Q (sonnet): What is the median survival time in the Pediatric Neuroblastoma study from TARGET? ▶ 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" } ◀ 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)."}]} ▶ clickhouse_run_select_query { "query": " SELECT attribute_name, attribute_value, count(DISTINCT patient_unique_id) AS n_patients FROM clinical_data_derived WHERE cancer_study_identifier = 'nbl_target_2018_pub' AND attribute_name IN ('OS_STATUS') GROUP BY attribute_name, attribute_value ORDER BY attribute_name, attribute_value " } ◀ result {"rows":[{"attribute_name":"OS_STATUS","n_patients":4},{"attribute_name":"OS_STATUS","attribute_value":"0:LIVING","n_patients":675},{"attribute_name":"OS_STATUS","attribute_value":"1:DECEASED","n_patients":397}]} ▶ clickhouse_run_select_query { "query": " SELECT min(toFloat64OrNull(attribute_value)) AS min_os_months, max(toFloat64OrNull(attribute_value)) AS max_os_months, count(DISTINCT patient_unique_id) AS n_with_os_months FROM clinical_data_derived WHERE cancer_study_identifier = 'nbl_target_2018_pub' AND attribute_name = 'OS_MONTHS' AND attribute_value != '' " } ◀ result {"rows":[{"min_os_months":1,"max_os_months":183,"n_with_os_months":1072}]} ▶ resolve_and_route { "studyIds": [ "nbl_target_2018_pub" ] } ◀ result {"success":false,"error":"Internal Server Error","details":{"status":500,"response":{"req":{"method":"POST","url":"https://www.cbioportal.org/api/molecular-profiles/fetch","data":{"studyIds":["nbl_target_2018_pub"]},"headers":{"user-agent":"node-superagent/3.8.3","accept":"application/json","content-type":"application/json"}},"header":{"cache-control":"no-cache, no-store, max-age=0, must-revalidate","content-encoding":"gzip","content-type":"application/json","date":"Sat, 26 Sep 2026 16:45:09 GMT","elapsed-time":"0","expires":"0","pragma":"no-cache","strict-transport-security":"max-age=31536000 ; includeSubDomains","vary":"origin,access-control-request-method,access-control-request-headers,accept-encoding","x-content-type-options":"nosniff","x-frame-options":"DENY","x-xss-protection":"0","connection":"close","transfer-encoding":"chunked"},"status":500,"text":"{\"timestamp\":1790441109670,\"status\":500,\"error\":\"Internal Server Error\",\"path\":\"/api/molecular-profiles/fetch\"}"}}} ═ answer (success) The navigation service returned an internal server error resolving that study, so I can't generate a live link right now. You can view the Kaplan-Meier overall survival curve directly on cBioPortal here: **[Pediatric Neuroblastoma (TARGET, 2018) — Study Summary](https://www.cbioportal.org/study/summary?id=nbl_target_2018_pub)** Once there, go to the **Survival** tab to see the KM curve, the reported median OS (or "not reached"), and number-at-risk table for the full cohort — or split by any clinical variable (e.g., stage, MYCN status) for a log-rank comparison. **Summary of what I found in the data** (patients, `nbl_target_2018_pub`): - 397 deaths (events), 675 censored (alive at last follow-up), 4 with unknown status - Follow-up ranged from 1 to 183 months Let me know if you'd like the survival breakdown split by a specific variable, like MYCN amplification status or INSS stage — I can pull those group counts and link you directly to the Survival comparison tab.