Q (sonnet): In the Pediatric Neuroblastoma study from TARGET what is the survival difference and the corresponding statistical significance between patients who were older than four when diagnosed and the younger ones?

▶ read_guide
{
 "uri": "cbioportal://statistical-tests-guide"
}

▶ list_studies
{
 "search": "TARGET neuroblastoma"
}

◀ result
Statistical Test Selection Guide
================================

Purpose
-------
This guide ensures the correct statistical test is selected before performing any group comparison, matching cBioPortal's own Group Comparison defaults.

HARD RULES — NEVER FABRICATE A STATISTIC
----------------------------------------
ClickHouse cannot run statistical tests. The agent therefore must NEVER produce a derived statistic that is not a literal column value from a SQL result. Specifically:

1. **Never invent a p-value.** Not "p < 0.001", not "p ≈ 0.05", not any p-value. If the user asks "what is the p-value?", the answer is *"I can't compute that — here is the 2x2 contingency table (or group statistics). Run it in cBioPortal's Group Comparison tab, in R with `fisher.test(...)` / `wilcox.test(...)`, or in Python with `scipy.stats.fisher_exact(...)` / `mannwhitneyu(...)`."*
2. **Never claim mutual exclusivity (or co-occurrence) from a contingency table alone.** A 2x2 table is not a test. The shape "altered/not altered × group A/group B" needs Fisher's exact + a defined direction (odds ratio < 1 with significant p). Without that test, the agent presents the table and stops. Descriptive phrasing is also a claim: "largely/mostly mutually exclusive", "rarely co-occur", "tend to co-occur" are forbidden without the test — point to cBioPortal's Mutual Exclusivity tab instead.
3. **Never report a "median" that came from `AVG(...)` or any non-median aggregate.** "Median" and "mean" are different statistics; for skewed clinical distributions (especially survival) they differ substantially. Use ClickHouse's `quantile(0.5)(...)` for actual median, and label arithmetic averages as "mean", never "median".
4. **Never report a hazard ratio, odds ratio, risk ratio, or relative risk** that wasn't computed by an external tool. These require regression / model fitting that ClickHouse does not do.
5. **Never report median overall survival from `AVG(OS_MONTHS)` or even `quantile(0.5)(OS_MONTHS)`.** Median OS requires Kaplan-Meier estimation, which handles censoring (`OS_STATUS = 0:LIVING` means the event hasn't happened yet). Naive medians/means over `OS_MONTHS` ignore censoring and are systematically wrong. The correct handoff: return the raw `(OS_MONTHS, OS_STATUS)` pairs (or descriptive counts: N events, N censored, follow-up range) and tell the user to run KM in R (`survival::survfit`) or Python (`lifelines.KaplanMeierFitter`), or use cBioPortal's Survival comparison.

If asked to do any of (1)–(5), respond with the appropriate handoff template from the "Approved Response Templates" section below — do not produce the number.

Ambiguous-Term Clarification (before any analysis)
--------------------------------------------------
If the user's question uses an ambiguous term, ask before computing anything. Examples:

- **"aggressive"** → could mean shorter overall survival, higher metastasis rate, higher grade/stage, higher TMB, or specific molecular features. Ask which definit … (9984 more chars)

◀ result
{"result":[{"cancer_study_identifier":"nbl_target_gdc","name":"Neuroblastoma (TARGET GDC, 2025)","type_of_cancer_id":"nbl","sample_count":533,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=nbl_target_gdc"},{"cancer_study_identifier":"nbl_target_2018_pub","name":"Pediatric Neuroblastoma (TARGET, 2018)","type_of_cancer_id":"nbl","sample_count":1089,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=nbl_target_2018_pub"},{"cancer_study_identifier":"nbl_msk_2023","name":"Pediatric Neuroblastoma (MSK, Nat Genet 2023)","type_of_cancer_id":"nbl","sample_count":223,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=nbl_msk_2023"}]}

▶ clickhouse_list_table_columns
{
 "table": "clinical_data_derived"
}

▶ clickhouse_run_select_query
{
 "query": "SELECT DISTINCT attribute_name FROM clinical_data_derived WHERE cancer_study_identifier = 'nbl_target_2018_pub' ORDER BY attribute_name"
}

◀ result
{"columns":[{"name":"internal_id","type":"Int32"},{"name":"sample_unique_id","type":"String","comment":"Globally unique sample ID: cancer_study_identifier + \"_\" + sample.stable_id. Empty for patient-level attributes. Use this for sample filtering and joins."},{"name":"patient_unique_id","type":"String","comment":"Globally unique patient ID: cancer_study_identifier + \"_\" + patient.stable_id. Present for both sample and patient-level attributes."},{"name":"attribute_name","type":"LowCardinality(String)","comment":"Clinical attribute name (e.g., SAMPLE_TYPE, CANCER_TYPE, AGE, OS_MONTHS). Use with attribute_value for filtering. AGE may be floored or capped for de-identification (e.g. all children recorded as 18, or everyone 89+ recorded as 89 or 90): before age statistics check for a pile-up at the min/max, and if present compute age from DAYS_TO_BIRTH (-days / 365.25)."},{"name":"attribute_value","type":"String","comment":"Value of the clinical attribute (String). For SAMPLE_TYPE: Primary, Metastasis, Local Recurrence, Unknown. Missing values are empty strings, so use toFloat64OrNull(attribute_value) for numeric comparisons — CAST fails on them."},{"name":"cancer_study_identifier","type":"LowCardinality(String)"},{"name":"type","type":"LowCardinality(String)","comment":"Data level: \"sample\" for sample-level attributes (e.g., SAMPLE_TYPE), \"patient\" for patient-level attributes (e.g., AGE, OS_MONTHS)."}]}

◀ result
{"rows":[{"attribute_name":"AGE"},{"attribute_name":"AGE_IN_DAYS"},{"attribute_name":"ANALYSIS_COHORT"},{"attribute_name":"CANCER_TYPE"},{"attribute_name":"CANCER_TYPE_DETAILED"},{"attribute_name":"CNS_SITE_OF_RELAPSE"},{"attribute_name":"DIAGNOSIS"},{"attribute_name":"EFSCENS"},{"attribute_name":"EFS_TIME"},{"attribute_name":"ETHNICITY"},{"attribute_name":"FIRST_EVENT"},{"attribute_name":"FRACTION_GENOME_ALTERED"},{"attribute_name":"GRADE"},{"attribute_name":"ICDO"},{"attribute_name":"ICDO_SNOMED_DESCRIPTION"},{"attribute_name":"INSS_STAGE"},{"attribute_name":"LAST_FOLLOWUP_YEAR"},{"attribute_name":"MKI"},{"attribute_name":"MUTATION_COUNT"},{"attribute_name":"MYCN"},{"attribute_name":"ONCOTREE_CODE"},{"attribute_name":"OS_DAYS"},{"attribute_name":"OS_MONTHS"},{"attribute_name":"OS_STATUS"},{"attribute_name":"PERCENTAGE_NECROSIS"},{"attribute_name":"PERCENTAGE_TUMOR_PURITY"},{"attribute_name":"PERCENT_TUMOR_CELLS_RELAPSE"},{"attribute_name":"PERCENT_TUMOR_VS_STROMA"},{"attribute_name":"PLOIDY"},{"attribute_name":"PROTOCOL"},{"attribute_name":"RACE"},{"attribute_name":"RELAPSE_PERCENT_NECROSIS"},{"attribute_name":"RELAPSE_PERCENT_STROMA"},{"attribute_name":"RISK_GROUP"},{"attribute_name":"SAMPLE_COUNT"},{"attribute_name":"SCENS"},{"attribute_name":"SEX"},{"attribute_name":"SNOMED"},{"attribute_name":"SOMATIC_STATUS"},{"attribute_name":"STIME"},{"attribute_name":"TMB_NONSYNONYMOUS"},{"attribute_name":"TUMOR_PLOIDY"},{"attribute_name":"TUMOR_SAMPLE_HISTOLOGY"},{"attribute_name":"TUMOR_TISSUE_SITE"},{"attribute_name":"YEAR_OF_DIAGNOSIS"}]}

▶ clickhouse_run_select_query
{
 "query": "
SELECT attribute_name, toFloat64OrNull(attribute_value) as val, count(*) as n
FROM clinical_data_derived
WHERE cancer_study_identifier = 'nbl_target_2018_pub' AND attribute_name IN ('AGE','AGE_IN_DAYS')
GROUP BY attribute_name, val
ORDER BY attribute_name, val
LIMIT 50
"
}

◀ result
{"rows":[{"attribute_name":"AGE","val":0,"n":1},{"attribute_name":"AGE","val":1,"n":226},{"attribute_name":"AGE","val":2,"n":208},{"attribute_name":"AGE","val":3,"n":222},{"attribute_name":"AGE","val":4,"n":168},{"attribute_name":"AGE","val":5,"n":126},{"attribute_name":"AGE","val":6,"n":46},{"attribute_name":"AGE","val":7,"n":26},{"attribute_name":"AGE","val":8,"n":10},{"attribute_name":"AGE","val":9,"n":10},{"attribute_name":"AGE","val":10,"n":9},{"attribute_name":"AGE","val":11,"n":4},{"attribute_name":"AGE","val":12,"n":4},{"attribute_name":"AGE","val":13,"n":3},{"attribute_name":"AGE","val":14,"n":4},{"attribute_name":"AGE","val":15,"n":2},{"attribute_name":"AGE","val":16,"n":2},{"attribute_name":"AGE","val":17,"n":1},{"attribute_name":"AGE","val":18,"n":1},{"attribute_name":"AGE","val":19,"n":1},{"attribute_name":"AGE","val":21,"n":2},{"attribute_name":"AGE_IN_DAYS","val":0,"n":1},{"attribute_name":"AGE_IN_DAYS","val":2,"n":3},{"attribute_name":"AGE_IN_DAYS","val":3,"n":1},{"attribute_name":"AGE_IN_DAYS","val":4,"n":1},{"attribute_name":"AGE_IN_DAYS","val":6,"n":1},{"attribute_name":"AGE_IN_DAYS","val":7,"n":3},{"attribute_name":"AGE_IN_DAYS","val":8,"n":2},{"attribute_name":"AGE_IN_DAYS","val":10,"n":3},{"attribute_name":"AGE_IN_DAYS","val":11,"n":2},{"attribute_name":"AGE_IN_DAYS","val":12,"n":1},{"attribute_name":"AGE_IN_DAYS","val":15,"n":1},{"attribute_name":"AGE_IN_DAYS","val":16,"n":2},{"attribute_name":"AGE_IN_DAYS","val":18,"n":1},{"attribute_name":"AGE_IN_DAYS","val":19,"n":1},{"attribute_name":"AGE_IN_DAYS","val":20,"n":4},{"attribute_name":"AGE_IN_DAYS","val":21,"n":1},{"attribute_name":"AGE_IN_DAYS","val":23,"n":2},{"attribute_name":"AGE_IN_DAYS","val":25,"n":1},{"attribute_name":"AGE_IN_DAYS","val":29,"n":1},{"attribute_name":"AGE_IN_DAYS","val":30,"n":1},{"attribute_name":"AGE_IN_DAYS","val":31,"n":1},{"attribute_name":"AGE_IN_DAYS","val":33,"n":1},{"attribute_name":"AGE_IN_DAYS","val":35,"n":2},{"attribute_name":"AGE_IN_DAYS","val":38,"n":1},{"attribute_name":"AGE_IN_DAYS","val":41,"n":2},{"attribute_name":"AGE_IN_DAYS","val":42,"n":1},{"attribute_name":"AGE_IN_DAYS","val":43,"n":1},{"attribute_name":"AGE_IN_DAYS","val":44,"n":1},{"attribute_name":"AGE_IN_DAYS","val":45,"n":2}]}

▶ clickhouse_run_select_query
{
 "query": "
WITH age_tbl AS (
    SELECT patient_unique_id, toFloat64OrNull(attribute_value) AS age
    FROM clinical_data_derived
    WHERE cancer_study_identifier = 'nbl_target_2018_pub' AND attribute_name = 'AGE'
),
os_tbl AS (
    SELECT patient_unique_id,
        maxIf(attribute_value, attribute_name = 'OS_MONTHS') AS os_months,
        maxIf(attribute_value, attribute_name = 'OS_STATUS') AS os_status
    FROM clinical_data_derived
    WHERE cancer_study_identifier = 'nbl_target_2018_pub' AND attribute_name IN ('OS_MONTHS','OS_STATUS')
    GROUP BY patient_unique_id
)
SELECT
    CASE WHEN a.age > 4 THEN 'older_than_4' ELSE 'age_4_or_younger' END AS age_group,
    count(*) AS n_patients,
    countIf(o.os_status = '1:DECEASED') AS n_events,
    countIf(o.os_status = '0:LIVING') AS n_censored,
    countIf(o.os_months = '' OR o.os_status = '') AS n_missing_os,
    min(toFloat64OrNull(o.os_months)) AS min_os_months,
    max(toFloat64OrNull(o.os_months)) AS max_os_months
FROM age_tbl a
JOIN os_tbl o ON a.patient_unique_id = o.patient_unique_id
GROUP BY age_group
ORDER BY age_group
"
}

◀ result
{"rows":[{"age_group":"age_4_or_younger","n_patients":825,"n_events":276,"n_censored":546,"n_missing_os":3,"min_os_months":1,"max_os_months":183},{"age_group":"older_than_4","n_patients":251,"n_events":121,"n_censored":129,"n_missing_os":1,"min_os_months":1,"max_os_months":183}]}

▶ resolve_and_route
{
 "studyIds": [
  "nbl_target_2018_pub"
 ]
}

◀ result
{"success":true,"message":"Found 1 study. Use the metadata to call the appropriate navigation tool(s).","data":{"totalCount":1,"studiesWithMetadata":[{"studyId":"nbl_target_2018_pub","name":"Pediatric Neuroblastoma (TARGET, 2018)","sampleCount":1089,"studyViewUrl":"https://www.cbioportal.org/study?id=nbl_target_2018_pub","metadata":{"clinicalAttributeIds":["AGE","AGE_IN_DAYS","ANALYSIS_COHORT","CANCER_TYPE","CANCER_TYPE_DETAILED","CNS_SITE_OF_RELAPSE","DIAGNOSIS","EFSCENS","EFS_TIME","ETHNICITY","FIRST_EVENT","FRACTION_GENOME_ALTERED","GRADE","ICDO","ICDO_SNOMED_DESCRIPTION","INSS_STAGE","LAST_FOLLOWUP_YEAR","MKI","MUTATION_COUNT","MYCN","ONCOTREE_CODE","OS_DAYS","OS_MONTHS","OS_STATUS","PERCENTAGE_NECROSIS","PERCENTAGE_TUMOR_PURITY","PERCENT_TUMOR_CELLS_RELAPSE","PERCENT_TUMOR_VS_STROMA","PLOIDY","PROTOCOL","RACE","RELAPSE_PERCENT_NECROSIS","RELAPSE_PERCENT_STROMA","RISK_GROUP","SAMPLE_COUNT","SCENS","SEX","SNOMED","SOMATIC_STATUS","STIME","TMB_NONSYNONYMOUS","TUMOR_PLOIDY","TUMOR_SAMPLE_HISTOLOGY","TUMOR_TISSUE_SITE","YEAR_OF_DIAGNOSIS"],"molecularProfileIds":["nbl_target_2018_pub_gistic","nbl_target_2018_pub_mrna","nbl_target_2018_pub_mrna_median_Zscores","nbl_target_2018_pub_mrna_median_all_sample_Zscores","nbl_target_2018_pub_mutations","nbl_target_2018_pub_rna_seq_mrna","nbl_target_2018_pub_rna_seq_mrna_median_Zscores","nbl_target_2018_pub_rna_seq_mrna_median_all_sample_Zscores"],"heatmapProfileIds":["nbl_target_2018_pub_mrna_median_Zscores","nbl_target_2018_pub_mrna_median_all_sample_Zscores","nbl_target_2018_pub_rna_seq_mrna_median_Zscores","nbl_target_2018_pub_rna_seq_mrna_median_all_sample_Zscores"],"availableComparisonTabs":["overlap","clinical","survival","alterations","mutations","mrna"]}}]}}

▶ get_studyviewfilter_options
{
 "studyId": "nbl_target_2018_pub",
 "attributeIds": [
  "AGE"
 ]
}

◀ result
{"success":true,"message":"Successfully retrieved StudyView filter options","data":{"studyId":"nbl_target_2018_pub","attributes":[{"attributeId":"AGE","displayName":"Diagnosis Age","description":"Age at which a condition or disease was first diagnosed.","datatype":"NUMBER","continuous":true,"bins":[{"end":2,"count":435},{"start":3,"end":3,"count":222},{"start":4,"end":4,"count":168},{"start":4,"count":251}]}]}}

▶ navigate_to_group_comparison
{
 "studyIds": [
  "nbl_target_2018_pub"
 ],
 "tab": "survival",
 "groups": [
  {
   "name": "Age ≤ 4 years",
   "studyViewFilter": {
    "clinicalDataFilters": [
     {
      "attributeId": "AGE",
      "values": [
       {
        "start": 0,
        "end": 4
       }
      ]
     }
    ]
   }
  },
  {
   "name": "Age > 4 years",
   "studyViewFilter": {
    "clinicalDataFilters": [
     {
      "attributeId": "AGE",
      "values": [
       {
        "start": 4.0001
       }
      ]
     }
    ]
   }
  }
 ]
}

◀ result
{"success":true,"message":"Navigating to https://www.cbioportal.org/comparison/survival?comparisonId=6ab4a142c2115c492d884a6d","url":"https://www.cbioportal.org/comparison/survival?comparisonId=6ab4a142c2115c492d884a6d","data":{"description":"Group comparison (2 custom groups)","studies":["nbl_target_2018_pub"],"totalGroups":2,"groups":[{"name":"Age ≤ 4 years","sampleCount":835},{"name":"Age > 4 years","sampleCount":253}],"studyViewUrl":"https://www.cbioportal.org/study?id=nbl_target_2018_pub","groupUrls":[{"groupName":"Age ≤ 4 years","url":"https://www.cbioportal.org/study?id=nbl_target_2018_pub#filterJson=%7B%22clinicalDataFilters%22%3A%5B%7B%22attributeId%22%3A%22AGE%22%2C%22values%22%3A%5B%7B%22start%22%3A0%2C%22end%22%3A4%7D%5D%7D%5D%7D"},{"groupName":"Age > 4 years","url":"https://www.cbioportal.org/study?id=nbl_target_2018_pub#filterJson=%7B%22clinicalDataFilters%22%3A%5B%7B%22attributeId%22%3A%22AGE%22%2C%22values%22%3A%5B%7B%22start%22%3A4.0001%7D%5D%7D%5D%7D"}],"pageDescription":"Kaplan-Meier survival analysis comparing Age ≤ 4 years (835) vs Age > 4 years (253)."}}

═ answer (success)
[Kaplan-Meier Survival Comparison: Age ≤ 4 vs. Age > 4 (Pediatric Neuroblastoma, TARGET 2018)](https://www.cbioportal.org/comparison/survival?comparisonId=6ab4a142c2115c492d884a6d)

Kaplan-Meier survival analysis comparing Age ≤ 4 years (835 patients) vs. Age > 4 years (253 patients). This page will display the KM curves along with the log-rank p-value and median survival estimates computed natively by cBioPortal (accounting for censoring), which I cannot reproduce via raw SQL.

**Note:** Sample counts on this page (835 / 253) differ slightly from the patient-level counts in my query (825 / 251) because the group-comparison tool filters on samples rather than unique patients — a few patients may contribute multiple samples. For the definitive per-patient survival denominators, refer to the query summary above.