BioinfoMachineLearning
The research in Dr. Jianlin (Jack) Cheng's BML lab at the University of Missouri-Columbia focuses on developing machine learning, deep learning, and artificial intelligence (AI) methods to analyze biological and medical data and address fundamental problems in biological and medical sciences. Currently, we are developing bioinformatics algorithms and tools for protein structure, interaction, and function prediction, protein and drug design, biological network modeling, and omics data analysis. Our research is funded by the National Institutes of Health (NIH), the National Science Foundation (NSF), the Department of Energy (DOE), and the US Department of Agriculture (USDA).
Our AI and bioinformatics tools, web services, and datasets are freely available. Our MULTICOM suite for the prediction of protein structure and structural features were ranked among the best methods in the last several community-wide biennial Critical Assessments of Techniques for Protein Structure Prediction (CASP7, 8, 9, 10, 11, 12, 13, 14, 15, and 16) in 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020, 2022, and 2024), respectively.
The citations to our research papers according to Google Scholar
In 2024, during the latest CASP16 competition, our MULTICOM predictors were ranked among the top in five major categories: (a) protein complex structure prediction (no. 1 in Phase 0 prediction without stoichiometry information, (b) Phase 1 protein complex structure prediction with stoichiometry information (no. 3), (c) tertiary structure prediction (no. 2), (d) protein model accuracy estimation (no. 2 in global fold accuracy estimation and no. 1 in ranking homo-multimer structures), and (e) protein-ligand structure (pose) and binding affinity prediction (no. 5).
Popular repositories Loading
-
bio-diffusion bio-diffusion Public
A geometry-complete diffusion generative model (GCDM) for 3D molecule generation and optimization. (Nature CommsChem)
-
DeepInteract DeepInteract Public
A geometric deep learning framework (Geometric Transformers) for predicting protein interface contacts. (ICLR 2022)
Repositories
- MULTICOM4 Public
The MULTICOM4 protein structure prediction system developed by the Bioinformatics and Machine Learning Lab at the University of Missouri - Columbia
- denoisecryodata Public
The dataset for training machine learning methods to denoise cryo-EM density maps
- PoseBench Public
Comprehensive benchmarking of protein-ligand structure prediction methods. (Nature Machine Intelligence)
- deep-learning-hpc-project-template Public
A PyTorch Lightning project template adapted for high-performance computing clusters such as Summit and Fugaku
- CAF3 Public
Engineering Multiple Sequence Alignments and Templates to Improve AlphaFold3 for Protein and Ligand Structure Prediction
- PSBench Public
A large and comprehensive benchmark for estimating the accuracy of protein complex structural models
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…