Daniel Zeiberg

About

Daniel Zeiberg is a Senior Machine Learning Engineer at the Institute for Experiential AI at Northeastern University, where he develops computational methods at the intersection of machine learning and the life sciences. His research focuses on applying deep learning, probabilistic modeling, and generative AI to problems in protein design, enzyme engineering, and genetic variant interpretation. He holds a Ph.D. in Computer Science from Northeastern University’s Khoury College of Computer Sciences, where his thesis explored methods for learning calibrated classifiers from nonrepresentative data, and a B.S.E. in Computer Science from the University of Michigan.

Daniel’s work spans both foundational machine learning and translational applications in biology and medicine. He has developed structure- and sequence-based models to predict enzyme activity and identify catalytic sites, built pipelines for protein-ligand binding affinity prediction, and created statistical frameworks to convert functional assay data into clinically actionable variant classifications. His research has been published in venues including AAAI, Bioinformatics, Human Genetics, and Nature. Daniel is interested in advancing the use of deep learning to design novel proteins and to accelerate enzyme discovery for industrial and therapeutic applications, aiming to build interpretable AI systems that bridge computational predictions and experimental validation.

Research Interests

Protein Design, Enzyme Performance Optimization, Variant Interpretation, Deep Learning, Probabilistic Modeling.

Education

Ph.D. in Computer Science, Northeastern University, 2024
B.S.E. in Computer Science, University of Michigan, 2018

Selected Publications

• D. Zeiberg, M. Tejura, A.E. McEwen, S. Fayer, V. Pejaver, A.F. Rubin, L.M. Starita, D.M. Fowler, A. O’Donnell-Luria, and P. Radivojac. “Gene-based calibration of high-throughput functional assays for clinical variant classification.” bioRxiv, 2025.
• IGVF Consortium. “Deciphering the impact of genomic variation on function.” Nature 633(8028), 2024.
• D. Zeiberg, S. Jain, and P. Radivojac. “Leveraging structure for improved classification of grouped biased data.” AAAI 2023.
• J. Lugo-Martinez, D. Zeiberg, T. Gaudelet, N. Malod-Dognin, N. Przulj, and P. Radivojac. “Classification in biological networks with hypergraphlet kernels.” Bioinformatics 37(7), 2021.
• D. Zeiberg, S. Jain, and P. Radivojac. “Fast nonparametric estimation of class proportions in the positive-unlabeled classification setting.” AAAI 2020.