Recent Advancements in the Application of Artificial Intelligence in Drug Molecular Generation and Synthesis Planning

Abstract

The design and synthesis of drug molecules is a pivotal stage in drug development that traditionally requires significant investment in time and finances. However, the integration of artificial intelligence (AI) in drug design accelerates the identification of potential drug candidates, optimizes the drug development process, and contributes to more informed decision-making. The application of AI in molecular generation is changing the way researchers explore the chemical space and design novel compounds. It accelerates the process of drug discovery and materials science, enabling rapid exploration of the vast chemical landscapes for the identification of promising candidates for further experimental validation. The application of AI in predicting reaction products accelerates the synthesis planning process, contributes to the automation of synthetic chemistry tasks, and supports chemists in making informed decisions during drug discovery. This paper reviewed the recent advances in two interrelated areas: the application of AI in molecular generation and synthesis routes. It will provide insights into the innovative ways in which AI is transforming traditional approaches in drug development and predict its future progress in these key fields.

Keywords

artificial intelligence - drug screen - molecular generation - retrosynthesis - deep learning

Publication History

Received: 16 January 2024

Accepted: 02 November 2024

Article published online:
02 December 2024

• References

• 1 Pantelidis P, Spartalis M, Zakynthinos G. et al. Artificial intelligence: the new “fuel” to accelerate pharmaceutical development. Curr Pharm Des 2022; 28 (26) 2127-2128
• 2 Alom MZ, Yakopcic C, Hasan M, Taha TM, Asari VK. Recurrent residual U-Net for medical image segmentation. J Med Imaging (Bellingham) 2019; 6 (01) 014006
• 3 Anstine DM, Isayev O. Generative models as an emerging paradigm in the chemical sciences. J Am Chem Soc 2023; 145 (16) 8736-8750
• 4 Sousa T, Correia J, Pereira V, Rocha M. Generative deep learning for targeted compound design. J Chem Inf Model 2021; 61 (11) 5343-5361
• 5 Martinelli DD. Generative machine learning for de novo drug discovery: a systematic review. Comput Biol Med 2022; 145: 105403
• 6 Choi S, Seo S, Kim BJ, Park C, Park S. PIDiff: Physics informed diffusion model for protein pocket-specific 3D molecular generation. Comput Biol Med 2024; 180: 108865
• 7 Klucznik T, Mikulak-Klucznik B, McCormack MP. et al. Efficient syntheses of diverse, medicinally relevant targets planned by computer and executed in the laboratory. Chem 2018; 4: 522-532
• 8 Cheng Y, Gong Y, Liu Y, Song B, Zou Q. Molecular design in drug discovery: a comprehensive review of deep generative models. Brief Bioinform 2021; 22 (06) bbab344
• 9 Tong X, Liu X, Tan X. et al. Generative models for de novo drug design. J Med Chem 2021; 64 (19) 14011-14027
• 10 Thomas M, Bender A, de Graaf C. Integrating structure-based approaches in generative molecular design. Curr Opin Struct Biol 2023; 79: 102559
• 11 Tang X, Dai H, Knight E. et al. A survey of generative AI for de novo drug design: new frontiers in molecule and protein generation. Brief Bioinform 2024; 25 (04) bbae338
• 12 Rácz A, Bajusz D, Héberger K. Consistency of QSAR models: correct split of training and test sets, ranking of models and performance parameters. SAR QSAR Environ Res 2015; 26 (7-9): 683-700
• 13 Parvatikar PP, Patil S, Khaparkhuntikar K. et al. Artificial intelligence: machine learning approach for screening large database and drug discovery. Antiviral Res 2023; 220: 105740
• 14 Wang J, Hsieh K, Wang M. et al. Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning. Nat Mach Intell 2021; 3: 914-922
• 15 Yang L, Yang G, Bing Z. et al. Transformer-based generative model accelerating the development of novel braf inhibitors. ACS Omega 2021; 6 (49) 33864-33873
• 16 Chen Y, Wang Z, Wang L. et al. Deep generative model for drug design from protein target sequence. J Cheminform 2023; 15 (01) 38
• 17 Lu F, Li M, Min X, Li C, Zeng X. De novo generation of dual-target ligands using adversarial training and reinforcement learning. Brief Bioinform 2021; 22 (06) bbab333
• 18 Ozawa M, Nakamura S, Yasuo N, Sekijima M. IEV2Mol: molecular generative model considering protein-ligand interaction energy vectors. J Chem Inf Model 2024; 64 (18) 6969-6978
• 19 Song T, Ren Y, Wang S. et al. DNMG: deep molecular generative model by fusion of 3D information for de novo drug design. Methods 2023; 211: 10-22
• 20 Zhang C, Xie L, Lu X, Mao R, Xu L, Xu X. Developing an improved cycle architecture for AI-based generation of new structures aimed at drug discovery. Molecules 2024; 29 (07) 1499
• 21 Erikawa D, Yasuo N, Sekijima M. MERMAID: an open source automated hit-to-lead method based on deep reinforcement learning. J Cheminform 2021; 13 (01) 94
• 22 Olivecrona M, Blaschke T, Engkvist O, Chen H. Molecular de-novo design through deep reinforcement learning. J Cheminform 2017; 9 (01) 48
• 23 Blaschke T, Arús-Pous J, Chen H. et al. REINVENT 2.0: an AI tool for de novo drug design. J Chem Inf Model 2020; 60 (12) 5918-5922
• 24 Loeffler HH, He J, Tibo A. et al. Reinvent 4: modern AI-driven generative molecule design. J Cheminform 2024; 16 (01) 20
• 25 Weller JA, Rohs R. Structure-based drug design with a deep hierarchical generative Model. J Chem Inf Model 2024; 64 (16) 6450-6463
• 26 Krenn M, Häse F, Nigam A, Friederich P, Aspuru-Guzik A. Self-referencing embedded strings (SELFIES): a 100% robust molecular string representation. Mach Learn Sci Technol 2020; 1: 045024
• 27 Zhou Y, Wang Z, Huang Z. et al. In silico prediction of ocular toxicity of compounds using explainable machine learning and deep learning approaches. J Appl Toxicol 2024; 44 (06) 892-907
• 28 Mercado R, Bjerrum EJ, Engkvist O. Exploring graph traversal algorithms in graph-based molecular generation. J Chem Inf Model 2022; 62 (09) 2093-2100
• 29 Lee M, Min K. MGCVAE: multi-objective inverse design via molecular graph conditional variational autoencoder. J Chem Inf Model 2022; 62 (12) 2943-2950
• 30 Gao Z, Wang X, Blumenfeld Gaines B, Shi X, Bi J, Song M. Fragment-based deep molecular generation using hierarchical chemical graph representation and multi-resolution graph variational autoencoder. Mol Inform 2023; 42 (05) e2200215
• 31 Kang SG, Morrone JA, Weber JK, Cornell WD. Analysis of training and seed bias in small molecules generated with a conditional graph-based variational autoencoder horizontal line insights for practical AI-driven molecule generation. J Chem Inf Model 2022; 62 (04) 801-816
• 32 Xu T, Wang M, Liu X. et al. A scaffold-based deep generative model considering molecular stereochemical information. Mol Inform 2022; 41 (12) e2200088
• 33 Langevin M, Minoux H, Levesque M, Bianciotto M. Scaffold-constrained molecular generation. J Chem Inf Model 2020; 60 (12) 5637-5646
• 34 Zheng S, Lei Z, Ai H, Chen H, Deng D, Yang Y. Deep scaffold hopping with multimodal transformer neural networks. J Cheminform 2021; 13 (01) 87
• 35 Xu C, Liu R, Huang S, Li W, Li Z, Luo HB. 3D-SMGE: a pipeline for scaffold-based molecular generation and evaluation. Brief Bioinform 2023; 24 (06) bbad327
• 36 Hu C, Li S, Yang C. et al. ScaffoldGVAE: scaffold generation and hopping of drug molecules via a variational autoencoder based on multi-view graph neural networks. J Cheminform 2023; 15 (01) 91
• 37 Atance SR, Diez JV, Engkvist O, Olsson S, Mercado R. De novo drug design using reinforcement learning with graph-based deep generative models. J Chem Inf Model 2022; 62 (20) 4863-4872
• 38 Hu F, Wang D, Huang H, Hu Y, Yin P. Bridging the gap between target-based and cell-based drug discovery with a graph generative multitask model. J Chem Inf Model 2022; 62 (23) 6046-6056
• 39 Pham TH, Xie L, Zhang P. FAME: fragment-based conditional molecular generation for phenotypic drug discovery. Proc SIAM Int Conf Data Min 2022; 2022: 720-728
• 40 Chen Z, Min MR, Parthasarathy S, Ning X. A deep generative model for molecule optimization via one fragment modification. Nat Mach Intell 2021; 3 (12) 1040-1049
• 41 Shen X, Zeng T, Chen N, Li J, Wu R. NIMO: a natural product-inspired molecular generative model based on conditional transformer. Molecules 2024; 29 (08) 1867
• 42 Mukaidaisi M, Vu A, Grantham K, Tchagang A, Li Y. Multi-objective drug design based on graph-fragment molecular representation and deep evolutionary learning. Front Pharmacol 2022; 13: 920747
• 43 Iwata H, Nakai T, Koyama T, Matsumoto S, Kojima R, Okuno Y. VGAE-MCTS: a new molecular generative model combining the variational graph auto-encoder and Monte Carlo tree search. J Chem Inf Model 2023; 63 (23) 7392-7400
• 44 Suzuki T, Ma D, Yasuo N, Sekijima M. Mothra: multiobjective de novo molecular generation using monte carlo tree search. J Chem Inf Model 2024; 64 (19) 7291-7302
• 45 Qian H, Lin C, Zhao D, Tu S, Xu L. AlphaDrug: protein target specific de novo molecular generation. PNAS Nexus 2022; 1 (04) pgac227
• 46 Li Y, Pei J, Lai L. Structure-based de novo drug design using 3D deep generative models. Chem Sci (Camb) 2021; 12 (41) 13664-13675
• 47 Imrie F, Hadfield TE, Bradley AR, Deane CM. Deep generative design with 3D pharmacophoric constraints. Chem Sci (Camb) 2021; 12 (43) 14577-14589
• 48 Papadopoulos K, Giblin KA, Janet JP, Patronov A, Engkvist O. De novo design with deep generative models based on 3D similarity scoring. Bioorg Med Chem 2021; 44: 116308
• 49 Xu M, Huang W, Xu M, Lei J, Chen H. 3D conformational generative models for biological structures using graph information-embedded relative coordinates. Molecules 2022; 28 (01) 321
• 50 Xie W, Wang F, Li Y, Lai L, Pei J. Advances and challenges in de novo drug design using three-dimensional deep generative models. J Chem Inf Model 2022; 62 (10) 2269-2279
• 51 Ragoza M, Masuda T, Koes DR. Generating 3D molecules conditional on receptor binding sites with deep generative models. Chem Sci (Camb) 2022; 13 (09) 2701-2713
• 52 Xu M, Ran T, Chen H. De novo molecule design through the molecular generative model conditioned by 3D information of protein binding sites. J Chem Inf Model 2021; 61 (07) 3240-3254
• 53 Zhung W, Kim H, Kim WY. 3D molecular generative framework for interaction-guided drug design. Nat Commun 2024; 15 (01) 2688
• 54 Wang M, Hsieh CY, Wang J. et al. RELATION: a deep generative model for structure-based de novo drug design. J Med Chem 2022; 65 (13) 9478-9492
• 55 Li S, Hu C, Ke S. et al. LS-MolGen: ligand-and-structure dual-driven deep reinforcement learning for target-specific molecular generation improves binding affinity and novelty. J Chem Inf Model 2023; 63 (13) 4207-4215
• 56 Sagar D, Risheh A, Sheikh N, Forouzesh N. Physics-guided deep generative model for new ligand discovery. ACM BCB 2023; . ACM BCB 2023;2023:
• 57 Wu P, Du H, Yan Y, Lee TY, Bai C, Wu S. Guided diffusion for molecular generation with interaction prompt. Brief Bioinform 2024; 25 (03) bbae174
• 58 Zhang J, Chen H. De novo molecule design using molecular generative models constrained by ligand-protein interactions. J Chem Inf Model 2022; 62 (14) 3291-3306
• 59 Nakata S, Mori Y, Tanaka S. End-to-end protein-ligand complex structure generation with diffusion-based generative models. BMC Bioinformatics 2023; 24 (01) 233
• 60 Cremer J, Le T, Noé F, Clevert DA, Schütt KT. PILOT: equivariant diffusion for pocket-conditioned de novo ligand generation with multi-objective guidance via importance sampling. Chem Sci (Camb) 2024; 15 (36) 14954-14967
• 61 Huang L, Xu T, Yu Y. et al. A dual diffusion model enables 3D molecule generation and lead optimization based on target pockets. Nat Commun 2024; 15 (01) 2657
• 62 Zhang O, Zhang J, Jin J. et al. ResGen is a pocket-aware 3D molecular generation model based on parallel multiscale modeling. Nat Mach Intell 2023; 5: 1020-1030
• 63 Zhang O, Wang T, Weng G. et al. Learning on topological surface and geometric structure for 3D molecular generation. Nat Comput Sci 2023; 3 (10) 849-859
• 64 Bilodeau C, Jin W, Jaakkola T, Barzilay R, Jensen KF. Generative models for molecular discovery: recent advances and challenges. Wiley Interdiscip Rev Comput Mol Sci 2022; 12 (05) e1608
• 65 Nguyen DH, Tsuda K. Generating reaction trees with cascaded variational autoencoders. J Chem Phys 2022; 156 (04) 044117
• 66 Wang J, Wang X, Sun H. et al. ChemistGA: a chemical synthesizable accessible molecular generation algorithm for real-world drug discovery. J Med Chem 2022; 65 (18) 12482-12496
• 67 Schwaller P, Laino T, Gaudin T. et al. Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Cent Sci 2019; 5 (09) 1572-1583
• 68 Chen S, Jung Y. A generalized-template-based graph neural network for accurate organic reactivity prediction. Nat Mach Intell 2022; 4: 772-780
• 69 Coley CW, Jin W, Rogers L. et al. A graph-convolutional neural network model for the prediction of chemical reactivity. Chem Sci (Camb) 2018; 10 (02) 370-377
• 70 Berisha V, Krantsevich C, Hahn PR. et al. Digital medicine and the curse of dimensionality. NPJ Digit Med 2021; 4 (01) 153
• 71 Collins KD, Gensch T, Glorius F. Contemporary screening approaches to reaction discovery and development. Nat Chem 2014; 6 (10) 859-871
• 72 Ahneman DT, Estrada JG, Lin S, Dreher SD, Doyle AG. Predicting reaction performance in C-N cross-coupling using machine learning. Science 2018; 360 (6385) 186-190
• 73 Ross J, Belgodere B, Chenthamarakshan V. et al. Large-scale chemical language representations capture molecular structure and properties. Nat Mach Intell 2022; 4: 1256-1264
• 74 Yoshikawa N, Skreta M, Darvish K. et al. Large language models for chemistry robotics. Auton Robots 2023; 47 (08) 1057-1086
• 75 Coley CW, Barzilay R, Jaakkola TS, Green WH, Jensen KF. Prediction of organic reaction outcomes using machine learning. ACS Cent Sci 2017; 3 (05) 434-443
• 76 Gao H, Struble TJ, Coley CW, Wang Y, Green WH, Jensen KF. Using machine learning to predict suitable conditions for organic reactions. ACS Cent Sci 2018; 4 (11) 1465-1476
• 77 Amar Y, Schweidtmann AM, Deutsch P, Cao L, Lapkin A. Machine learning and molecular descriptors enable rational solvent selection in asymmetric catalysis. Chem Sci (Camb) 2019; 10 (27) 6697-6706
• 78 Rinehart NI, Saunthwal RK, Wellauer J. et al. A machine-learning tool to predict substrate-adaptive conditions for Pd-catalyzed C-N couplings. Science 2023; 381 (6661) 965-972
• 79 Gong Y, Xue D, Chuai G, Yu J, Liu Q. DeepReac+: deep active learning for quantitative modeling of organic chemical reactions. Chem Sci (Camb) 2021; 12 (43) 14459-14472
• 80 Shields BJ, Stevens J, Li J. et al. Bayesian reaction optimization as a tool for chemical synthesis. Nature 2021; 590 (7844) 89-96
• 81 Burger B, Maffettone PM, Gusev VV. et al. A mobile robotic chemist. Nature 2020; 583 (7815) 237-241
• 82 Wang X, Hsieh CY, Yin X. et al. Generic interpretable reaction condition predictions with open reaction condition datasets and unsupervised learning of reaction center. Research (Wash D C) 2023; 6: 0231
• 83 Andronov M, Voinarovska V, Andronova N, Wand M, Clevert DA, Schmidhuber J. Reagent prediction with a molecular transformer improves reaction data quality. Chem Sci (Camb) 2023; 14 (12) 3235-3246
• 84 Maser MR, Cui AY, Ryou S, DeLano TJ, Yue Y, Reisman SE. Multilabel classification models for the prediction of cross-coupling reaction conditions. J Chem Inf Model 2021; 61 (01) 156-166
• 85 Schwaller P, Vaucher AC, Laplaza R. et al. Machine intelligence for chemical reaction space. Wiley Interdiscip Rev Comput Mol Sci 2022; 12: e1604
• 86 Schwaller P, Probst D, Vaucher AC. et al. Mapping the space of chemical reactions using attention-based neural networks. Nat Mach Intell 2021; 3: 144-152
• 87 Saebi M, Nan B, Herr JE. et al. On the use of real-world datasets for reaction yield prediction. Chem Sci (Camb) 2023; 14 (19) 4997-5005
• 88 Probst D, Schwaller P, Reymond JL. Reaction classification and yield prediction using the differential reaction fingerprint DRFP. Digit Discov 2022; 1 (02) 91-97
• 89 Sandfort F, Strieth-Kalthoff F, Kühnemund M, Beecks C, Glorius F. A structure-based platform for predicting chemical reactivity. Chem 2020; 6: 1379-1390
• 90 Schwaller P, Vaucher AC, Laino T, Reymond JL. Prediction of chemical reaction yields using deep learning. Mach Learn Sci Technol 2021; 2: 015016
• 91 Yin X, Hsieh CY, Wang X. et al. Enhancing generic reaction yield prediction through reaction condition-based contrastive learning. Research (Wash D C) 2024; 7: 0292
• 92 Ma Y, Zhang X, Zhu L. et al. Machine learning and quantum calculation for predicting yield in Cu-catalyzed P-H reactions. Molecules 2023; 28 (16) 5995
• 93 Maruoka T, Yada A, Sato K, Matsubara S. Machine learning that proposes reaction conditions and yields for wittig-type methylenation of aldehydes with bis(iodozincio)methane in a flow-microreactor. Chem Lett 2023; 52: 397-399