Papers
- Learning maximally spanning representations improves protein function annotationRECOMB, 2025 (accepted)
- Rewiring protein sequence and structure generative models to enhance protein stability predictionRECOMB, 2025 (accepted)
- BioDolphin as a comprehensive database of lipid–protein binding interactionsCommunications Chemistry, 2024
- Machine learning-guided co-optimization of fitness and diversity facilitates combinatorial library design in enzyme engineeringNature Communications, 2024
- Opportunities and challenges of graph neural networks in electrical engineeringNature Reviews Electrical Engineering, 2024
- Leveraging conformal prediction to annotate enzyme function space with limited false positivesPLOS Computational Biology, 2024
- Contrastive Fitness Learning: Reprogramming Protein Language Models for Low-N Learning of Protein Fitness LandscapeRECOMB, 2024
- Calibrated geometric deep learning improves kinase-drug binding predictionsNature Machine Intelligence, 2023
- LinkerNet: Fragment Poses and Linker Co-Design with 3D Equivariant DiffusionNeurIPS, 2023 (Spotlight)
- Supervised biological network alignment with graph neural networksISMB, 2023
- Metabolic activity organizes olfactory representationseLife, 2023
- Enzyme function prediction using contrastive learningScience, 2023
- Sensing the shape of functional proteins with topologyNature Computational Science, 2023 (News & Views)
- Interpretable Geometric Deep Learning via Learnable Randomness InjectionICLR, 2023
- Contrastive learning of protein representations with graph neural networks for structural and functional annotationsPSB, 2023
- Next Decade’s AI-Based Drug Development Features Tight Integration of Data and ComputationHealth Data Science, 2022 (Perspective)
- scPretrain: multi-task self-supervised learning for cell-type classificationBioinformatics, 2022
- ECNet is an evolutionary context-integrated deep learning framework for protein engineeringNature Communications, 2021
- Deep geometric representations for modeling effects of mutations on protein-protein binding affinityPLoS computational biology, 2021
- Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patientsNature Cancer, 2021
- Crowdsourced mapping of unexplored target space of kinase inhibitorsNature Communications, 2021
- An integrative drug repositioning framework discovered a potential therapeutic agent targeting COVID-19Signal Transduction and Targeted Therapy, 2021
- Evolutionary context-integrated deep sequence modeling for protein engineeringRECOMB, 2020
- Characterization of SARS-CoV-2 viral diversity within and across hostsbioRxiv:2020.05.07.083410, 2020
- STAIR 2.0: A Generic and Automatic Algorithm to Fuse Modis, Landsat, and Sentinel-2 to Generate 10 m, Daily, and Cloud-/Gap-Free Surface Reflectance ProductRemote Sensing, 2020
- Deriving high-spatiotemporal-resolution leaf area index for agroecosystems in the U.S. Corn Belt using Planet Labs CubeSat and STAIR fusion dataRemote Sensing of Environment, 2020
- Integrating Deep Neural Networks and Symbolic Inference for Organic Reactivity PredictionchemRxiv:11659563, 2020
- Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement LearningarXiv:1905.13420, 2019
- DeepMask: An algorithm for cloud and cloud shadow detection in optical satellite remote sensing images using deep residual networkarXiv:1911.03607, 2019
- Integrating thermodynamic and sequence contexts improves protein-RNA binding predictionPLoS computational biology, 2019 (Presented at GLBIO’19)
- Mitigating Data Scarcity in Protein Binding Prediction Using Meta-LearningRECOMB, 2019
- Metagenomic binning through low-density hashingBioinformatics, 2018
- STAIR: A generic and fully-automated method to fuse multiple sources of optical satellite data to generate a high-resolution, daily and cloud-/gap-free surface reflectance productRemote Sensing of Environment, 2018
- Deciphering Signaling Specificity with Deep Neural NetworksRECOMB, 2018
- Large-scale integration of heterogeneous pharmacogenomic data for identifying drug mechanism of actionPSB, 2018
- A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous informationNature communications, 2017 (Extended version of the RECOMB’17 paper)
- A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous informationRECOMB, 2017
- Low-density locality-sensitive hashing boosts metagenomic binningRECOMB, 2016