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

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 structural 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-powered drug discovery engines constituted of a biocomputational platform PandaOmics and a generative chemistry platform Chemistry42, to identify a first-in-class hit molecule of a novel target without an experimental structure starting from target selection towards hit identification in a cost- and time-efficient manner. PandaOmics provided the targets of interest and Chemistry42 generated the molecules based on the AlphaFold predicted structure, and the selected molecules were synthesized and tested in biological assays. Through this approach, we identified a small molecule hit compound for CDK20 with a Kd value of 8.9 +/- 1.6 uM (n = 4) within 30 days from target selection and after only synthesizing 7 compounds. Based on the available data, the second round of AI-powered compound generation was conducted and through which, a more potent hit molecule, ISM042-2 048, was discovered with a Kd value of 210.0 +/- 42.4 nM (n = 2), within 30 days and after synthesizing 6 compounds from the discovery of the first hit ISM042-2-001. To the best of our knowledge, this is the first reported small molecule targeting CDK20 and more importantly, this work is the first demonstration of AlphaFold application in the hit identification process in early drug discovery.

[1]  K. Brockmann,et al.  Mapping of a N-terminal α-helix domain required for human PINK1 stabilization, Serine228 autophosphorylation and activation in cells , 2022, Open Biology.

[2]  Science’s 2021 Breakthrough of the Year: AI brings protein structures to all , 2021, AAAS Articles DO Group.

[3]  The science news that shaped 2021: Nature's picks. , 2021, Nature.

[4]  P. Koenig,et al.  The structure of HiSiaQM defines the architecture of tripartite ATP-independent periplasmic (TRAP) transporters , 2021, bioRxiv.

[5]  C. Orengo,et al.  Characterizing disease-associated human proteins without available protein structures or homologues , 2021 .

[6]  D. Hassabis,et al.  AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models , 2021, Nucleic Acids Res..

[7]  S. Keeney,et al.  Computed structures of core eukaryotic protein complexes , 2021, Science.

[8]  M. Tress,et al.  APPRIS: selecting functionally important isoforms , 2021, Nucleic Acids Res..

[9]  Xiuwen Liu,et al.  Applications of AlphaFold beyond Protein Structure Prediction , 2021, bioRxiv.

[10]  C. Chuaqui,et al.  Discovery of SY-5609: A Selective, Noncovalent Inhibitor of CDK7. , 2021, Journal of medicinal chemistry.

[11]  Hwei-Jen Lee,et al.  Whole Exome Sequencing Identifies a Novel Homozygous Missense Mutation in the CSB Protein-Encoding ERCC6 Gene in a Taiwanese Boy with Cockayne Syndrome , 2021, Life.

[12]  Yuzong Chen,et al.  Therapeutic target database update 2022: facilitating drug discovery with enriched comparative data of targeted agents , 2021, Nucleic Acids Res..

[13]  T. Sixma,et al.  AI revolutions in biology , 2021, EMBO reports.

[14]  J. Korbel,et al.  AlphaDesign: A de novo protein design framework based on AlphaFold , 2021, bioRxiv.

[15]  D. Hassabis,et al.  Protein complex prediction with AlphaFold-Multimer , 2021, bioRxiv.

[16]  Oriol Vinyals,et al.  Applying and improving AlphaFold at CASP14 , 2021, Proteins.

[17]  R. Laskowski,et al.  AlphaFold heralds a data-driven revolution in biology and medicine , 2021, Nature Medicine.

[18]  Douglas E. V. Pires,et al.  A structural biology community assessment of AlphaFold2 applications , 2021, bioRxiv.

[19]  Oriol Vinyals,et al.  Highly accurate protein structure prediction with AlphaFold , 2021, Nature.

[20]  Gyu Rie Lee,et al.  Accurate prediction of protein structures and interactions using a 3-track neural network , 2021, Science.

[21]  Evgeny Putin,et al.  Chemistry42: An AI-based platform for de novo molecular design , 2021, ArXiv.

[22]  J. Hurley,et al.  Crystallographic molecular replacement using an in silico-generated search model of SARS-CoV-2 ORF8 , 2021, bioRxiv.

[23]  C. Park,et al.  Expression of Pregnancy Up-regulated Non-ubiquitous Calmodulin Kinase (PNCK) in Hepatocellular Carcinoma , 2020, Cancer Genomics & Proteomics.

[24]  B. Vértessy,et al.  Structure-based inhibitor design of mutant RAS proteins—a paradigm shift , 2020, Cancer and Metastasis Reviews.

[25]  A. Zhavoronkov,et al.  The Advent of Generative Chemistry. , 2020, ACS medicinal chemistry letters.

[26]  S. Cairo,et al.  Epigenetic footprint enables molecular risk stratification of hepatoblastoma with clinical implications. , 2020, Journal of hepatology.

[27]  E. Schadt,et al.  Intratumoral heterogeneity and clonal evolution in liver cancer , 2020, Nature Communications.

[28]  Mikael Olsson.  Struct , 2019, C# 8 Quick Syntax Reference.

[29]  Alán Aspuru-Guzik,et al.  Deep learning enables rapid identification of potent DDR1 kinase inhibitors , 2019, Nature Biotechnology.

[30]  Sangdun Choi,et al.  A Structure-Based Drug Discovery Paradigm , 2019, International journal of molecular sciences.

[31]  M. Buendia,et al.  New insights into diagnosis and therapeutic options for proliferative hepatoblastoma , 2018, Hepatology.

[32]  A. Cheng,et al.  CCRK is a novel signalling hub exploitable in cancer immunotherapy , 2018, Pharmacology & therapeutics.

[33]  M. Emmert-Buck,et al.  Molecular Signature and Mechanisms of Hepatitis D Virus–Associated Hepatocellular Carcinoma , 2018, Molecular Cancer Research.

[34]  S. Arii,et al.  Fatty Acid Binding Protein 4 (FABP4) Overexpression in Intratumoral Hepatic Stellate Cells within Hepatocellular Carcinoma with Metabolic Risk Factors. , 2018, The American journal of pathology.

[35]  A. Cheng,et al.  Hepatoma-intrinsic CCRK inhibition diminishes myeloid-derived suppressor cell immunosuppression and enhances immune-checkpoint blockade efficacy , 2017, Gut.

[36]  J. Bei,et al.  CDK20 interacts with KEAP1 to activate NRF2 and promotes radiochemoresistance in lung cancer cells , 2017, Oncogene.

[37]  A. Aliper,et al.  In silico Pathway Activation Network Decomposition Analysis (iPANDA) as a method for biomarker development , 2016, Nature Communications.

[38]  Lei Liu,et al.  Potential diagnostic and prognostic marker dimethylglycine dehydrogenase (DMGDH) suppresses hepatocellular carcinoma metastasis in vitro and in vivo , 2016, Oncotarget.

[39]  G. von Heijne,et al.  Tissue-based map of the human proteome , 2015, Science.

[40]  K. Kao,et al.  Plasmalemmal Vesicle Associated Protein (PLVAP) as a therapeutic target for treatment of hepatocellular carcinoma , 2014, BMC Cancer.

[41]  Tsung-Han Hsieh,et al.  Forfeited hepatogenesis program and increased embryonic stem cell traits in young hepatocellular carcinoma (HCC) comparing to elderly HCC , 2013, BMC Genomics.

[42]  Jun Yu,et al.  Cell cycle-related kinase is a direct androgen receptor-regulated gene that drives β-catenin/T cell factor-dependent hepatocarcinogenesis. , 2011, The Journal of clinical investigation.

[43]  Jide Wang,et al.  Functional characterisation of cell cycle-related kinase (CCRK) in colorectal cancer carcinogenesis. , 2010, European journal of cancer.

[44]  Y. Zeng,et al.  Cell cycle‐related kinase supports ovarian carcinoma cell proliferation via regulation of cyclin D1 and is a predictor of outcome in patients with ovarian carcinoma , 2009, International journal of cancer.