Q (sonnet-5.5): In the Breast Invasive Carcinoma TCGA study what are the top 5 down-regulated genes in TP53 mutated samples compared to non-mutated ones?

▶ read_guide
{
 "uri": "cbioportal://gene-expression-guide"
}

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

◀ result
# Gene Expression Analysis Guide

This guide covers continuous-value genomic data: gene **expression**, **copy number** values, **methylation**, and related profile types. Mutation/CNA/SV *frequency* analysis lives in `cbioportal://mutation-frequency-guide`.

## Where this data lives

Continuous per-sample-per-gene values are stored in `genetic_alteration_derived`:

| Column | Description |
|---|---|
| `sample_unique_id` | `<study>_<sample_stable_id>` |
| `cancer_study_identifier` | study scope |
| `hugo_gene_symbol` | gene |
| `profile_type` | which assay/normalization (see below) |
| `alteration_value` | the actual value — stored as Nullable(String); cast with `toFloat64OrNull` |

`alteration_value` is a string because the same column hosts many different value scales. The `''` and `'NA'` sentinels mean "missing"; always filter them out and use `toFloat64OrNull(alteration_value) IS NOT NULL` for downstream math.

## Discovering profile types for a study

Different studies expose different profile types depending on what assays were run and how the data was normalized. Always check what a specific study supports before picking one:

```sql
SELECT DISTINCT profile_type
FROM genetic_alteration_derived
WHERE cancer_study_identifier = 'brca_metabric'
ORDER BY profile_type;
```

Common values across the public portal:

| Family | Profile types |
|---|---|
| mRNA expression | `rna_seq_v2_mrna`, `rna_seq_v2_mrna_median_Zscores`, `rna_seq_v2_mrna_median_all_sample_Zscores` (TCGA PanCancer Atlas), `mrna`, `mrna_median_Zscores`, `mrna_seq_v2_rsem`, `mrna_seq_v2_rsem_Zscores`, `mrna_seq_cpm`, `mrna_seq_fpkm`, `mrna_U133`, `mrna_outliers` |
| Copy number (continuous) | `cna`, `linear_CNA`, `log2CNA`, `cna_consensus`, `cna_rae`, `gistic` |
| Methylation | `methylation_hm27`, `methylation_hm450`, `methylation_epic`, `methylation_promoters_rrbs` |
| miRNA | `mirna`, `mirna_median_Zscores` |
| Protein | `protein_quantification`, `protein_level`, `RPPA` |

**Z-score vs raw choice.** When the user asks "is X correlated with Y", either works for Spearman (rank-based) — Pearson would care. Default to the non-Z-score variant if both exist, and call out which one in the response.

## Canonical recipe — Spearman correlation between two genes

```sql
SELECT *
FROM gene_pair_coexpression(
    study        = 'brca_metabric',
    gene_a       = 'TP53',
    gene_b       = 'MYC',
    profile_type = 'mrna'
);
```

Returns one row: `(gene_a, gene_b, profile_type, spearman_correlation, num_samples)`.

- `spearman_correlation` in [−1, 1]; `NULL` when fewer than 3 valid paired samples.
- Mirrors cbioportal-backend's `ClickhouseCoExpressionMapper.getCoExpressions`, simplified to a pair lookup (the backend computes one ref gene vs ALL other genes for the coexpression page; here the agent asks about a specific pair).

### Verified examples

| Study | gene_a | gene_b | profile_type | spearman | n |
|---|---|---|---|---|---|
| `brca_metabric` | TP53 | MYC | `mrna` | 0.118 | 1980 |
|  … (4931 more chars)

▶ list_studies
{
 "search": "breast TCGA"
}

◀ 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":"brca_tcga","name":"Breast Invasive Carcinoma (TCGA, Firehose Legacy)","type_of_cancer_id":"brca","sample_count":1108,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=brca_tcga"},{"cancer_study_identifier":"brca_tcga_gdc","name":"Invasive Breast Carcinoma (TCGA GDC, 2025)","type_of_cancer_id":"brca","sample_count":1102,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=brca_tcga_gdc"},{"cancer_study_identifier":"brca_tcga_pan_can_atlas_2018","name":"Breast Invasive Carcinoma (TCGA, PanCancer Atlas)","type_of_cancer_id":"brca","sample_count":1084,"has_guide":true,"url":"https://www.cbioportal.org/study/summary?id=brca_tcga_pan_can_atlas_2018"},{"cancer_study_identifier":"brca_tcga_pub","name":"Breast Invasive Carcinoma (TCGA, Nature 2012)","type_of_cancer_id":"brca","sample_count":825,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=brca_tcga_pub"},{"cancer_study_identifier":"brca_tcga_pub2015","name":"Breast Invasive Carcinoma (TCGA, Cell 2015)","type_of_cancer_id":"brca","sample_count":818,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=brca_tcga_pub2015"},{"cancer_study_identifier":"mixed_msk_tcga_2021","name":"RAD51B Associated Mixed Cancers (MSK, NPJ Breast Cancer 2021)","type_of_cancer_id":"mixed","sample_count":17,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=mixed_msk_tcga_2021"}]}

═ answer (success)
Several TCGA Breast Invasive Carcinoma studies match your question. Which one do you want me to use?

- Breast Invasive Carcinoma (TCGA, PanCancer Atlas), `brca_tcga_pan_can_atlas_2018`, 1,084 samples
- Breast Invasive Carcinoma (TCGA, Firehose Legacy), `brca_tcga`, 1,108 samples
- Breast Invasive Carcinoma (TCGA, Nature 2012), `brca_tcga_pub`, 825 samples
- Breast Invasive Carcinoma (TCGA, Cell 2015), `brca_tcga_pub2015`, 818 samples
- Invasive Breast Carcinoma (TCGA GDC, 2025), `brca_tcga_gdc`, 1,102 samples

The PanCancer Atlas study is the usual default. You can also tell me to run all of them.

I'll rank genes by the difference in mean log2 mRNA expression between TP53-mutated and non-mutated samples. I'll report the group sizes and expression values, but not p-values. To test significance, use the Group Comparison mRNA tab in cBioPortal, which applies a t-test with multiple-testing correction.