Q (sonnet): show me gbm with mgmt hypermethylation

▶ list_studies
{
 "search": "glioblastoma"
}

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

◀ result
{"result":[{"cancer_study_identifier":"gbm_tcga","name":"Glioblastoma Multiforme (TCGA, Firehose Legacy)","type_of_cancer_id":"difg","sample_count":619,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=gbm_tcga"},{"cancer_study_identifier":"gbm_tcga_gdc","name":"Glioblastoma Multiforme (TCGA GDC, 2025)","type_of_cancer_id":"difg","sample_count":611,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=gbm_tcga_gdc"},{"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":"gbm_tcga_pub2013","name":"Glioblastoma (TCGA, Cell 2013)","type_of_cancer_id":"difg","sample_count":577,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=gbm_tcga_pub2013"},{"cancer_study_identifier":"gbm_tcga_pub","name":"Glioblastoma (TCGA, Nature 2008)","type_of_cancer_id":"difg","sample_count":206,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=gbm_tcga_pub"},{"cancer_study_identifier":"gbm_cptac_2021","name":"Glioblastoma (CPTAC, Cell 2021)","type_of_cancer_id":"difg","sample_count":99,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=gbm_cptac_2021"},{"cancer_study_identifier":"gbm_columbia_2019","name":"Glioblastoma (Columbia, Nat Med. 2019)","type_of_cancer_id":"difg","sample_count":42,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=gbm_columbia_2019"},{"cancer_study_identifier":"gbm_iatlas_prins_2019","name":"Glioblastoma (Randomized Clinical Trial, Nat Med. 2019) - iAtlas Harmonized","type_of_cancer_id":"adifg","sample_count":30,"has_guide":false,"url":"https://www.cbioportal.org/study/summary?id=gbm_iatlas_prins_2019"}]}

◀ 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)

▶ get_study_guide
{
 "study_id": "gbm_tcga_pan_can_atlas_2018"
}

▶ clickhouse_list_table_columns
{
 "table": "clinical_attribute_counts"
}

◀ result
# Glioblastoma Multiforme (TCGA, PanCancer Atlas)

**Study ID:** `gbm_tcga_pan_can_atlas_2018`

See `_tcga_pancan_template.md` for common TCGA clinical attributes.

## Study-Specific Attributes

### Molecular Classification
| Attribute | Description | Values (patients) |
|-----------|-------------|--------|
| `SUBTYPE` | TCGA glioma IDH classification | `GBM_IDHwt` 114, `GBM_IDHmut-non-codel` 7, `GBM` 5, blank 459 |

`SUBTYPE` is blank for most patients and does not hold the transcriptional subtypes (Classical/Mesenchymal/Proneural/Neural).

### Not available in this study
- **IDH status**: no `IDH_STATUS` attribute. Use IDH1/IDH2 mutations from mutation data (covers all sequenced samples), or `SUBTYPE` for the 121 classified patients.
- **MGMT promoter methylation status**: not available (the methylation profiles are CpG-probe level, with no MGMT status call).
- **Karnofsky performance status and extent of resection**: not available.

## Key Genes & Pathways
- **TP53**: Frequently mutated
- **PTEN**: Common deletions
- **EGFR**: Amplified in ~40%, often with EGFRvIII variant
- **IDH1**: R132H mutation defines IDH-mutant subtype (better prognosis)
- **RB pathway**: CDKN2A deletion, CDK4 amplification, RB1 mutation (often mutually exclusive)

## Notes
- IDH-mutant GBMs have significantly better prognosis
- MGMT methylation predicts temozolomide response
- EGFR amplification and EGFRvIII are GBM-specific
- Molecular subtypes have distinct transcriptional programs


◀ result
{"columns":[]}

▶ clickhouse_run_select_query
{
 "query": "SELECT cancer_study_identifier, attribute_name, count(DISTINCT sample_unique_id) AS n
FROM clinical_data_derived
WHERE cancer_study_identifier IN ('gbm_tcga','gbm_tcga_gdc','gbm_tcga_pub2013','gbm_tcga_pub','gbm_cptac_2021','gbm_columbia_2019')
  AND upper(attribute_name) LIKE '%MGMT%'
GROUP BY cancer_study_identifier, attribute_name
ORDER BY cancer_study_identifier"
}

◀ result
{"rows":[{"cancer_study_identifier":"gbm_tcga_pub2013","attribute_name":"MGMT_STATUS","n":577}]}

▶ clickhouse_run_select_query
{
 "query": "SELECT attribute_value, count(DISTINCT sample_unique_id) AS n
FROM clinical_data_derived
WHERE cancer_study_identifier = 'gbm_tcga_pub2013'
  AND attribute_name = 'MGMT_STATUS'
GROUP BY attribute_value
ORDER BY n DESC"
}

◀ result
{"rows":[{"n":227},{"attribute_value":"UNMETHYLATED","n":180},{"attribute_value":"METHYLATED","n":170}]}

▶ resolve_and_route
{
 "studyIds": [
  "gbm_tcga_pub2013"
 ]
}

◀ result
{"success":true,"message":"Found 1 study. Use the metadata to call the appropriate navigation tool(s).","data":{"totalCount":1,"studiesWithMetadata":[{"studyId":"gbm_tcga_pub2013","name":"Glioblastoma (TCGA, Cell 2013)","sampleCount":577,"studyViewUrl":"https://www.cbioportal.org/study?id=gbm_tcga_pub2013","metadata":{"clinicalAttributeIds":["AGE","CANCER_TYPE","CANCER_TYPE_DETAILED","DFS_MONTHS","DFS_STATUS","EXPRESSION_SUBTYPE","FRACTION_GENOME_ALTERED","G_CIMP_METHYLATION","IDH1_MUTATION","METHYLATION_STATUS","MGMT_STATUS","MUTATION_COUNT","ONCOTREE_CODE","OS_MONTHS","OS_STATUS","SAMPLE_COUNT","SAMPLE_TYPE","SEX","SOMATIC_STATUS","THERAPY","TMB_NONSYNONYMOUS"],"molecularProfileIds":["gbm_tcga_pub2013_gistic","gbm_tcga_pub2013_linear_CNA","gbm_tcga_pub2013_mutations","gbm_tcga_pub2013_protein_quantification","gbm_tcga_pub2013_protein_quantification_zscores","gbm_tcga_pub2013_rna_seq_v2_mrna","gbm_tcga_pub2013_rna_seq_v2_mrna_median_Zscores","gbm_tcga_pub2013_rna_seq_v2_mrna_median_all_sample_Zscores"],"heatmapProfileIds":["gbm_tcga_pub2013_protein_quantification_zscores","gbm_tcga_pub2013_rna_seq_v2_mrna_median_Zscores","gbm_tcga_pub2013_rna_seq_v2_mrna_median_all_sample_Zscores"],"availableComparisonTabs":["overlap","clinical","survival","alterations","mutations","mrna","protein"]}}]}}

▶ navigate_to_study_view
{
 "studyIds": [
  "gbm_tcga_pub2013"
 ],
 "filterJson": {
  "clinicalDataFilters": [
   {
    "attributeId": "MGMT_STATUS",
    "values": [
     {
      "value": "METHYLATED"
     }
    ]
   }
  ]
 }
}

◀ result
{"success":true,"message":"Navigating to https://www.cbioportal.org/study/summary?id=gbm_tcga_pub2013#filterJson=%7B%22clinicalDataFilters%22%3A%5B%7B%22attributeId%22%3A%22MGMT_STATUS%22%2C%22values%22%3A%5B%7B%22value%22%3A%22METHYLATED%22%7D%5D%7D%5D%7D","url":"https://www.cbioportal.org/study/summary?id=gbm_tcga_pub2013#filterJson=%7B%22clinicalDataFilters%22%3A%5B%7B%22attributeId%22%3A%22MGMT_STATUS%22%2C%22values%22%3A%5B%7B%22value%22%3A%22METHYLATED%22%7D%5D%7D%5D%7D","data":{"studyIds":["gbm_tcga_pub2013"],"studies":[{"studyId":"gbm_tcga_pub2013","name":"Glioblastoma (TCGA, Cell 2013)","sampleCount":577}],"tab":"summary","hasFilters":true,"hasPlotsConfig":false,"pageDescription":"Overview of all study data displayed as interactive charts summarizing available clinical and genomic data. Click within a chart to filter. Additional charts may be available in the Charts menu."}}

═ answer (success)
[View GBM cohort filtered to MGMT-methylated (hypermethylated) samples](https://www.cbioportal.org/study/summary?id=gbm_tcga_pub2013#filterJson=%7B%22clinicalDataFilters%22%3A%5B%7B%22attributeId%22%3A%22MGMT_STATUS%22%2C%22values%22%3A%5B%7B%22value%22%3A%22METHYLATED%22%7D%5D%7D%5D%7D)

This opens the **Glioblastoma (TCGA, Cell 2013)** study filtered to the 170 samples with `MGMT_STATUS = METHYLATED` (out of 350 with a called status; 577 total in the study). From there you can explore clinical distributions, mutations, and outcomes for this subgroup interactively, or use the Comparison tools to contrast methylated vs. unmethylated groups.