Ryann M. Perez

Computational Biochemist

Summary

Accomplished computational biochemist with over 5 years of experience translating in silico experimental techniques into real-world results. Accelerated adoption of generative AI and large language models (LLMs) in biological chemistry. Harnessed machine learning (ML), simulations, and statistical analysis in collaboration with cross-disciplinary teams to unravel complex molecular mechanisms. Seeking opportunities in building novel and impactful AI systems.

Education

PhD Candidate, Computational Biochemistry

University of Pennsylvania | GPA: 3.99

Expected March 2026

Bachelor of Science, Chemistry (Minor: Biochemistry)

University of Delaware | GPA: 3.72

May 2020

Research Experience

Graduate Researcher

University of Pennsylvania, Lab of Dr. E. James Petersson

Sept 2020 - Present
  • Crafted custom LLMs to achieve state-of-the-art performance on biologic aggregation and protein stability; scaled LLM for inference on 64 million datapoints
  • Trained students to use a novel LLM system for biological chemistry Q&A tasks, adopted by faculty for recurrent use
  • Constructed machine learning pipelines to predict ligand affinity toward alpha-synuclein fibrils
  • Enhanced productivity by creating custom Python software packages for experimental analysis, drug discovery, and protein simulations

Selected Awards & Presentations

  • NIH F31 Predoctoral Fellowship - Awarded for original proposal on amyloid polymorphism determination assay (Sept 2024)
  • University of Pennsylvania Dean's Scholar - Given to 20 students for outstanding academic achievement (April 2024)
  • Lectures on Generative AI in Chemistry - Seminars attended by 50+ professionals on ChatGPT in chemistry workflows (May 2025)
  • Invited Lecture, Temple University - Deep learning lecture for biochemistry audience (April 2024)

Technical Skills

Programming & ML

PythonPyTorchTensorFlowHuggingFacescikit-learnLLMsTransformersDiffusion ModelsRAGFine-tuningMulti-GPU TrainingAWS

Computational Chemistry

Virtual ScreeningRosetta/PyRosettaPyMOLADMET PredictionMolecular Simulations

Wet Lab

LC-MSHPLCNMRProtein ExpressionMALDI-TOFPeptide Synthesis

Selected Publications

  • Perez, R. M.; Shimogawa M.; et al. Large Language Models for Education: ChemTAsk -- An Open-Source Paradigm for Automated Q&A in the Graduate Classroom. Comput. Educ.: Artif. Intel. Accepted
  • Li, X.; Perez, R. M.; Mach, R. H.; Giannakoulias, S.; Petersson, E. J. Machine Learning Prediction of Multiple Distinct High-Affinity Chemotypes for α-Synuclein Fibrils. Chem. Commun. 2026
  • Li, X.; Perez, R. M.; et al. Accurate Prediction of Protein Tertiary and Quaternary Stability Using Fine-Tuned Protein Language Models. Int. J. Mol. Sci. 2025
  • Perez, R. M.; Li, X.; Petersson, E. J.; Giannakoulias, S. AggBERT: Best in Class Prediction of Hexapeptide Amyloidogenesis with a Semi-Supervised ProtBERT Model. J. Chem. Inf. Model. 2023
View all publications on Google Scholar →