• Corpus ID: 246240398

AlphaFold Accelerates Artificial Intelligence Powered Drug Discovery: Efficient Discovery of a Novel Cyclin-dependent Kinase 20 (CDK20) Small Molecule Inhibitor

  title={AlphaFold Accelerates Artificial Intelligence Powered Drug Discovery: Efficient Discovery of a Novel Cyclin-dependent Kinase 20 (CDK20) Small Molecule Inhibitor},
  author={Fengzhi Ren and Xiao Ding and Mingzhong Zheng and Mikhail B. Korzinkin and Xin Cai and Wei Zhu and Alexey B. Mantsyzov and Alexander Aliper and Vladimir Aladinskiy and Zhongying Cao and Shan Kong and Xi Long and Bo Liu and Yingtao Liu and Vladimir A. Naumov and Anastasia Shneyderman and Ivan V. Ozerov and Ju Wang and Frank Wing Pun and Al{\'a}n Aspuru-Guzik and Michael M. Levitt and Alex Zhavoronkov},
The AlphaFold computer program predicted protein structures for the whole human genome, which has been considered as a remarkable breakthrough both in artificial intelligence (AI) application and structure biology. Despite the varying confidence level, these predicted structures still could significantly contribute to structure-based drug design of novel targets, especially the ones with no or limited structural information. In this work, we successfully applied AlphaFold in our end-to-end AI… 

Figures from this paper

Accelerating Inhibitor Discovery for Multiple SARS-CoV-2 Targets with a Single, Sequence-Guided Deep Generative Framework
The broad utility of a single deep generative framework toward discovering novel drug-like inhibitor molecules against two distinct SARS-CoV-2 targets — the main protease and the receptor binding domain (RBD) of the spike protein are demonstrated.
How to select the best model from AlphaFold2 structures?
Among the methods for protein structure prediction, which is important in biological research, AlphaFold2 has demonstrated astonishing accuracy in the 14th Community Wide Experiment on the Critical
EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structures
The Equivariant Graph Refiner (EGR) is introduced, a novel E(3)-equivariant graph neural network (GNN) for multi-task structure re⬁nement and assessment of protein complexes and establishes a baseline for future studies in macromolecular re- characterization and structure analysis.
Recent Biophysical Advances in Drug Discovery
  • H. Ng
  • Biology
  • 2022
In recent years, there has seen an explosion of technological progress related to drug discovery, including computing power, artificial intelligence, and electron microscopy, which has transformed the field of drug discovery.


A Structure-Based Drug Discovery Paradigm
This review focuses on the currently available methods and algorithms for structure-based drug design including virtual screening and de novo drug design, with a special emphasis on AI- and deep-learning-based methods used for drug discovery.
AlphaFold heralds a data-driven revolution in biology and medicine.
The AlphaFold AI program rapidly generates models of protein structures from their amino acid sequence more accurately than had previously been achieved, and the quality of the predictions is comparable in quality to those from experimental structure determination.
Chemistry42: An AI-based platform for de novo molecular design
Chemistry42 is a software platform for de novo small molecule design that integrates Artificial Intelligence (AI) techniques with computational and medicinal chemistry methods. Chemistry42 is unique
AlphaDesign: A de novo protein design framework based on AlphaFold
AlphaDesign, a computational framework for de novo protein design that embeds AF as an oracle within an optimisable design process, enables rapid prediction of completely novel protein monomers starting from random sequences and suggests that the framework allows for fairly accurate protein design.
Structure-based inhibitor design of mutant RAS proteins—a paradigm shift
The latest advances in covalent modification strategy mostly applicable for G12C mutation are summarized, perspectives for novel approaches are provided, and the special properties of KRAS are highlighted, which might issue some new challenges.
Computed structures of core eukaryotic protein complexes
A coevolution-guided protein interaction identification pipeline that incorporates a rapidly computable version of RoseTTAFold with the slower but more accurate AlphaFold to systematically evaluate interactions between 8.3 million pairs of yeast proteins is developed.
Applications of AlphaFold beyond Protein Structure Prediction
It is found that experimentally measured stability changes of point mutations correlate poorly with the confidence scores produced by AlphaFold, however, the stability changes can be accurately predicted using features extracted from the representations learned by Alphafold, indicating greater generalizability ofAlphaFold to designed or engineered sequences than previously thought.
Therapeutic target database update 2022: facilitating drug discovery with enriched comparative data of targeted agents
A major update of the Therapeutic Target Database, previously featured in NAR, was introduced and a variety of additional data and function are provided, which include the cross-links to the target structure in PDB and AlphaFold, newly emerged targets and drugs, and the advanced search function for multi-entry target sequences or drug structures.
Characterizing disease-associated human proteins without available protein structures or homologues
Use of models from the two state-of-the-art techniques provide better confidence in the predictions, and 93 additional mutations are explained based on RoseTTAFold models which could not be explained based solely on AlphaFolds.
Highly accurate protein structure prediction with AlphaFold
This work validated an entirely redesigned version of the neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experiment in a majority of cases and greatly outperforming other methods.