leonchaox/qinyan-academic-skills/depmap

import requests
import pandas as pd
BASE_URL = "https://depmap.org/portal/api"
def depmap_get(endpoint, params=None):
    url = f"{BASE_URL}/{endpoint}"
    response = requests.get(url, params=params)
    response.raise_for_status()
    return response.json()

def get_gene_dependency(gene_symbol, dataset="Chronos_Combined"):
    """Get CRISPR dependency scores for a gene across all cell lines."""
    url = f"{BASE_URL}/gene"
    params = {
        "gene_id": gene_symbol,
        "dataset": dataset
    }
    response = requests.get(url, params=params)
    return response.json()
# Alternatively, use the /data endpoint:
def get_dependencies_slice(gene_symbol, dataset_name="CRISPRGeneEffect"):
    """Get a gene's dependency slice from a dataset."""
    url = f"{BASE_URL}/data/gene_dependency"
    params = {"gene_name": gene_symbol, "dataset_name": dataset_name}
    response = requests.get(url, params=params)
    data = response.json()
    return data

import pandas as pd
import requests, os
def download_depmap_data(url, output_path):
    """Download a DepMap data file."""
    response = requests.get(url, stream=True)
    with open(output_path, 'wb') as f:
        for chunk in response.iter_content(chunk_size=8192):
            f.write(chunk)
# DepMap 24Q4 data files (update version as needed)
FILES = {
    "crispr_gene_effect": "https://figshare.com/ndownloader/files/...",
    # OR download from: https://depmap.org/portal/download/all/
    # Files available:
    # CRISPRGeneEffect.csv - Chronos gene effect scores
    # OmicsExpressionProteinCodingGenesTPMLogp1.csv - mRNA expression
    # OmicsSomaticMutationsMatrixDamaging.csv - mutation binary matrix
    # OmicsCNGene.csv - copy number
    # sample_info.csv - cell line metadata
}
def load_depmap_gene_effect(filepath="CRISPRGeneEffect.csv"):
    """
    Load DepMap CRISPR gene effect matrix.
    Rows = cell lines (DepMap_ID), Columns = genes (Symbol (EntrezID))
    """
    df = pd.read_csv(filepath, index_col=0)
    # Rename columns to gene symbols only
    df.columns = [col.split(" ")[0] for col in df.columns]
    return df
def load_cell_line_info(filepath="sample_info.csv"):
    """Load cell line metadata."""
    return pd.read_csv(filepath)

import numpy as np
import pandas as pd
def find_selective_dependencies(gene_effect_df, cell_line_info, target_gene,
                                 cancer_type=None, threshold=-0.5):
    """Find cell lines selectively dependent on a gene."""
    # Get scores for target gene
    if target_gene not in gene_effect_df.columns:
        return None
    scores = gene_effect_df[target_gene].dropna()
    dependent = scores[scores <= threshold]
    # Add cell line info
    result = pd.DataFrame({
        "DepMap_ID": dependent.index,
        "gene_effect": dependent.values
    }).merge(cell_line_info[["DepMap_ID", "cell_line_name", "primary_disease", "lineage"]])
    if cancer_type:
        result = result[result["primary_disease"].str.contains(cancer_type, case=False, na=False)]
    return result.sort_values("gene_effect")
# Example usage (after loading data)
# df_effect = load_depmap_gene_effect("CRISPRGeneEffect.csv")
# cell_info = load_cell_line_info("sample_info.csv")
# deps = find_selective_dependencies(df_effect, cell_info, "KRAS", cancer_type="Lung")

import pandas as pd
from scipy import stats
def biomarker_analysis(gene_effect_df, mutation_df, target_gene, biomarker_gene):
    """
    Test if mutation in biomarker_gene predicts dependency on target_gene.
    Args:
        gene_effect_df: CRISPR gene effect DataFrame
        mutation_df: Binary mutation DataFrame (1 = mutated)
        target_gene: Gene to assess dependency of
        biomarker_gene: Gene whose mutation may predict dependency
    """
    if target_gene not in gene_effect_df.columns or biomarker_gene not in mutation_df.columns:
        return None
    # Align cell lines
    common_lines = gene_effect_df.index.intersection(mutation_df.index)
    scores = gene_effect_df.loc[common_lines, target_gene].dropna()
    mutations = mutation_df.loc[scores.index, biomarker_gene]
    mutated = scores[mutations == 1]
    wt = scores[mutations == 0]
    stat, pval = stats.mannwhitneyu(mutated, wt, alternative='less')
    return {
        "target_gene": target_gene,
        "biomarker_gene": biomarker_gene,
        "n_mutated": len(mutated),
        "n_wt": len(wt),
        "mean_effect_mutated": mutated.mean(),
        "mean_effect_wt": wt.mean(),
        "pval": pval,
        "significant": pval < 0.05
    }

import pandas as pd
def co_essentiality(gene_effect_df, target_gene, top_n=20):
    """Find genes with most correlated dependency profiles (co-essential partners)."""
    if target_gene not in gene_effect_df.columns:
        return None
    target_scores = gene_effect_df[target_gene].dropna()
    correlations = {}
    for gene in gene_effect_df.columns:
        if gene == target_gene:
            continue
        other_scores = gene_effect_df[gene].dropna()
        common = target_scores.index.intersection(other_scores.index)
        if len(common) < 50:
            continue
        r = target_scores[common].corr(other_scores[common])
        if not pd.isna(r):
            correlations[gene] = r
    corr_series = pd.Series(correlations).sort_values(ascending=False)
    return corr_series.head(top_n)
# Co-essential genes often share biological complexes or pathways