Machine Learning Computational Biology

Zeiberg - * of *

Daniel L. Zeiberg, PhD

609-***-**** *.*******@************.*** linkedin.com/in/danielzeiberg SUMMARY

Machine learning expert with 8+ years of experience addressing complex and nuanced computational biology challenges. Specialized in training and deploying calibrated machine learning models tailored for managing complex and biased datasets to elucidate the functional and phenotypic effects of genetic variants. Passionate and eager to leverage expertise to tackle intricate problems in computational biology and medicine.

EDUCATION

Northeastern University, Boston, MA 09/2018 - 12/2024 PhD, Computer Science

Thesis: Learning Calibrated Classifiers from Nonrepresentative Data University of Michigan, Ann Arbor, MI 08/2014 - 04/2018 Bachelor of Science, Computer Science Minor, Statistics

• Summa cum laude, University of Michigan Engineering Honors College

• Engineering honors societies: Tau Beta Pi, Eta Kappa Nu Awards: Most Likely to Have Transformative Scientific Impact - Michigan Institute for Data Science PROFESSIONAL EXPERIENCE

Northeastern University, Boston, MA

Postdoctoral Researcher, Institute for Experiential AI 01/2025 - Present

• Pioneering novel deep learning approaches for protein design and function prediction, leveraging advanced protein structure analysis and language models

• Mentored PhD students in computational biology research projects Northeastern University, Boston, MA

PhD Candidate, Computer Science 09/2018 - 12/2024

• Collaborated with experimentalists to develop a probabilistic model for quantifying variant-level evidence strengths of functional assays in clinical variant classification

• Presented computational models and insights on variant interpretation to audiences with biology and chemistry backgrounds

• Published fast positive-unlabeled class prior estimation algorithm achieving 40% performance improvement with Python and Matlab open-source implementations, used in developing clinical variant classification guidelines

• Trained deep learning models to associate genetic variants with rare diseases, improving classification accuracy by 17%.

• Led a machine learning and computational biology bootcamp teaching 21 undergraduate and high-school students the principles in training machine learning models to classify genetic variants

• Implemented an end-to-end pipeline using sequence-based variant classification models and gene-phenotype association networks to identify the genetic variant causing rare diseases in 30 families

• Trained deep-learning-based sequence-to-sequence models using PyTorch and TensorFlow to forecast spatiotemporal data University of Michigan, Ann Arbor, MI

Undergraduate Researcher 05/2017 - 07/2018

• Devised a state-of-the-art machine learning model to identify hospital patients at risk for developing acute respiratory distress syndrome

TECHNICAL STRENGTHS

Languages: Python, Matlab, R, C, C++

Tools & Frameworks:

Computational Biology Resources:

TensorFlow, PyTorch, scikit-learn, high-throughput computing, MySQL ClinVar, gnomAD, dbNSFP, Ensembl VEP, BLAST

PUBLICATIONS

• Zeiberg D, Tejura M, McEwen A, Fayer S, Pejaver V, Rubin AF, et al. Gene-based calibration of high-throughput functional assays for clinical variant classification. bioRxiv 2025.04.29.651326.

• Stenton SL, O'Leary MC, Lemire G, VanNoy GE, DiTroia S, Ganesh VS, et al. Critical assessment of variant prioritization methods for rare disease diagnosis within the rare genomes project. Hum Genomics. 2024;18(1):44 Zeiberg - 2 of 2

• Jain S, Trinidad M, Nguyen TB, Jones K, Neto SD, Ge F, et al. Evaluation of enzyme activity predictions for variants of unknown significance in Arylsulfatase A. bioRxiv. 2024.05.16.594558.

• Engreitz JM, Lawson HA, Singh H, Starita LM, Hon GC, Carter H, et al. Deciphering the impact of genomic variation on function. Nature. 2024;633(8028):47-57. doi: 10.1038/s41586-024-07510-0.

• Zeiberg D, Jain S, Radivojac P, editors. Leveraging structure for improved classification of grouped biased data. Proceedings of the AAAI Conference on Artificial Intelligence; 2023.

• Chen Y, Jain S, Zeiberg D, Iakoucheva LM, Mooney SD, Radivojac P, et al. Multi-objective prioritization of genes for high-throughput functional assays towards improved clinical variant classification. Pac Symp Biocomput. 2023;28:323-34.

• Lugo-Martinez J, Zeiberg D, Gaudelet T, Malod-Dognin N, Przulj N, Radivojac P. Classification in biological networks with hypergraphlet kernels. Bioinformatics. 2021;37(7):1000-7. doi: 10.1093/bioinformatics/btaa768

• Zeiberg D, Jain S, Radivojac P, editors. Fast nonparametric estimation of class proportions in the positive-unlabeled classification setting. Proceedings of the AAAI Conference on Artificial Intelligence; 2020.

• Zeiberg D, Prahlad T, Nallamothu BK, Iwashyna TJ, Wiens J, Sjoding MW. Machine learning for patient risk stratification for acute respiratory distress syndrome. PLoS One. 2019;14(3):e0214465.

Contact this candidate