Q (sonnet): Do samples with TP53 truncating mutations have significantly lower TP53 mRNA expression compared to wild-type samples?

▶ read_guide
{
 "uri": "cbioportal://common-pitfalls#16"
}

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

◀ result
### 16. 🚨 SILENT QUERY SUBSTITUTION ("did you mean...")

When the user's wording differs from canonical terminology (e.g. "V600V" looks like "V600E" with a typo, or "point mutation" sounds like "missense"), it is forbidden to silently rewrite the question and answer the rewritten version. Doing so produces an answer that looks confident but is for a different question — the user cannot tell what was changed.

#### ❌ Wrong: silently substitute

> User: *"Find patients in colorectal cancer with the V600V alteration in BRAF"*
> Agent: *(internally treats this as V600E)* "I found 412 samples with BRAF V600E in colorectal studies..."

> User: *"What is the most prevalent TP53 mutation in uterine cancer that is not a point mutation?"*
> Agent: *(internally treats "point mutation" = "missense", silently excludes only missense)* "The most prevalent non-missense TP53 mutation is..."

#### ✅ Correct: answer the literal question, flag any normalization

For an unusual-looking variant the user may have typed deliberately:
- Query for what was asked, literally.
- If 0 rows come back, **explain *why* zero is the expected answer** before suggesting a likely-intended alternative. For synonymous variants (e.g. BRAF V600V, TP53 R175R), the explanation is: *cBioPortal's mutation tables filter out synonymous (silent) variants in most studies, so 0 hits means "filtered upstream", not "no such variant exists in any patient"*. Then ask: *"Did you mean V600E (the canonical activating variant)? Or would you like me to look for V600V in the studies that do retain synonymous calls?"*
- If the wording is ambiguous (e.g. "point mutation"), ask the user which definition they meant before querying — do not pick one silently.

#### Mutation-type terminology mapping (use this to disambiguate)

| User says | Canonical definition | `mutation_type` filter |
|---|---|---|
| "point mutation" | Any SNV (single-nucleotide variant) — includes missense, nonsense, synonymous, splice-site SNVs | `mutation_type IN ('Missense_Mutation','Nonsense_Mutation','Silent','Splice_Site')` — **but ask the user to confirm scope first** |
| "missense" | Single amino-acid substitution that changes the protein | `mutation_type = 'Missense_Mutation'` |
| "nonsense" / "stop-gain" | Premature stop codon | `mutation_type = 'Nonsense_Mutation'` |
| "synonymous" / "silent" | Nucleotide change with no amino-acid change | `mutation_type = 'Silent'` (**often filtered out of public datasets** — see below) |
| "splice site" | Mutation in canonical splice acceptor/donor | `mutation_type = 'Splice_Site'` |
| "frameshift" | Indel changing reading frame | `mutation_type IN ('Frame_Shift_Ins','Frame_Shift_Del')` |
| "indel" / "in-frame" | In-frame insertion or deletion | `mutation_type IN ('In_Frame_Ins','In_Frame_Del')` |
| "truncating" | Anything that disrupts the protein early | `mutation_type IN ('Nonsense_Mutation','Frame_Shift_Ins','Frame_Shift_Del','Splice_Site','Nonstop_Mutation')` |

**Synonymous-variant filter. … (785 more chars)

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

◀ 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
# 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 | `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 |
| `brca_metabric` | ESR1 | PGR | `mrna` | 0.487 | 1980 |

ESR1↔PGR is the textbook breast-cancer estrogen-receptor coregula … (2785 more chars)

═ answer (success)
The user hasn't specified a study yet. This analysis (TP53 truncating mutation vs wild-type mRNA expression) is a classic, well-behaved comparison — I'll use a study with both mutation and expression data. Let me confirm with the user which cohort, but a reasonable default is a well-known TCGA PanCancer Atlas study. Let me check what's commonly used and ask, since no cancer type was specified.

Given TP53 truncating mutations are relevant across nearly all cancer types, I should ask which cohort. But per the "prefer TCGA, pick one and proceed" guidance for ambiguous asks, and since the user's question is generic, let me clarify quickly rather than picking a study arbitrarily — this is a scientific analysis, not a keyword search, so I should ask.

Which cohort would you like this analyzed in? A few options:

1. **TCGA PanCancer Atlas — pick a specific cancer type** (e.g., breast, lung adenocarcinoma, colorectal) — since TP53 truncating mutation rates and expression baselines vary substantially by tissue, pooling across all cancer types would confound the comparison.
2. A **specific study** you already have in mind.

Since TP53 is near-ubiquitously mutated across cancers but mRNA levels/tissue context differ a lot, I'd recommend picking one cancer type for a clean comparison rather than mixing cohorts. Which would you like — or should I default to a commonly used one like **breast invasive carcinoma (TCGA, PanCancer Atlas)**, which has a good sample size and both mutation + mRNA data?