This paper proposes an unsupervised framework using large language models to compare SARS-CoV-2 protein sequences, showing improved clustering performance for emerging variants.

bioRxiv · Dec 16, 2024 · PreprintBioinformatics

Identification and prediction of Parkinson's disease subtypes and progression using machine learning in two cohorts.

Anant Dadu, Vipul K. Satone, Rachneet Kaur, Sayed Hadi Hashemi, Hampton L. Leonard, Hirotaka Iwaki, Mary B. Makarious, Kimberley J. Billingsley, Sara Bandrés‐Ciga, Lana J. Sargent, Alastair John Noyce, Ali Daneshmand, Cornelis Blauwendraat, KENNETH L. MAREK, Sonja W. Scholz, , Faraz Faghri

This study uses machine learning to identify Parkinson's disease subtypes and predict progression in two cohorts, finding three subtypes with distinct progression rates and high prediction accuracy.

npj Parkinson s Disease · Dec 16, 2022Peer-reviewedBioinformatics

Classifying COVID-19 variants based on genetic sequences using deep learning models

Sayantani Basu, Roy H. Campbell

This paper proposes an alignment-free LSTM model for classifying 20 COVID-19 variants using k-mer sequences, achieving up to 92.5% test accuracy with one-vs-all classifiers.

Springer series in reliability engineering · Jul 25, 2022Peer-reviewedBioinformatics

Multi-Modality Machine Learning Predicting Parkinsons Disease

Mary B. Makarious, Hampton L. Leonard, Dan Vitale, Hirotaka Iwaki, Lana J. Sargent, Anant Dadu, Ivo Violich, Elizabeth D. Hutchins, David Saffo, Sara Bandrés‐Ciga, Jonggeol Jeff Kim, Yeajin Song, Melina Maleknia, Matt Bookman, Willy Nojopranoto, , Mike A. Nalls

This paper develops an automated ML model to predict Parkinson's Disease using multi-modal data, achieving high AUC scores and constructing gene networks relevant to PD.

npj Parkinson s Disease · Apr 1, 2022Peer-reviewedGenomics

Application of Aligned-UMAP to longitudinal biomedical studies

Anant Dadu, Vipul K. Satone, Rachneet Kaur, Mathew J. Koretsky, Hirotaka Iwaki, Yue Andy Qi, Daniel M. Ramos, Brian Avants, Jacob Y. Hesterman, Roger N. Gunn, Mark Cookson, Michael Emmerson Ward, Andrew Singleton, Roy H. Campbell, Mike A. Nalls, Faraz Faghri

This paper applies Aligned-UMAP to longitudinal biomedical datasets to reveal time-dependent patterns and provides best practices for its use.

Patterns · Jan 1, 2022Peer-reviewedBioinformatics

Predicting Alzheimer's disease progression trajectory and clinical subtypes using machine learning

Vipul K. Satone, Rachneet Kaur, Anant Dadu, Hampton L. Leonard, Hirotaka Iwaki, Mary B. Makarious, Lana J. Sargent, Alzheimer’s Disease Neuroimaging Initiative, Ali Daneshmand, Sonja W. Scholz, Andrew Singleton, Mike A. Nalls, Roy H. Campbell, Faraz Faghri

This paper uses machine learning to predict Alzheimer's disease progression rates and classify clinical subtypes based on early clinical data.

bioRxiv · Aug 26, 2020 · PreprintNeuroscience

Analysis and Prediction of Unplanned Intensive Care Unit Readmission using Recurrent Neural Networks with Long Short-Term Memory

Yu-Wei Lin, Yuqian Zhou, Faraz Faghri, Michael J. Shaw, Roy H. Campbell

This paper uses LSTM-based RNNs to predict ICU readmissions from EHR data, achieving higher sensitivity and AUC than traditional methods.

PLoS ONE · Jul 8, 2019Peer-reviewedBioinformatics

Predicting onset, progression, and clinical subtypes of Parkinson disease using machine learning

Faraz Faghri, Sayed Hadi Hashemi, Hampton L. Leonard, Sonja W. Scholz, Roy H. Campbell, Mike A. Nalls, Andrew Singleton

This study uses machine learning to identify Parkinson disease subtypes and predict progression, finding three distinct subtypes with accurate progression predictions.

bioRxiv · Jun 5, 2018 · PreprintNeuroscience