Nam D. Nguyen | Carnegie Mellon University

About

I am a Lane Fellow at the Computational Biology Department in School of Computer Science at Carnegie Mellon University, working with Professor Ziv Bar-Joseph. Previously, I was a research fellow in the Daifeng Wang Laboratory at the Waisman Center, University of Wisconsin-Madison. I earned my PhD in Computer Science from Stony Brook University .

My current research interest lies in machine learning on graphs and manifolds, and their applications for understanding molecular mechanisms and improving genotype-phenotype predictions in complex biological systems. Additionally, I am interested in the ethical, epistemological, and societal aspects of AI/ML, such as machine learning fairness, explainability in AI, data-driven scientific discoveries, and AI for social good.

[Resume]

On a personal note, I am an avid readear with a strong interest in philosophy and literature. I am also an amateur photographer.

Research Interests

Machine Learning: multiview learning, representation learning, geometric deep learning, interpretable learning, quantum machine learning, statistical learning theory
Network Science: link prediction, network diffusion, network embedding, network curvatures, social & bilogiccal network analysis
Bioinformatics: computational genomics, single-cell multiomics, gene & genome regulation, precision medicine, neurobiology

News

[January 2022] Our deepManReg is published in Nature Computational Science. This new method solves the trade-off between nonlinear and parametric manifold alignment and learns cross-modal manifolds as a feature graph for improving phenotype prediction and prioritizing multi-modal features & links. News & Views about this work is here .
[June 2021] I successfully defend my Ph.D. dissertation.
[April 2021] I am awarded the Ray and Stephanie Lane Fellowship from School of Computer Science, Carnegie Mellon University, supporting scientists of outstanding intellect who are dedicated to a career at the interface of computational and biological sciences.
[April 2021] I am selected for the PostDoc-Net-AI Fellowship 2021, a DAAD initiative funded by the Federal Ministry for Education and Research, bringing together young international researchers to visit the German hotspots in AI and to set the base for collaborations and career opportunities in AI and ML.
[Dec 2020] I pass my thesis proposal defense on Interpretable Multiview Learning for Understanding Functional Multiomics.
[Nov 2020] I give an oral presentation in RECOMB RSG 2020.
[Nov 2020] Our paper on a generative model for revealing gene regulatory mechanisms is published in Bioinformatics.
[Oct 2020] Our paper on an interpretable deep architecture for genotype-phenotype interactions is published in Bioinformatics.

Journal Publications

*joint first authorship

A deep manifold-regularized learning model for improving phenotype prediction from multi-modal data
Nam D. Nguyen, Jiawei Huang, Daifeng Wang
Nature Computational Science (2022), 2, 38–46, https://doi.org/10.1038/s43588-021-00185-x
News & Views
ECMarker: interpretable machine learning model identifies gene expression biomarkers predicting clinical outcomes and reveals molecular mechanisms of human disease in early stages
Ting Jin*, Nam D. Nguyen*, Flaminia Talos, Daifeng Wang
Bioinformatics (2020), btaa935, https://doi.org/10.1093/bioinformatics/btaa935.
[PDF] [Code]
Varmole: a biologically drop-connect deep neural network model for prioritizing disease risk variants and genes
Nam D. Nguyen, Ting Jing, Daifeng Wang
Bioinformatics (2020), btaa866, https://doi.org/10.1093/bioinformatics/btaa866.
[PDF] [Code]
Multiview learning for understanding functional multiomics
Nam D. Nguyen, Daifeng Wang
PLOS Computational Biology 16.4 (2020), e1007677, https://doi.org/10.1371/journal.pcbi.1007677.
[PDF]
ManiNetCluster: a novel manifold learning approach to reveal the functional links between gene networks
Nam D. Nguyen, Ian K. Blaby, Daifeng Wang
BMC Genomics 20.12 (2019), pp. 1–14, https://doi.org/10.1186/s12864-019-6329-2.
[PDF] [Code]

Selected Talks

Varmole: a biologically drop-connect deep neural network model for prioritizing disease risk variants and genes
The 13th annual RECOMB/ISCB Conference on Regulatory & Systems Genomics with DREAM Challenges. RECOMB RSG DREAM 2020. [Slides]
Multiview learning for understanding functional multiomics
The 28th Conference on Intelligent Systems for Molecular Biology. ISMB 2020. [Slides] [Poster]
ManiNetCluster: a novel manifold learning approach to reveal the functional links between gene networks
International Conference on Intelligent Biology and Medicine. ICIBM 2019.
Columbus, OH, USA, June 9-11, 2019 [Slides]

Activities

Mentor for CSIRE (Computer Science and Informatics Summer Research Experience Program), 2018.
TA for CSE114: Introduction to Object-Oriented Programming, 2017.
TA for CSE101: Computer Science Principles, 2016.