Diffusion models in protein structure and docking
Citations Over TimeTop 1% of 2024 papers
Abstract
Abstract Generative AI is rapidly transforming the frontier of research in computational structural biology. Indeed, recent successes have substantially advanced protein design and drug discovery. One of the key methodologies underlying these advances is diffusion models (DM). Diffusion models originated in computer vision, rapidly taking over image generation and offering superior quality and performance. These models were subsequently extended and modified for uses in other areas including computational structural biology. DMs are well equipped to model high dimensional, geometric data while exploiting key strengths of deep learning. In structural biology, for example, they have achieved state‐of‐the‐art results on protein 3D structure generation and small molecule docking. This review covers the basics of diffusion models, associated modeling choices regarding molecular representations, generation capabilities, prevailing heuristics, as well as key limitations and forthcoming refinements. We also provide best practices around evaluation procedures to help establish rigorous benchmarking and evaluation. The review is intended to provide a fresh view into the state‐of‐the‐art as well as highlight its potentials and current challenges of recent generative techniques in computational structural biology. This article is categorized under: Data Science > Artificial Intelligence/Machine Learning Structure and Mechanism > Molecular Structures Software > Molecular Modeling
Related Papers
- Strategic Benchmarking: How to Rate Your Company's Performance against the World's Best(1993)
- → COMPARISON OF BEST PRACTICE BENCHMARKING MODELS(2011)11 cited
- → A guide for mental health clinicians to develop and undertake benchmarking activities(2010)2 cited
- Theoretical Aspects of Benchmarking Theory(2004)
- → Comparing ourselves: using benchmarking techniques to measure performance between academic libraries(2009)1 cited