Assistant Professor at Rensselaer Polytechnic Institute
City of Troy, New York, United States
Join Prog.AI to see contacts
Join Prog.AI to see contacts
Summary
🤩
Rockstar
🎓
Top School
Tianfan Fu is an Assistant Professor and machine learning researcher with 12 years of experience bridging academic research and open-source engineering in AI for drug discovery. Based at RPI and affiliated with Georgia Tech, he holds a PhD in Computer Science and has deep expertise in molecular ML, probabilistic/Bayesian methods, and graph neural networks. His open-source contributions include integrating MPNN models into the DeepPurpose toolkit and extending the Therapeutics Data Commons (TDC) backend with SMILES processing and oracle scoring—work that directly supports drug-target and molecular generation research. Tianfan combines rigorous research (speech, recommendation, Bayesian computation) with practical engineering, frequently shipping tested backend and data-processing code for scientific toolkits. Colleagues value his ability to turn complex model architectures into reusable, production-ready components that accelerate AI4drug workflows.
12 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD, CS, Doctor of Philosophy - PhD, CS at Georgia Institute of Technology
Master's degree, Computer Science and Technology, Master's degree, Computer Science and Technology at Shanghai Jiao Tong University
A Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)
Role in this project:
ML Engineer & Data Scientist
Contributions:1 review, 206 commits, 96 pushes in 2 years
Contributions summary:Tianfan implemented and integrated a Message Passing Neural Network (MPNN) model into the DeepPurpose toolkit, which involved significant code modifications to existing modules (models.py, utils.py, encoders.py) to handle new feature extraction. The user also made modifications to the data processing, including using the MPNN and handling its unique data structures. The user also contributed to setting up the data loading/preprocessing for the MPNN model and implemented changes to the main training loop to accommodate the new model architecture.
Therapeutics Commons (TDC-2): Multimodal Foundation for Therapeutic Science
Role in this project:
Back-end Developer & Data Scientist
Contributions:294 commits, 24 PRs, 143 pushes in 2 years
Contributions summary:Tianfan primarily contributed to the development and maintenance of the backend code. Their work involved implementing and modifying functionality within the tdc package, specifically around the integration of molecular generation datasets and the development of associated helper functions. They also added methods to the `tdc.chem_utils` module for scoring and converting SMILES. The user showed a focus on including and testing various oracle functions and models.
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Tianfan Fu - Assistant Professor at Rensselaer Polytechnic Institute