depressionbarbu / config.json
lucascamillomd's picture
Correct publication references, input guidance and output units
6045161 verified
Raw History Blame Contribute Delete
1.43 kB
{
"approved_by_author": "\u231b",
"citation": "Barbu, Miruna C., et al. \"Epigenetic prediction of major depressive disorder.\" Molecular Psychiatry 26.9 (2021): 5112-5123.",
"citations": 93,
"citations_date": "2026-10-02",
"clock_name": "depressionbarbu",
"data_type": "DNA methylation",
"doi": "https://doi.org/10.1038/s41380-020-0808-3",
"journal": "Molecular Psychiatry",
"last_author": "Andrew M. McIntosh",
"model_type": "LASSO regression",
"n_features": 196,
"notes": "Blood methylation risk score for major depressive disorder, fitted with LASSO in 1,223 cases and 1,824 controls. The training outcome was MDD status residualized for age, sex and ten genetic principal components. The paper used dasen-normalized M-values, with training methylation additionally adjusted for relatedness, blood-cell composition and processing batch. The packaged linear model does not perform those input transformations or adjustments; raw beta values are not the published training input. Its output is a unitless score, not a depression probability or a classifier of prevalent versus incident disease.",
"platform": [
"Illumina EPIC"
],
"population": "adults",
"predicts": [
"major depressive disorder"
],
"research_only": null,
"species": "Homo sapiens",
"tissue": [
"whole blood"
],
"training_target": [
"major depressive disorder"
],
"unit": [
"unitless"
],
"version": "0.5.7",
"year": 2021
}