Olatomiwa O. Bifarin

PubMedBERT embeddings of 80,656 metabolomics abstracts, projected with t-SNE and grouped into 20 GPT-4o mini-labelled topics, map the field's domains and trends (1998 to early 2024), browsable online.

This paper develops an AutoML-XAI pipeline for metabolomics data, improving cancer diagnostics by combining automated machine learning with explainable AI techniques.

This study identifies a distinct lipidome signature in Korean women with ovarian cancer, showing early-stage alterations and a predictive panel of 17 lipids with 85% accuracy.

The paper compares SHAP and VIP for interpreting ML models in metabolomics, finding SHAP provides deeper explanations than VIP.