A curated set of peer-reviewed work applying deep learning and machine learning to computational biology: cancer biomarker discovery, multi-cancer classification, and biomedical interpretability. Full list and live citation counts on Google Scholar.
2021
Multi-run concrete autoencoder to identify prognostic lncRNAs for 12 cancers
International Journal of Molecular Sciences, 22(21), 11919 · MDPI · Q1
Deep-learning approach (concrete autoencoder) for biomarker discovery across 12 cancer types. Finds prognostic long non-coding RNAs that survive across independent runs, giving clinicians a stable feature set.
2020
Pan-cancer feature selection and classification reveals important long non-coding RNAs
IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2020)
Machine-learning feature-selection pipeline for pan-cancer classification. Identifies a compact set of lncRNAs that distinguish tumor types, useful for diagnostic ML models on TCGA.
2020
Deep learning to discover cancer glycome genes signifying the origins of cancer
IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2020)
Deep-learning pipeline that surfaces cancer-origin glycome genes from high-dimensional expression data, bridging interpretable ML and tumor biology to point at tissue-of-origin signatures.
2020
Deep learning to discover genomic signatures for racial disparity in lung cancer
IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2020)
Deep learning surfaces genomic signals that differ between racial groups in lung cancer: a societal-impact application of ML to a healthcare-equity problem.
2019
Long non-coding RNA based cancer classification using deep neural networks
Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (ACM-BCB 2019)
End-to-end deep neural network for multi-cancer classification using lncRNA expression. Outperforms classical ML baselines on the TCGA pan-cancer dataset.
For the complete list, conference proceedings, and live citation counts, see Google Scholar.