AF2BIND: Predicting ligand-binding sites using the pair representation of AlphaFold2

Gazizov, Artem; Lian, Anna; Goverde, Casper; Ovchinnikov, Sergey; Polizzi, Nicholas F.

doi:10.1101/2023.10.15.562410

Cited by 7 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2023, the Baker group reported designed 3D protein crystals capable of rapid in vitro self-assembly. 200 Additional machine learning tools, such as AlphaFold, have been used to predict allosteric and protein-ligand interactions, 201 and may be used to alter the structure and binding affinities of LPCs. With the advent of reliable protein crystal design, we anticipate rapid growth in the number of engineered crystals with functional applications.…”

Section: Discussionmentioning

confidence: 99%

Porous protein crystals: synthesis and applications

Jones,

Snow

2024

Chem. Commun.

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Porous protein crystals: synthesis and applications

Jones,

Snow

2024

Chem. Commun.

View full text Add to dashboard Cite

show abstract

“…This points to a lack of an internal representation for physical interactions with metal ions, which could be used to place the ions. It is well known that structure prediction models such as AlphaFold2 can take into account energetic frustration which can be exploited for predicting ligand binding sites ( Gazizov et al, 2023 ). The reason for the performance difference of RFAA versus AF3 for metal ions is likely the non-inclusion of a direct frame loss function for the metals in RFAA and the relatively low sampling of proteinmetal complexes during training.…”

Section: Discussionmentioning

confidence: 99%

Predicting metal-protein interactions using cofolding methods: Status quo

Dürr,

Rothlisberger

2024

Preprint

View full text Add to dashboard Cite

Metals play important roles for enzyme function and many therapeutically relevant proteins. Despite the fact that the first drugs developed via computer aided drug design were metalloprotein inhibitors, many computational pipelines for drug discovery still discard metalloproteins due to the difficulties of modelling them computationally. New “cofolding” methods such as AlphaFold3 (AF3) (Abramson et al., 2024) and RoseTTAfold-AllAtom (RFAA) (Krishna et al., 2024) promise to improve this issue by being able to dock small molecules in presence of multiple complex cofactors including metals or covalent modifications. Here, we analyze the current status for metal ion prediction using these methods. We find that currently only AF3 provides realistic predictions for metal ions, RFAA in contrast does perform worse than more specialized models such as AllMetal3D in predicting the location of metal ions accurately. We find that AF3 predictions are consistent with expected physico-chemical trends/intuition whereas RFAA often also predicts unrealistic metal ion locations.

show abstract

“…SurfGen uses two isovariant neural networks, Geodesic-GNN and Geoatom-GNN, to capture topological interactions and spatial interactions between ligand atoms and surface nodes, respectively, allowing it to provide effective solutions to problems including mutation-induced drug resistance in proteins . For example, Gazizov et al proposed a logistic regression model, AF2BIND, which is trained by using an internal representation of the protein structure and sequence of AlphaFold2 to predict the residues of the protein’s small molecule binding site and to calculate the ligand polarity compatible with the binding pocket . These AI methods and tools will be combined with experiments to have a profound impact on future protein structure prediction and facilitate SBDD targeting SLCs.…”

Section: Drug Design Targeting Slcsmentioning

confidence: 99%

Computational Chemistry in Structure-Based Solute Carrier Transporter Drug Design: Recent Advances and Future Perspectives

Tu,

Fu,

Zheng

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Solute carrier transporters (SLCs) are a class of important transmembrane proteins that are involved in the transportation of diverse solute ions and small molecules into cells. There are approximately 450 SLCs within the human body, and more than a quarter of them are emerging as attractive therapeutic targets for multiple complex diseases, e.g., depression, cancer, and diabetes. However, only 44 unique transporters (∼9.8% of the SLC superfamily) with 3D structures and specific binding sites have been reported. To design innovative and effective drugs targeting diverse SLCs, there are a number of obstacles that need to be overcome. However, computational chemistry, including physics-based molecular modeling and machine learning-and deep learning-based artificial intelligence (AI), provides an alternative and complementary way to the classical drug discovery approach. Here, we present a comprehensive overview on recent advances and existing challenges of the computational techniques in structure-based drug design of SLCs from three main aspects: (i) characterizing multiple conformations of the proteins during the functional process of transportation, (ii) identifying druggability sites especially the cryptic allosteric ones on the transporters for substrates and drugs binding, and (iii) discovering diverse small molecules or synthetic protein binders targeting the binding sites. This work is expected to provide guidelines for a deep understanding of the structure and function of the SLC superfamily to facilitate rational design of novel modulators of the transporters with the aid of state-of-the-art computational chemistry technologies including artificial intelligence.

show abstract

AF2BIND: Predicting ligand-binding sites using the pair representation of AlphaFold2

Cited by 7 publications

References 39 publications

Porous protein crystals: synthesis and applications

Porous protein crystals: synthesis and applications

Predicting metal-protein interactions using cofolding methods: Status quo

Computational Chemistry in Structure-Based Solute Carrier Transporter Drug Design: Recent Advances and Future Perspectives

Contact Info

Product

Resources

About