Q (sonnet): Help me rank TCGA cancer studies based on median CD3 expression

▶ list_guides
{}

◀ result
{"result":[{"uri":"cbioportal://mutation-frequency-guide","description":"Comprehensive guide for calculating gene mutation frequencies with gene-specific profiling denominators"},{"uri":"cbioportal://clinical-data-guide","description":"Guide for querying clinical data including patient vs sample level considerations"},{"uri":"cbioportal://sample-filtering-guide","description":"Guide for filtering samples and studies in cBioPortal queries"},{"uri":"cbioportal://common-pitfalls","description":"Guide to avoid common mistakes when querying cBioPortal data. If you already know which numbered pitfall applies, fetch just that section via read_guide(\"cbioportal://common-pitfalls#<number>\") (e.g. #16) instead of the full guide"},{"uri":"cbioportal://treatment-guide","description":"Guide for querying treatment/clinical event data including drug agents, timelines, and linking to genomic data"},{"uri":"cbioportal://faq-guide","description":"General cBioPortal FAQ: history, how to cite, data types, reference genome, abbreviations, GISTIC thresholds, API access"},{"uri":"cbioportal://statistical-tests-guide","description":"Statistical test selection guide — decision matrix for choosing Fisher's exact, Wilcoxon, chi-squared, t-test, ANOVA, etc. based on data type and group count"},{"uri":"cbioportal://gene-expression-guide","description":"Gene expression / copy-number / methylation analysis. Covers genetic_alteration_derived, profile_type discovery, and the gene_pair_coexpression view for Spearman correlation between two genes"},{"uri":"cbioportal://external-resources-guide","description":"Guide for finding external linked resources such as imaging, pathology, Minerva, HTAN, or other resource_* table links before declaring data unavailable"},{"uri":"cbioportal://gene-resolution-guide","description":"Guide for resolving ambiguous gene symbols, aliases, gene families, and shorthand such as CD3 before querying expression or alteration data"},{"uri":"cbioportal://study-resolution-guide","description":"Guide for resolving requested studies, avoiding silent substitute cohorts, and redirecting to known external cBioPortal instances when data is not in this deployment"},{"uri":"cbioportal://germline-guide","description":"Guide for querying germline variant data — storage columns, study discovery, query patterns, and somatic vs germline considerations"},{"uri":"cbioportal://study-guide/{study_id}","description":"Dynamic study-specific guide - use get_study_guide(study_id) tool to generate"}]}

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

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

◀ result
# Gene Resolution Guide

Use this guide before querying gene expression, mutation, copy-number, methylation, or structural-variant data when the user's gene term may be ambiguous.

## Routing Triggers

Read this guide when the user mentions:

- a gene family shorthand: `CD3`, `HLA`, `KRT`, `MUC`, `MT-`, `IGH`, `IGK`, `IGL`
- a marker name that may refer to multiple genes or proteins
- a gene alias, old symbol, or informal name
- a wildcard-like term such as "all CD3 genes"

These examples are not exhaustive. Apply this guide to any gene term that may resolve to multiple symbols, aliases, paralogs, family members, or marker genes.

## Core Rule

Do not silently aggregate multiple genes when the user names an ambiguous symbol. Either ask for clarification or choose a clearly standard marker and state the choice.

For example, "CD3 expression" can refer to `CD3D`, `CD3E`, or `CD3G`; in many immune-marker contexts `CD3E` is the standard marker, but the agent must not average all CD3 genes unless the user asks for a combined signature.

## Gene Discovery Query

After validating the gene table exists, search exact symbols first, then prefix/alias-like matches:

```sql
SELECT
    hugo_gene_symbol,
    entrez_gene_id
FROM gene
WHERE upper(hugo_gene_symbol) = upper('CD3')
   OR upper(hugo_gene_symbol) LIKE upper('CD3%')
ORDER BY hugo_gene_symbol
LIMIT 50;
```

If aliases are available in this deployment, inspect the relevant alias table before assuming no match. If no alias table exists, state that alias resolution is limited to available gene symbols.

## Answer Pattern

If multiple plausible genes are found:

> "CD3" is ambiguous in cBioPortal gene-symbol terms. I found `CD3D`, `CD3E`, and `CD3G`. Did you mean `CD3E` as a T-cell marker, or should I analyze all three separately?

If the user clearly asks for a combined family/signature:

- report each gene separately by default
- only compute an average/signature if the user explicitly requests it
- state exactly how the combined value was calculated

## Do Not

- Do not average multiple genes into one expression value without explicit permission.
- Do not rewrite an ambiguous symbol to a single gene without telling the user.
- Do not treat a prefix match as a validated gene symbol.


◀ 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)

▶ clickhouse_run_select_query
{
 "query": "SELECT hugo_gene_symbol, entrez_gene_id FROM gene WHERE upper(hugo_gene_symbol) LIKE 'CD3%' ORDER BY hugo_gene_symbol"
}

◀ result
{"rows":[{"hugo_gene_symbol":"CD300A","entrez_gene_id":11314},{"hugo_gene_symbol":"CD300C","entrez_gene_id":10871},{"hugo_gene_symbol":"CD300E","entrez_gene_id":342510},{"hugo_gene_symbol":"CD300H","entrez_gene_id":100130520},{"hugo_gene_symbol":"CD300LB","entrez_gene_id":124599},{"hugo_gene_symbol":"CD300LD","entrez_gene_id":100131439},{"hugo_gene_symbol":"CD300LD-AS1","entrez_gene_id":146723},{"hugo_gene_symbol":"CD300LF","entrez_gene_id":146722},{"hugo_gene_symbol":"CD300LG","entrez_gene_id":146894},{"hugo_gene_symbol":"CD302","entrez_gene_id":9936},{"hugo_gene_symbol":"CD320","entrez_gene_id":51293},{"hugo_gene_symbol":"CD33","entrez_gene_id":945},{"hugo_gene_symbol":"CD34","entrez_gene_id":947},{"hugo_gene_symbol":"CD36","entrez_gene_id":948},{"hugo_gene_symbol":"CD37","entrez_gene_id":951},{"hugo_gene_symbol":"CD38","entrez_gene_id":952},{"hugo_gene_symbol":"CD38-AS1","entrez_gene_id":143433680},{"hugo_gene_symbol":"CD3D","entrez_gene_id":915},{"hugo_gene_symbol":"CD3E","entrez_gene_id":916},{"hugo_gene_symbol":"CD3G","entrez_gene_id":917}]}

▶ list_studies
{
 "search": "pan can atlas",
 "limit": 5
}

◀ result
{"result":[{"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":"coadread_tcga_pan_can_atlas_2018","name":"Colorectal Adenocarcinoma (TCGA, PanCancer Atlas)","type_of_cancer_id":"coadread","sample_count":594,"has_guide":true,"url":"https://www.cbioportal.org/study/summary?id=coadread_tcga_pan_can_atlas_2018"},{"cancer_study_identifier":"gbm_tcga_pan_can_atlas_2018","name":"Glioblastoma Multiforme (TCGA, PanCancer Atlas)","type_of_cancer_id":"difg","sample_count":592,"has_guide":true,"url":"https://www.cbioportal.org/study/summary?id=gbm_tcga_pan_can_atlas_2018"},{"cancer_study_identifier":"ov_tcga_pan_can_atlas_2018","name":"Ovarian Serous Cystadenocarcinoma (TCGA, PanCancer Atlas)","type_of_cancer_id":"hgsoc","sample_count":585,"has_guide":true,"url":"https://www.cbioportal.org/study/summary?id=ov_tcga_pan_can_atlas_2018"},{"cancer_study_identifier":"luad_tcga_pan_can_atlas_2018","name":"Lung Adenocarcinoma (TCGA, PanCancer Atlas)","type_of_cancer_id":"luad","sample_count":566,"has_guide":true,"url":"https://www.cbioportal.org/study/summary?id=luad_tcga_pan_can_atlas_2018"}]}

═ answer (success)
Confirmed: **CD3 resolves to three distinct genes** in cBioPortal — `CD3D`, `CD3E`, and `CD3G` (the CD3 T-cell receptor complex subunits). I don't want to silently pick one or average them.

Two things I need from you before running the ranking:

**1. Which CD3 gene(s)?**
- `CD3E` — the most commonly used single-gene T-cell marker, or
- All three (`CD3D`, `CD3E`, `CD3G`) reported **separately** (default, no averaging), or
- An explicit combined/averaged CD3 signature score across all three (I'll only do this if you ask for it, and I'll state exactly how it's computed — e.g., mean of per-sample z-scores)

**2. Which "TCGA cancer studies" scope?**
- The 32 TCGA PanCancer Atlas studies (most common definition, uniformly processed, Z-scored RNA-seq available — good for cross-study ranking), or
- All TCGA-flavored studies in this portal (includes older non-PanCanAtlas TCGA builds, which could double-count some cohorts), or
- A specific subset you have in mind

My default recommendation, if you don't have a preference: **CD3E**, ranked by median across the **32 TCGA PanCancer Atlas studies** using the `mrna_median_Zscores` profile (the standard cross-study-comparable expression measure, since raw RSEM scales aren't directly comparable between tumor types). Let me know if that works or if you'd like a different gene/scope.