Q (sonnet): Can you analyze thyroid hormone gene expression by diagnosis in the Pediatric Brain Tumor Atlas (PBTA, Provisional) cohort?

▶ list_studies
{
 "search": "Pediatric Brain Tumor Atlas"
}

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

◀ result
{"result":[]}

▶ read_guide
{
 "uri": "cbioportal://clinical-data-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)

◀ result
# Clinical Data Query Guide

## Overview
Clinical data in cBioPortal is stored at both patient and sample levels. Understanding the distinction is crucial for accurate analysis.

## Data Organization

### Patient-Level vs Sample-Level Data
- **Patient-level**: Demographics, overall survival, disease stage (stored once per patient)
- **Sample-level**: Sample type, sequencing platform, purity (can have multiple per patient)

### Key Tables
- `clinical_patient`: Patient-level clinical attributes
- `clinical_sample`: Sample-level clinical attributes
- `clinical_data_derived`: Pre-joined view combining both levels
- `clinical_attribute_meta`: Metadata about available clinical attributes

## Recommended Approach: Use clinical_data_derived

The `clinical_data_derived` table is pre-joined and optimized for most queries:

```sql
-- Get clinical data for specific attributes
SELECT
    sample_unique_id,
    patient_unique_id,
    attribute_name,
    attribute_value
FROM clinical_data_derived
WHERE
    cancer_study_identifier = 'your_study_id'
    AND attribute_name IN ('CANCER_TYPE', 'SAMPLE_TYPE', 'TMB_NONSYNONYMOUS');
```

## Clinical Attribute Discovery

### Use clinical_attribute_meta for Discovering Available Attributes
**Always start here** to see what clinical attributes are available for a specific study:

```sql
-- Discover available clinical attributes for a study
SELECT
    attr_id,
    description,
    patient_attribute,
    cancer_study_id
FROM clinical_attribute_meta
WHERE
    cancer_study_id = (
        SELECT cancer_study_id
        FROM cancer_study
        WHERE cancer_study_identifier = 'your_study_id'
    )
ORDER BY patient_attribute, attr_id;
```

**Key Fields:**
- **attr_id**: matches attr_id in clinical_sample/clinical_patient tables
- **description**: human-readable description of the attribute
- **patient_attribute**: true = patient attribute, false = sample attribute
- **cancer_study_id**: links to cancer_study table (filter by study)

## Attribute Semantics and Matching

### Case-Insensitive Matching for Attribute Values

Clinical values are free text across studies and may differ only by case. For example, a controlled-looking value such as germline mutation status may appear as `GERMLINE`, `Germline`, or another case variant.

When filtering `clinical_data_derived.attribute_value`, use case-insensitive matching unless you have already profiled the exact values in the target study:

```sql
-- Correct: case-insensitive clinical value filter
SELECT DISTINCT sample_unique_id, patient_unique_id
FROM clinical_data_derived
WHERE cancer_study_identifier = 'your_study_id'
  AND attribute_name = 'MUTATION_STATUS'
  AND upper(attribute_value) = 'GERMLINE';
```

Do not write `attribute_value = 'GERMLINE'` without first checking all distinct values for that attribute in the study.

### Query the Requested Attribute, Not a Proxy

Do not infer one clinical attribute from a related subtype or marker. Query the actual requested attribute when it … (17073 more chars)

▶ list_studies
{
 "search": "PBTA"
}

▶ list_studies
{
 "search": "pediatric brain"
}

◀ result
{"result":[]}

◀ result
{"result":[{"cancer_study_identifier":"brain_cptac_2020","name":"Pediatric Brain Cancer (CPTAC/CHOP, Cell 2020)","type_of_cancer_id":"brain","sample_count":218,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=brain_cptac_2020"}]}

▶ list_studies
{
 "search": "Open Pediatric Brain"
}

◀ result
{"result":[]}

▶ list_studies
{
 "search": "brain tumor pediatric"
}

▶ list_studies
{
 "search": "provisional pediatric"
}

◀ result
{"result":[{"cancer_study_identifier":"brain_cptac_2020","name":"Pediatric Brain Cancer (CPTAC/CHOP, Cell 2020)","type_of_cancer_id":"brain","sample_count":218,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=brain_cptac_2020"}]}

◀ result
{"result":[]}

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

◀ result
# Study Resolution Guide

Use this guide when the user names a study, cohort, portal, or data source that may not exist in the connected cBioPortal deployment.

## Routing Triggers

Read this guide when the user mentions:

- PBTA, Pediatric Brain Tumor Atlas, pediatric cBioPortal, Kids First
- GENIE, AACR GENIE, MSK private cohorts, institutional cohorts
- "download study", "which study", "find cohort", "data from [portal]"
- a named cohort that `list_studies(search=...)` does not find
- HTAN, or an HTAN center (OHSU, MSK, Vanderbilt, ...)

## Core Rules

1. Resolve the requested study before substituting another study.
2. If the requested study is not in this deployment, say so explicitly.
3. Do not silently analyze a substitute cohort.
4. If the user agrees to a substitute, keep a one-line scope caveat when reporting numbers.

## Known External cBioPortal Instances

These are not necessarily queryable from this MCP server, but they are useful redirects:

| User wording | Likely external instance | Scope |
|---|---|---|
| PBTA, Pediatric Brain Tumor Atlas, pediatric brain tumors | https://pedcbioportal.kidsfirstdrc.org/ | Pediatric cancer studies, including pediatric brain tumor cohorts |
| GENIE | https://genie.cbioportal.org/ | AACR GENIE data access, depending on release and permissions |
| MSK private / institutional cohorts | private institutional cBioPortal deployments | Not queryable from public cBioPortal unless exported to the public database |

## HTAN Studies

HTAN study ids carry the atlas code (`hta9`, `hta8`, ...), and the names don't always name the center, so `list_studies(search="OHSU HTAN")` finds nothing. Search `list_studies(search="HTAN")` and match the center by atlas code:

| Atlas code | Center | Study |
|---|---|---|
| `hta8` | MSK | `crc_hta8_htan_2024` |
| `hta9` | OHSU | `brca_hta9_htan_2022` ("Breast Cancer (HTAN, 2022)") |
| `hta11` | Vanderbilt | `crc_hta11_htan_2021` |

For HTAN imaging (Minerva, MxIF, H&E), continue with the external-resources-guide.

## Study Resolution Workflow

1. Call `list_studies(search=...)` with the user's exact study/cohort phrase and close variants.
2. If a cancer type is mentioned, call `search_oncotree(search_term)` before disease-level study discovery.
3. If no matching study is found, check known external instances above before declaring the study absent.
4. If proposing a substitute, describe why it is a substitute and how its scope differs.

## Substitute-Cohort Answer Pattern

> I cannot query PBTA from this cBioPortal deployment. PBTA is typically accessed through pediatric cBioPortal at https://pedcbioportal.kidsfirstdrc.org/. I can analyze `[substitute_study_id]` here, but its results should not be interpreted as PBTA results.

When reporting numbers from a substitute:

> Scope note: these counts are from `[substitute_study_id]` in this deployment, not from the requested PBTA cohort.

## Do Not

- Do not answer a PBTA question with `brain_cptac_2020` numbers without a scope wa … (169 more chars)

═ answer (success)
This confirms it: the Pediatric Brain Tumor Atlas (PBTA) is not available in this cBioPortal deployment's database.

**PBTA is not queryable here.** The Pediatric Brain Tumor Atlas is hosted on a separate, pediatric-focused cBioPortal instance — **[Pediatric cBioPortal (Kids First DRC)](https://pedcbioportal.kidsfirstdrc.org/)** — not the public cBioPortal database I have direct query access to. I cannot pull gene expression values or clinical/diagnosis data for it from here.

A couple of options:

1. **Go directly to Pediatric cBioPortal** and search for "Pediatric Brain Tumor Atlas" or "OpenPBTA" there — it supports the same kind of expression-by-subgroup plots (via the Plots tab, grouping by diagnosis) that you're describing.
2. **If you'd like, I can run an analogous analysis in this deployment** on a substitute cohort I *do* have access to — the closest match here is [Pediatric Brain Cancer (CPTAC/CHOP, Cell 2020)](https://www.cbioportal.org/study/summary?id=brain_cptac_2020) (218 samples). This is a different cohort, not PBTA, and results would not be interpretable as PBTA findings — but I can still look at thyroid hormone-related gene expression (e.g., THRA, THRB, DIO1/2/3, TSHR, SLC16A2) by tumor diagnosis in that study if that's useful as a stand-in.

Would you like me to proceed with the CPTAC/CHOP pediatric brain cancer study as a substitute (with that scope caveat), or would you prefer to pursue PBTA directly on Pediatric cBioPortal yourself?