Curated Papers > High-impact authoritative literature on "AI Drug Discovery"

AlphaFold accelerates artificial intelligence powered drug discovery: efficient discovery of a novel CDK20 small molecule inhibitor.

Literature Information

DOI	10.1039/d2sc05709c
PMID	36794205
Journal	Chemical science
Impact Factor	7.4
JCR Quartile	Q1
Publication Year	2023
Times Cited	91
Keywords	Artificial Intelligence, Drug Discovery, CDK20 Inhibitor
Literature Type	Journal Article
ISSN	2041-6520
Pages	1443-1452
Issue	14(6)
Authors	Feng Ren, Xiao Ding, Min Zheng, Mikhail Korzinkin, Xin Cai, Wei Zhu, Alexey Mantsyzov, Alex Aliper, Vladimir Aladinskiy, Zhongying Cao, Shanshan Kong, Xi Long, Bonnie Hei Man Liu, Yingtao Liu, Vladimir Naumov, Anastasia Shneyderman, Ivan V Ozerov, Ju Wang, Frank W Pun, Daniil A Polykovskiy, Chong Sun, Michael Levitt, Alán Aspuru-Guzik, Alex Zhavoronkov

TL;DR

This study highlights the innovative application of AlphaFold in an AI-driven drug discovery pipeline, successfully identifying a novel small molecule, ISM042-2-048, targeting cyclin-dependent kinase 20 (CDK20) for hepatocellular carcinoma (HCC) treatment within 30 days. The findings underscore the potential of integrating AI-generated protein structures in accelerating the development of targeted therapeutics, particularly for previously unexplored targets.

Search for more papers on MaltSci.com

Artificial Intelligence · Drug Discovery · CDK20 Inhibitor

Abstract

The application of artificial intelligence (AI) has been considered a revolutionary change in drug discovery and development. In 2020, the AlphaFold computer program predicted protein structures for the whole human genome, which has been considered a remarkable breakthrough in both AI applications and structural biology. Despite the varying confidence levels, these predicted structures could still 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 to our end-to-end AI-powered drug discovery engines, including a biocomputational platform PandaOmics and a generative chemistry platform Chemistry42. A novel hit molecule against a novel target without an experimental structure was identified, starting from target selection towards hit identification, in a cost- and time-efficient manner. PandaOmics provided the protein of interest for the treatment of hepatocellular carcinoma (HCC) and Chemistry42 generated the molecules based on the structure predicted by AlphaFold, and the selected molecules were synthesized and tested in biological assays. Through this approach, we identified a small molecule hit compound for cyclin-dependent kinase 20 (CDK20) with a binding constant Kd value of 9.2 ± 0.5 μM (n = 3) within 30 days from target selection and after only synthesizing 7 compounds. Based on the available data, a second round of AI-powered compound generation was conducted and through this, a more potent hit molecule, ISM042-2-048, was discovered with an average Kd value of 566.7 ± 256.2 nM (n = 3). Compound ISM042-2-048 also showed good CDK20 inhibitory activity with an IC50 value of 33.4 ± 22.6 nM (n = 3). In addition, ISM042-2-048 demonstrated selective anti-proliferation activity in an HCC cell line with CDK20 overexpression, Huh7, with an IC50 of 208.7 ± 3.3 nM, compared to a counter screen cell line HEK293 (IC50 = 1706.7 ± 670.0 nM). This work is the first demonstration of applying AlphaFold to the hit identification process in drug discovery.

MaltSci.com AI Research Service

Intelligent ReadingAnswer any question about the paper and explain complex charts and formulas

Locate StatementsFind traces of a specific claim within the paper

Add to KBasePerform data extraction, report drafting, and advanced knowledge mining

Primary Questions Addressed

1. How does the integration of AlphaFold with biocomputational platforms enhance the efficiency of drug discovery processes?
2. What are the implications of using AI-generated protein structures in identifying novel drug targets that lack experimental data?
3. In what ways can the predictive capabilities of AlphaFold be applied to other areas of drug discovery beyond small molecule inhibitors?
4. How does the performance of ISM042-2-048 compare to existing CDK20 inhibitors in terms of efficacy and safety profiles?
5. What challenges remain in the application of AI technologies like AlphaFold in drug discovery, particularly in translating predictions into clinical outcomes?

Key Findings

Research Background and Objective

The study focuses on the application of AlphaFold, an advanced artificial intelligence tool, in the field of drug discovery. The primary objective is to efficiently discover novel small molecule inhibitors for CDK20, a cyclin-dependent kinase implicated in various cancers. This research aims to demonstrate the effectiveness of AI-driven methodologies in accelerating the drug discovery process.

Main Methods/Materials/Experimental Design

The research employed a combination of computational and synthetic chemistry techniques. The experimental design involved several synthetic pathways to develop small molecule inhibitors. Key steps included:

1. Compound Synthesis: Various small molecules were synthesized through multi-step reactions involving reagents like K2CO3, LiOH, and Pd-catalysts.
2. Characterization: The synthesized compounds were characterized using techniques such as NMR and LCMS to confirm their structures and purities.
3. Screening: The biological activity of the compounds was evaluated against CDK20 to identify potential inhibitors.

The following flowchart illustrates the technical route of the study:

Key Results and Findings

• Synthesis Yield: The study achieved varying yields for different compounds, with some compounds synthesized at yields exceeding 90%.
• Structural Confirmation: All synthesized compounds were confirmed through NMR and LCMS, ensuring the integrity of the structures.
• Biological Activity: Several compounds demonstrated promising inhibitory activity against CDK20, indicating their potential as therapeutic agents.

Main Conclusions/Significance/Innovation

The research highlights the capability of AI, particularly AlphaFold, to enhance the drug discovery process by accurately predicting protein structures and guiding the design of small molecule inhibitors. The successful synthesis and identification of CDK20 inhibitors underscore the innovative integration of computational methods with traditional synthetic chemistry, potentially leading to more efficient drug development pipelines.

Research Limitations and Future Directions

• Limitations: The study's limitations include the reliance on in vitro assays for biological activity, which may not fully predict in vivo efficacy. Additionally, the scope of compounds tested was limited to those designed based on computational predictions.
• Future Directions: Future research should focus on expanding the library of compounds, conducting in vivo studies to validate the efficacy of identified inhibitors, and exploring the integration of further advanced AI techniques to refine drug discovery processes.

Section	Details
Research Objective	Efficient discovery of CDK20 small molecule inhibitors using AI
Synthesis Techniques	Multi-step reactions, use of various reagents and purification methods
Key Findings	High yields, structural confirmation, promising biological activity against CDK20
Conclusions	AlphaFold enhances drug discovery efficiency
Limitations	In vitro focus, limited compound library
Future Directions	Expand compound library, in vivo studies, integrate advanced AI techniques

References

1. 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. - Guo-Qing Wu;Dan Xie;Guo-Feng Yang;Yi-Ji Liao;Shi-Juan Mai;Hai-Xia Deng;Johnny Sze;Xin-Yuan Guan;Yi-Xin Zeng;Marie C Lin;Hsiang-Fu Kung - International journal of cancer (2009)
2. Entangled Conditional Adversarial Autoencoder for de Novo Drug Discovery. - Daniil Polykovskiy;Alexander Zhebrak;Dmitry Vetrov;Yan Ivanenkov;Vladimir Aladinskiy;Polina Mamoshina;Marine Bozdaganyan;Alexander Aliper;Alex Zhavoronkov;Artur Kadurin - Molecular pharmaceutics (2018)
3. Accurate prediction of protein structures and interactions using a three-track neural network. - Minkyung Baek;Frank DiMaio;Ivan Anishchenko;Justas Dauparas;Sergey Ovchinnikov;Gyu Rie Lee;Jue Wang;Qian Cong;Lisa N Kinch;R Dustin Schaeffer;Claudia Millán;Hahnbeom Park;Carson Adams;Caleb R Glassman;Andy DeGiovanni;Jose H Pereira;Andria V Rodrigues;Alberdina A van Dijk;Ana C Ebrecht;Diederik J Opperman;Theo Sagmeister;Christoph Buhlheller;Tea Pavkov-Keller;Manoj K Rathinaswamy;Udit Dalwadi;Calvin K Yip;John E Burke;K Christopher Garcia;Nick V Grishin;Paul D Adams;Randy J Read;David Baker - Science (New York, N.Y.) (2021)
4. AI revolutions in biology: The joys and perils of AlphaFold. - Anastassis Perrakis;Titia K Sixma - EMBO reports (2021)
5. The Advent of Generative Chemistry. - Quentin Vanhaelen;Yen-Chu Lin;Alex Zhavoronkov - ACS medicinal chemistry letters (2020)
6. In silico Pathway Activation Network Decomposition Analysis (iPANDA) as a method for biomarker development. - Ivan V Ozerov;Ksenia V Lezhnina;Evgeny Izumchenko;Artem V Artemov;Sergey Medintsev;Quentin Vanhaelen;Alexander Aliper;Jan Vijg;Andreyan N Osipov;Ivan Labat;Michael D West;Anton Buzdin;Charles R Cantor;Yuri Nikolsky;Nikolay Borisov;Irina Irincheeva;Edward Khokhlovich;David Sidransky;Miguel Luiz Camargo;Alex Zhavoronkov - Nature communications (2016)
7. Bifunctional immune checkpoint-targeted antibody-ligand traps that simultaneously disable TGFβ enhance the efficacy of cancer immunotherapy. - Rajani Ravi;Kimberly A Noonan;Vui Pham;Rishi Bedi;Alex Zhavoronkov;Ivan V Ozerov;Eugene Makarev;Artem V Artemov;Piotr T Wysocki;Ranee Mehra;Sridhar Nimmagadda;Luigi Marchionni;David Sidransky;Ivan M Borrello;Evgeny Izumchenko;Atul Bedi - Nature communications (2018)
8. CCRK is a novel signalling hub exploitable in cancer immunotherapy. - Myth T Mok;Jingying Zhou;Wenshu Tang;Xuezhen Zeng;Antony W Oliver;Simon E Ward;Alfred S Cheng - Pharmacology & therapeutics (2018)
9. Atezolizumab and bevacizumab as first line therapy in advanced hepatocellular carcinoma: Practical considerations in routine clinical practice. - Ankit Jain;Shivakumar Chitturi;Geoffrey Peters;Desmond Yip - World journal of hepatology (2021)
10. Forfeited hepatogenesis program and increased embryonic stem cell traits in young hepatocellular carcinoma (HCC) comparing to elderly HCC. - Hsei-Wei Wang;Tsung-Han Hsieh;Ssu-Yi Huang;Gar-Yang Chau;Chien-Yi Tung;Chien-Wei Su;Jaw-Ching Wu - BMC genomics (2013)

Literatures Citing This Work

1. High-confidence cancer patient stratification through multiomics investigation of DNA repair disorders. - Garik V Mkrtchyan;Alexander Veviorskiy;Evgeny Izumchenko;Anastasia Shneyderman;Frank W Pun;Ivan V Ozerov;Alex Aliper;Alex Zhavoronkov;Morten Scheibye-Knudsen - Cell death & disease (2022)
2. Future directions in regulatory affairs. - Orin Chisholm;Helen Critchley - Frontiers in medicine (2022)
3. Chemistry42: An AI-Driven Platform for Molecular Design and Optimization. - Yan A Ivanenkov;Daniil Polykovskiy;Dmitry Bezrukov;Bogdan Zagribelnyy;Vladimir Aladinskiy;Petrina Kamya;Alex Aliper;Feng Ren;Alex Zhavoronkov - Journal of chemical information and modeling (2023)
4. AlphaFold2 and its applications in the fields of biology and medicine. - Zhenyu Yang;Xiaoxi Zeng;Yi Zhao;Runsheng Chen - Signal transduction and targeted therapy (2023)
5. Identification of dual-purpose therapeutic targets implicated in aging and glioblastoma multiforme using PandaOmics - an AI-enabled biological target discovery platform. - Andrea Olsen;Zachary Harpaz;Christopher Ren;Anastasia Shneyderman;Alexander Veviorskiy;Maria Dralkina;Simon Konnov;Olga Shcheglova;Frank W Pun;Geoffrey Ho Duen Leung;Hoi Wing Leung;Ivan V Ozerov;Alex Aliper;Mikhail Korzinkin;Alex Zhavoronkov - Aging (2023)
6. Effectively utilizing publicly available databases for cancer target evaluation. - Daniel Croft;Puja Lodhia;Sofia Lourenco;Craig MacKay - NAR cancer (2023)
7. The Hitchhiker's Guide to Deep Learning Driven Generative Chemistry. - Yan Ivanenkov;Bogdan Zagribelnyy;Alex Malyshev;Sergei Evteev;Victor Terentiev;Petrina Kamya;Dmitry Bezrukov;Alex Aliper;Feng Ren;Alex Zhavoronkov - ACS medicinal chemistry letters (2023)
8. Pan-cancer structurome reveals overrepresentation of beta sandwiches and underrepresentation of alpha helical domains. - Kirill E Medvedev;R Dustin Schaeffer;Kenneth S Chen;Nick V Grishin - Scientific reports (2023)
9. Petascale Homology Search for Structure Prediction. - Sewon Lee;Gyuri Kim;Eli Levy Karin;Milot Mirdita;Sukhwan Park;Rayan Chikhi;Artem Babaian;Andriy Kryshtafovych;Martin Steinegger - bioRxiv : the preprint server for biology (2023)
10. Toward the appropriate interpretation of Alphafold2. - Tian Xu;Qin Xu;Jianyong Li - Frontiers in artificial intelligence (2023)

... (81 more literatures)

---

© 2025 MaltSci - We reshape scientific research with AI technology