It offers a curated set of experimental binding data and corresponding antibody-protein complex structures.ĪntigenDB is a manually curated database of experimentally verified antigens that includes detailed information about the antigen, the source organism, and the associated antibodies.ĬAMEO (Continuous Automated Model EvaluatiOn) is a project for the automated evaluation of methods predicting macromolecular structure. It is primarily used for the development and validation of computational methods for predicting molecular interactions.ĪB-Bind is a database for antibody binding affinity data. PDBbind is a comprehensive collection of the binding data of all types of biomolecular complexes in the PDB database. It provides highly accurate predictions of protein 3D structures. These data are gathered using experimental methods such as X-ray crystallography, NMR spectroscopy, or cryo-electron microscopy.ĪlphaFoldDB is a database of protein structure predictions produced by DeepMind's AlphaFold system. The Protein Data Bank (PDB) is a database of 3D structural data of large biological molecules, such as proteins and nucleic acids. et al.Ī list of suggested protein databases, more lists at CNCB. Sampling of structure and sequence space of small protein folds Yang and Zhangyang Gao, Cheng Tan, Stan Z. Wittmann, Nicholas Bhattacharya, Samuel Goldman, Ali Madani, Kevin K.
Happy to see the work of Christian Dallago, Jody Mou, Kadina E. (Maybe should add the evaluation of protein design for deep learning method (especially deep generative model))ĭifficulties and opportunities always coexist. In terms of datasets and benchmarks, protein design is far less mature than drug discovery ( paperwithcode drug discovery benchmarks). MoleculeNet published a small molecule related benchmark four years ago. TDC maintains a resource list that currently contains 22 tasks (and its datasets) related to small molecules and macromolecules, including PPI, DDI and so on. SidechainNet: An All-Atom Protein Structure Dataset for Machine Learning Igor Melnyk, Payel Das, Vijil Chenthamarakshan, Aurelie LozanoĪlphaDesign: A graph protein design method and benchmark on AlphaFoldDB Leonardo V Castorina, Rokas Petrenas, Kartic Subr, Christopher W Woodīenchmarking deep generative models for diverse antibody sequence design PDBench: Evaluating Computational Methods for Protein-Sequence Design Paper unavailable at Machine Learning in Structural Biology Workshop 2022 Jeffrey Chan, Seyone Chithrananda, David Brookes, Sam Sinai NeurIPS 2021 Datasets and Benchmarks Track/ bioRxiv 2021 Ī Benchmark Framework for Evaluating Structure-to-Sequence Models for Protein Design Benchmarks and datasets 0.1 Sequence DatasetsįLIP: Benchmark tasks in fitness landscape inference for proteinsĬhristian Dallago, Jody Mou, Kadina E Johnston, Bruce Wittmann, Nick Bhattacharya, Samuel Goldman, Ali Madani, Kevin K Yang Protein language models and representation learning Protein Design with Guided Discrete Diffusion**Įffects of mutations & Fitness Landscape.AI Models for Protein Design are Driving Antibody Engineering.Inverse Protein Folding Using Deep Bayesian Optimization.Inspired by Kevin Kaichuang Yang's awesome Machine-learning-for-proteins, we established this repository with a sharper focus on deep learning for protein design, which is a rapidly evolving field.Ĭontributions and suggestions are warmly welcome! List of papers about Proteins Design using Deep Learning
0 kommentar(er)
