AI for Molecules
Machine learning and AI methods like AlphaFold and RFDiffusion have revolutionized our ability to model biomolecules like proteins and small molecules, as well as design biomolecules that can act as novel enzymes or drug compounds. As a Rosetta Commons REU intern in Professor Jeffrey J. Gray’s lab at Johns Hopkins University, I developed LambdaDockScore, a novel method for improving models for protein-protein interactions by incorporating learning to rank (LTR) machine learning approaches. Leveraging machine learning, geometric deep learning, and molecular modeling to design and understand molecular interactions, protein structures, and therapeutic compounds.
Related Publications & Presentations:
- Zhu, R., & Nishi, K. (2026). Evolutionary curriculum learning for biological sequence modeling. ICML SPIGM Workshop
- Zhu, R., Xu, D., Chu, L., & Gray, J. (2025). Improving scoring functions for protein–protein docking with LambdaLoss. Machine Learning in Structural Biology (MLSB) Workshop [Paper]
- Pan, R.*, Zhu, R.*, Lakshman, V., & Qu, F. (2025). Mutagenic: An embedding-based approach to protein masking for functional redesign. ICLR LMRL Workshop [Paper]
Agentic AI for Biomedicine
Agentic AI—AI models that can use tools, conduct multi-step reasoning, and interact with their environment—has opened up new opportunities for autonomous biomedical reasoning. As a SIBMI and KURE intern in Professor Marinka Zitnik’s lab at Harvard Medical School, I helped develop ToolUniverse, an ecosystem with 1000+ tools that allows anyone to build an AI agent for biomedicine from traditional large language models. I also helped develop TxAgent, an AI agent built on top of ToolUniverse that specializes in personalized therapeutic and treatment decision-making.
Related Publications & Presentations:
- Gao, S., Zhu, R.*, Sui, P.*, Kong, Z.*, Aldogram, S.*, et al. (2025). Democratizing AI scientists using ToolUniverse. arXiv preprint arXiv:2509.23426 [Paper, Website, GitHub]
- Gao, S., Zhu, R., Kong, Z., et al. (2025). TxAgent: An AI agent for therapeutic reasoning across a universe of tools. arXiv preprint arXiv:2503.10970 [Paper, GitHub]
- Gao, S., Zhu, R., et al. (2025). CURE-Bench: Competition on reasoning models for drug decision-making in precision therapeutics. NeurIPS Competition Track
Other Research
I have explored a number of other scientific fields, including microbial bioinformatics under Professor Vinayak Mathur, tool development for clinical assessments of hand function, and AI for ecology.
Related Publications & Presentations:
- Zhu, R., & Mathur, V. (2022). Prophages present in Acinetobacter pittii influence bacterial virulence, antibiotic resistance, and genomic rearrangements. PHAGE, 3(1), 38–49 [Paper]
- Mancini, K., Cao, I., Ge, C., Mu, E., Zhu, R., & Mathur, V. (2024). Investigating the role of phage mediated HGT in increasing bacterial virulence. Bios, 95(2), 73–78 [Paper]
- Laane, C.*, Zhu, R.*, Chandra, J., et al. (2024). Hand and wrist immobilization affects pressure in complex spiral-based drawings. Tufts Biology Research Symposium
- Zhu, R., Hou, C., & McPhie, K. (2026). BIRDGen: Multimodal conditional inference of latent unbiased species distributions. ICML SPIGM Workshop
* denotes equal contribution