Robert M. Raddi

Philadelphia, PA ; (267) 312-0604 ; robertraddi@gmail.com ; robraddi.github.io

Professional Summary

Machine Learning & Computational Scientist with 6+ years experience applying Bayesian inference, deep learning, molecular dyanamics, and cheminformatics to improve predictive models of biological/small molecules; published 12+ papers, 4+ software packages adopted in academia and enabled collaborations.

Skills
  • Programming: Python, C/C++, Cython, Bash (~10 yrs of experience for each)
  • Machine Learning & Deep Learning: PyTorch, generative modeling, scikit-learn, QSAR, trained models on high-dimensional biological and chemical datasets (e.g., large MD trajectories, NMR data)
  • Bayesian Inference & Statistical Inference: Bayesian model selection, maximum entropy, uncertainty quantification
  • Cheminformatics & Computational Chemistry: RDKit, OpenEye, MD/MCMC, free energy calculations, force field optimization, forward model optimization, kinetic network models
  • Tools & Platforms: Git, HPC clusters, Linux, Unix
Education

2018 - 2024
Ph.D. in Theoretical Chemistry, Temple University, Philadelphia, Pennsylvania, USA

"A Bayesian Inference/Maximum Entropy Approach for Optimization and Validation of
Empirical Molecular Models"

Advisor: Dr. Vincent Voelz

2013 - 2017
B.S in Chemistry, Temple University, Philadelphia, Pennsylvania, USA
Minor in Mathematics

Experience

2025-Present
Postdoctoral Scholar [Mentors: Andrej Šali & Rada Savic]
University of California, San Francisco, CA
  • Developing scalable Bayesian metamodeling framework to integrate multiscale models (molecular, kinetic, network) for biological systems, supporting predictive drug discovery.

2024-2025
Adjunct Research Assistant Professor [Mentor: Vincent Voelz]
Temple University, Philadelphia, PA
  • Publish, write, and conduct experiments for numerous projects involving: deep learning and generative modeling for all-purpose molecular simulations, an optimization tool for free energy calculations, and high-resolution tuning of non-natural and cyclic peptide folding landscapes against NMR measurements.

2018-2024
Graduate Researcher/Fellow [Mentor: Vincent Voelz]
Temple University, Philadelphia, PA
  • Developed Bayesian inference and maximum entropy methods that refines force field parameters, forward model parameters, and predicts peptide/protein folding stabilities with error $\lt$ 0.5 kcal/mol, advancing the accuracy of molecular simulations.
  • Above-average ranking for three SAMPL blind challenges (logP, pKa, binding free energies).

2018-2023
Teaching Assistant [Mentors: John Michel & Vincent Voelz]
Temple University, Philadelphia, PA
  • Received awards from both the university and department for exceptional teaching in Quantum Mechanics, Thermodynamics, Physical Chemistry of Biomolecules, Analytical Chemistry, and General Chemistry across various levels.

2019
Academic Intern for Computing & Statistics Summer Workshop
Temple University, Philadelphia, PA

Selected Publications ($^{\large\boldsymbol{\dagger}}$these authors contributed equally)
  1. Robert M. Raddi, Tim Marshall and Vincent A. Voelz. "Automatic Forward Model Parameterization with Bayesian Inference of Conformational Populations." APL Mach. Learn. 4, 016102 (2026), preprint; article
  2. Thi Dung Nguyen$^{\large\boldsymbol{\dagger}}$, Robert M. Raddi$^{\large\boldsymbol{\dagger}}$, and Vincent A. Voelz. "High-resolution tuning of non-natural and cyclic peptide folding landscapes against NMR measurements using Markov models and Bayesian Inference of Conformational Populations." J. Chem. Theory Comput. (2025), preprint; article
  3. Matthew F.D. Hurley$^{\large\boldsymbol{\dagger}}$, Robert M. Raddi$^{\large\boldsymbol{\dagger}}$, Jason Pattis and Vincent A. Voelz. "Expanded Ensemble Predictions of Absolute Binding Free Energies in the SAMPL9 Host-Guest Challenge." Phys. Chem. Chem. Phys., 2023,25, 32393-32406. preprint; article
  4. Robert M. Raddi, and Vincent A. Voelz. "Stacking Gaussian Processes to Improve pKa Predictions in the SAMPL7 Challenge." Journal of Computer-Aided Molecular Design 35 (2021): 953-961. preprint; article
Selected Fellowships & Awards

  • 2024 Temple University College of Science and Technology Dissertation Grant (one winner from Chem. dept.)
  • 2023 Temple University College of Science and Technology Outstanding Research Award (one winner per dept.)
  • 2023 Francis H. Case Research Award (one winner)
  • 2022 Daniel Swern Research Award (two winners)
  • 2022 Temple University College of Science and Technology Outstanding Teaching Assistant Award (one winner per dept.)
  • 2019 The Guy Allen Award for Outstanding Teaching (one winner)