVER","LUNG","LYMPH_NODES","METASTATIC_SITE","MSI_COMMENT","MSI_SCORE","MSI_TYPE","MUTATION_COUNT","NUM_ICDO_DX","ONCOTREE_CODE","OS_MONTHS","OS_STATUS","OTHER","PATHOLOGICAL_GROUP","PDL1_POSITIVE","PLEURA","PRIMARY_SITE","PRIOR_MED_TO_MSK","RACE","REPRODUCTIVE_ORGANS","SAMPLE_CLASS","SAMPLE_COUNT","SAMPLE_COVERAGE","SAMPLE_TYPE","SMOKING_PREDICTIONS_3_CLASSES","SOMATIC_STATUS","STAGE_HIGHEST_RECORDED","TMB_NONSYNONYMOUS","TUMOR_PURITY"],"molecularProfileIds":["msk_chord_2024_cna","msk_chord_2024_mutations","msk_chord_2024_structural_variants"],"availableComparisonTabs":["overlap","clinical","survival","alterations","mutations"]}}]}}

═ answer (success)
[View MSK-CHORD Study](https://www.cbioportal.org/study?id=msk_chord_2024)

The MSK-CHORD study contains 25,040 total samples across multiple cancer types, with Non-Small Cell Lung Cancer representing the largest cohort by far.