Machine learning (ML) is poised to accelerate antibiotic discovery by rapidly identifying and generating compounds with desirable properties. Despite focused effort, algorithmic advances alone have yielded only modest improvements in real-world performance. Greater gains will likely come from improved data acquisition, data representation, and model output interpretation by domain experts. Field-wide efforts in more standardized data curation, benchmarking, and publication practices are also essential to ensure that ML methods reach their full potential to help us efficiently discover new antibiotics to address unmet clinical needs. This review focuses on the data-centric choices necessary to build ML pipelines for antibiotic discovery that are robust, reliable, efficient, and biologically grounded.
MurrayCJL, IkutaKS, ShararaF, et al.Global burden of bacterial antimicrobial resistance in 2019: A systematic analysis. Lancet2022;399(10325):629–655; doi: 10.1016/S0140-6736(21)02724-0
2.
BrownED, WrightGD. Antibacterial drug discovery in the resistance era. Nature2016;529(7586):336–343; doi: 10.1038/nature17042
3.
McDowellLL, QuinnCL, LeedsJA, et al.Perspective on antibacterial lead identification challenges and the role of hypothesis-driven strategies. SLAS Discov2019;24(4):440–456; doi: 10.1177/2472555218818786
4.
MakurvetFD. Biologics vs. small molecules: Drug costs and patient access. Med Drug Discov2021;9:100075; doi: 10.1016/j.medidd.2020.100075
5.
BeckH, HärterM, HaßB, et al.Small molecules and their impact in drug discovery: A perspective on the occasion of the 125th anniversary of the Bayer Chemical Research Laboratory. Drug Discov Today2022;27(6):1560–1574; doi: 10.1016/j.drudis.2022.02.015
6.
KangD, BagchiD, ChenIA. Pharmacokinetics and biodistribution of phages and their current applications in antimicrobial therapy. Adv Ther (Weinh)2024;7(3):2300355; doi: 10.1002/adtp.202300355
7.
OoC, KalbagSS. Leveraging the attributes of biologics and small molecules, and releasing the bottlenecks: A new wave of revolution in drug development. Expert Rev Clin Pharmacol2016;9(6):747–749; doi: 10.1586/17512433.2016.1160778
8.
VermaS, GoandUK, HusainA, et al.Challenges of peptide and protein drug delivery by oral route: Current strategies to improve the bioavailability. Drug Dev Res2021;82(7):927–944; doi: 10.1002/ddr.21832
9.
WangL, WangN, ZhangW, et al.Therapeutic peptides: Current applications and future directions. Signal Transduct Target Ther2022;7(1):48; doi: 10.1038/s41392-022-00904-4
10.
ArnoldA, McLellanS, StokesJM. How AI can help us beat AMR. NPJ Antimicrob Resist2025;3(1):18; doi: 10.1038/s44259-025-00085-4
11.
CatacutanDB, AlexanderJ, ArnoldA, et al.Machine learning in preclinical drug discovery. Nat Chem Biol2024;20(8):960–973; doi: 10.1038/s41589-024-01679-1
12.
JumperJ, EvansR, PritzelA, et al.Highly accurate protein structure prediction with AlphaFold. Nature2021;596(7873):583–589; doi: 10.1038/s41586-021-03819-2
13.
DurantG, BoylesF, BirchallK, et al.The future of machine learning for small-molecule drug discovery will be driven by data. Nat Comput Sci2024;4(10):735–743; doi: 10.1038/s43588-024-00699-0
14.
TouvronH, MartinL, StoneK, et al.Llama 2: Open foundation and fine-tuned chat models. arXiv [Preprint]2023; doi: 10.48550/arXiv.2307.09288
15.
RameshA, DhariwalP, NicholA, et al.Hierarchical text-conditional image generation with CLIP latents. arXiv [Preprint]2022; doi: 10.48550/arXiv.2204.06125
16.
ZhengW, ThorneN, McKewJC. Phenotypic screens as a renewed approach for drug discovery. Drug Discov Today2013;18(21–22):1067–1073; doi: 10.1016/j.drudis.2013.07.001
17.
AulnerN, DanckaertA, IhmJ, et al.Next-generation phenotypic screening in early drug discovery for infectious diseases. Trends Parasitol2019;35(7):559–570; doi: 10.1016/j.pt.2019.05.004
18.
PayneDJ, GwynnMN, HolmesDJ, et al.Drugs for bad bugs: Confronting the challenges of antibacterial discovery. Nat Rev Drug Discov2007;6(1):29–40; doi: 10.1038/nrd2201
19.
TommasiR, BrownDG, WalkupGK, et al.ESKAPEing the labyrinth of antibacterial discovery. Nat Rev Drug Discov2015;14(8):529–542; doi: 10.1038/nrd4572
20.
LiJW-H, VederasJC. Drug discovery and natural products: End of an era or an endless frontier? Science2009;325(5937):161–165; doi: 10.1126/science.1168243
21.
ClardyJ, FischbachMA, WalshCT. New antibiotics from bacterial natural products. Nat Biotechnol2006;24(12):1541–1550; doi: 10.1038/nbt1266
22.
NewmanDJ, CraggGM. Natural products as sources of new drugs over the last 25 years. J Nat Prod2007;70(3):461–477; doi: 10.1021/np068054v
23.
CosP, VlietinckAJ, BergheDV, et al.Anti-infective potential of natural products: How to develop a stronger in vitro ‘proof-of-concept’. J Ethnopharmacol2006;106(3):290–302; doi: 10.1016/j.jep.2006.04.003
CareyAF, RockJM, KriegerIV, et al.TnSeq of Mycobacterium tuberculosis clinical isolates reveals strain-specific antibiotic liabilities. PLoS Pathog2018;14(3):e1006939; doi: 10.1371/journal.ppat.1006939
26.
ShiD, MiG, WangM, et al.In vitro and ex vivo systems at the forefront of infection modeling and drug discovery. Biomaterials2019;198:228–249; doi: 10.1016/j.biomaterials.2018.10.030
27.
NizetV. The accidental orthodoxy of Drs. Mueller and Hinton. EBioMedicine2017;22:26–27; doi: 10.1016/j.ebiom.2017.07.002
28.
JacobsAC, SayoodK, OlmstedSB, et al.Characterization of the Acinetobacter baumannii growth phase-dependent and serum responsive transcriptomes. FEMS Immunol Med Microbiol2012;64(3):403–412; doi: 10.1111/j.1574-695X.2011.00926.x
29.
BlanchardC, BarnettP, PerlmutterJ, et al.Identification of Acinetobacter baumannii serum-associated antibiotic efflux pump inhibitors. Antimicrob Agents Chemother2014;58(11):6360–6370; doi: 10.1128/aac.03535-14
30.
KruczekC, KottapalliKR, DissanaikeS, et al.Major transcriptome changes accompany the growth of Pseudomonas aeruginosa in blood from patients with severe thermal injuries. PLoS One2016;11(3):e0149229; doi: 10.1371/journal.pone.0149229
HeesterbeekDAC, MartinNI, VelthuizenA, et al.Complement-dependent outer membrane perturbation sensitizes Gram-negative bacteria to Gram-positive specific antibiotics. Sci Rep2019;9(1):3074; doi: 10.1038/s41598-019-38577-9
33.
WeberBS, De JongAM, GuoABY, et al.Genetic and chemical screening in human blood serum reveals unique antibacterial targets and compounds against Klebsiella pneumoniae. Cell Rep2020;32(3):107927; doi: 10.1016/j.celrep.2020.107927
34.
SadriA. Is target-based drug discovery efficient? Discovery and “Off-target” mechanisms of all drugs. J Med Chem2023;66(18):12651–12677; doi: 10.1021/acs.jmedchem.2c01737
35.
BrownD. Unfinished business: Target-based drug discovery. Drug Discov Today2007;12(23–24):1007–1012; doi: 10.1016/j.drudis.2007.10.017
36.
LewisK. The science of antibiotic discovery. Cell2020;181(1):29–45; doi: 10.1016/j.cell.2020.02.056
37.
SilverLL. Challenges of antibacterial discovery. Clin Microbiol Rev2011;24(1):71–109; doi: 10.1128/CMR.00030-10
38.
FarhaMA, TuMM, BrownED. Important challenges to finding new leads for new antibiotics. Curr Opin Microbiol2025;83:102562; doi: 10.1016/j.mib.2024.102562
39.
LeusIV, WeeksJW, BonifayV, et al.Property space mapping of Pseudomonas aeruginosa permeability to small molecules. Sci Rep2022;12(1):8220; doi: 10.1038/s41598-022-12376-1
40.
Le GoffF, HazemannJ, ChristenL, et al.Measurement and prediction of small molecule retention by Gram-negative bacteria based on a large-scale LC/MS screen. Sci Rep2025;15(1):25431; doi: 10.1038/s41598-025-10208-6
41.
MineraliE, FoilDH, ZornKM, et al.Comparing machine learning algorithms for predicting drug-induced liver injury (DILI). Mol Pharm2020;17(7):2628–2637; doi: 10.1021/acs.molpharmaceut.0c00326
42.
RyuJY, LeeMY, LeeJH, et al.DeepHIT: A deep learning framework for prediction of hERG-induced cardiotoxicity. Bioinformatics2020;36(10):3049–3055; doi: 10.1093/bioinformatics/btaa075
43.
SwansonK, LiuG, CatacutanDB, et al.Generative AI for designing and validating easily synthesizable and structurally novel antibiotics. Nat Mach Intell2024;6(3):338–353; doi: 10.1038/s42256-024-00809-7
44.
FernandesPO, DiasALT, dos Santos JúniorVS, et al.Machine learning-based virtual screening of antibacterial agents against Methicillin-susceptible and resistant Staphylococcus aureus. J Chem Inf Model2024;64(6):1932–1944; doi: 10.1021/acs.jcim.4c00087
45.
ZakharovAV, PeachML, SitzmannM, et al.QSAR modeling of imbalanced high-throughput screening data in PubChem. J Chem Inf Model2014;54(3):705–712; doi: 10.1021/ci400737s
46.
Diéguez-SantanaK, Casañola-MartinGM, TorresR, et al.Machine learning study of metabolic networks vs ChEMBL data of antibacterial compounds. Mol Pharm2022;19(7):2151–2163; doi: 10.1021/acs.molpharmaceut.2c00029
47.
MendezD, GaultonA, BentoAP, et al.ChEMBL: Towards direct deposition of bioassay data. Nucleic Acids Res2019;47(D1):D930–D940; doi: 10.1093/nar/gky1075
48.
ZdrazilB, FelixE, HunterF, et al.The ChEMBL database in 2023: A drug discovery platform spanning multiple bioactivity data types and time periods. Nucleic Acids Res2024;52(D1):D1180–D1192; doi: 10.1093/nar/gkad1004
49.
WangY, XiaoJ, SuzekTO, et al.PubChem: A public information system for analyzing bioactivities of small molecules. Nucleic Acids Res2009;37(Web Server issue):W623–W633; doi: 10.1093/nar/gkp456
50.
KimS, ThiessenPA, BoltonEE, et al.PubChem substance and compound databases. Nucleic Acids Res2016;44(D1):D1202–D1213; doi: 10.1093/nar/gkv951
51.
KimS, ChenJ, ChengT, et al.PubChem 2023 update. Nucleic Acids Res2023;51(D1):D1373–D1380.
ChenX, LiuM, GilsonM. BindingDB: A web-accessible molecular recognition database. Comb Chem High Throughput Screen2001;4(8):719–725; doi: 10.2174/1386207013330670
54.
ChenX, LinY, GilsonMK. The binding database: Overview and user’s guide. Biopolymers2001;61(2):127–141; doi: 10.1002/1097-0282(2002)61:2%3C127::AID-BIP10076%3E3.0.CO;2-N
55.
ChenX, LinY, LiuM, et al.The binding database: Data management and interface design. Bioinformatics2002;18(1):130–139; doi: 10.1093/bioinformatics/18.1.130
56.
LiuT, LinY, WenX, et al.BindingDB: A web-accessible database of experimentally determined protein-ligand binding affinities. Nucleic Acids Res2007;35(Database issue):D198–D201; doi: 10.1093/nar/gkl999
57.
GilsonMK, LiuT, BaitalukM, et al.BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res2016;44(D1):D1045–D1053; doi: 10.1093/nar/gkv1072
58.
LiuT, HwangL, BurleySK, et al.BindingDB in 2024: A FAIR knowledgebase of protein-small molecule binding data. Nucleic Acids Res2025;53(D1):D1633–D1644; doi: 10.1093/nar/gkae1075
59.
FourchesD, MuratovE, TropshaA. Trust, but verify II: A practical guide to chemogenomics data curation. J Chem Inf Model2016;56(7):1243–1252; doi: 10.1021/acs.jcim.6b00129
60.
PapadatosG, GaultonA, HerseyA, et al.Activity, assay and target data curation and quality in the ChEMBL database. J Comput Aided Mol Des2015;29(9):885–896; doi: 10.1007/s10822-015-9860-5
61.
DesselleMR, NealeR, HansfordKA, et al.Institutional profile: Community for open antimicrobial drug discovery—Crowdsourcing new antibiotics and antifungals. Future Sci OA2017;3(2):FSO171; doi: 10.4155/fsoa-2016-0093
62.
SadybekovAV, KatritchV. Computational approaches streamlining drug discovery. Nature2023;616(7958):673–685; doi: 10.1038/s41586-023-05905-z
63.
BlaskovichMAT, ZueggJ, ElliottAG, et al.Helping chemists discover new antibiotics. ACS Infect Dis2015;1(7):285–287; doi: 10.1021/acsinfecdis.5b00044
64.
WishartDS, KnoxC, GuoAC, et al.DrugBank: A comprehensive resource for in silico drug discovery and exploration. Nucleic Acids Res2006;34(Database issue):D668–D672; doi: 10.1093/nar/gkj067
65.
WishartDS, KnoxC, GuoAC, et al.DrugBank: A knowledgebase for drugs, drug actions and drug targets. Nucleic Acids Res2008;36(Database issue):D901–D906; doi: 10.1093/nar/gkm958
66.
KnoxC, LawV, JewisonT, et al.DrugBank 3.0: A comprehensive resource for ‘OMICS’ research on drugs. Nucleic Acids Res2011;39(Database issue):D1035–D1041; doi: 10.1093/nar/gkq1126
67.
LawV, KnoxC, DjoumbouY, et al.DrugBank 4.0: Shedding new light on drug metabolism. Nucleic Acids Res2014;42(Database issue):D1091–D1097; doi: 10.1093/nar/gkt1068
68.
WishartDS, FeunangYD, GuoAC, et al.DrugBank 5.0: A major update to the DrugBank database for 2018. Nucleic Acids Res2018;46(D1):D1074–D1082; doi: 10.1093/nar/gkx1037
69.
KnoxC, WilsonM, KlingerCM, et al.DrugBank 6.0: The DrugBank knowledgebase for 2024. Nucleic Acids Res2024;52(D1):D1265–D1275; doi: 10.1093/nar/gkad976
70.
HalipL, AvramS, CurpanR, et al.Exploring DrugCentral: From molecular structures to clinical effects. J Comput Aided Mol Des2023;37(12):681–694; doi: 10.1007/s10822-023-00529-x
71.
CorselloSM, BittkerJA, LiuZ, et al.The drug repurposing hub: A next-generation drug library and information resource. Nat Med2017;23(4):405–408; doi: 10.1038/nm.4306
72.
ZengX, ZhangP, HeW, et al.NPASS: Natural product activity and species source database for natural product research, discovery and tool development. Nucleic Acids Res2018;46(D1):D1217–D1222; doi: 10.1093/nar/gkx1026
73.
ZhaoH, YangY, WangS, et al.NPASS database update 2023: Quantitative natural product activity and species source database for biomedical research. Nucleic Acids Res2023;51(D1):D621–D628; doi: 10.1093/nar/gkac1069
74.
Martinez-MayorgaK, Rosas-JiménezJG, Gonzalez-PonceK, et al.The pursuit of accurate predictive models of the bioactivity of small molecules. Chem Sci2024;15(6):1938–1952; doi: 10.1039/D3SC05534E
75.
MeloMCR, MaaschJRMA, de la Fuente-NunezC. Accelerating antibiotic discovery through artificial intelligence. Commun Biol2021;4(1):1050; doi: 10.1038/s42003-021-02586-0
76.
MiethkeM, PieroniM, WeberT, et al.Towards the sustainable discovery and development of new antibiotics. Nat Rev Chem2021;5(10):726–749; doi: 10.1038/s41570-021-00313-1
77.
VeríssimoGC, dos Santos JúniorVS, de AlmeidaIAdR, et al.The Brazilian compound library (BraCoLi) database: A repository of chemical and biological information for drug design. Mol Divers2022;26(6):3387–3397; doi: 10.1007/s11030-022-10386-9
78.
PilonAC, ValliM, DamettoAC, et al.NuBBEDB: An updated database to uncover chemical and biological information from Brazilian biodiversity. Sci Rep2017;7(1):7215; doi: 10.1038/s41598-017-07451-x
MacNairCR, RutherfordST, TanM-W. Alternative therapeutic strategies to treat antibiotic-resistant pathogens. Nat Rev Microbiol2024;22(5):262–275; doi: 10.1038/s41579-023-00993-0
81.
LandrumGA, RinikerS. Combining IC50 or Ki values from different sources is a source of significant noise. J Chem Inf Model2024;64(5):1560–1567; doi: 10.1021/acs.jcim.4c00049
82.
SchoenmakerL, SastrokarijoEG, HeitmanLH, et al.Toward assay-aware bioactivity model(er)s: Getting a grip on biological context. J Chem Inf Model2025;65(13):7013–7023; doi: 10.1021/acs.jcim.5c00603
83.
CesaroA, BagheriM, TorresM, et al.Deep learning tools to accelerate antibiotic discovery. Expert Opin Drug Discov2023;18(11):1245–1257; doi: 10.1080/17460441.2023.2250721
84.
SmajićA, RamiI, SosninS, et al.Identifying differences in the performance of machine learning models for off-targets trained on publicly available and proprietary data sets. Chem Res Toxicol2023;36(8):1300–1312; doi: 10.1021/acs.chemrestox.3c00042
85.
BoscN, AtkinsonF, FelixE, et al.Large scale comparison of QSAR and conformal prediction methods and their applications in drug discovery. J Cheminform2019;11(1):4; doi: 10.1186/s13321-018-0325-4
86.
BhalodiAA, OppermannN, CampeauSA, et al.Variability of Beta-Lactam Broth Microdilution for Pseudomonas aeruginosa. Antimicrob Agents Chemother2021;65(10):e00640-21; doi: 10.1128/AAC.00640-21
87.
IngleseJ, ShamuCE, GuyRK. Reporting data from high-throughput screening of small-molecule libraries. Nat Chem Biol2007;3(8):438–441; doi: 10.1038/nchembio0807-438
88.
FanelliD. Negative results are disappearing from most disciplines and countries. Scientometrics2012;90(3):891–904; doi: 10.1007/s11192-011-0494-7
de la Fuente-NunezC, CollinsJJ. Essay: Using machine learning for antibiotic discovery. Phys Rev Lett2025;135(3):030001; doi: 10.1103/y3fg-s9vg
91.
KapoorS, NarayananA. Leakage and the reproducibility crisis in machine-learning-based science. Patterns (N Y)2023;4(9):100804; doi: 10.1016/j.patter.2023.100804
MonganJ, MoyL, KahnCE. Checklist for artificial intelligence in medical imaging (CLAIM): A guide for authors and reviewers. Radiol Artif Intell2020;2(2):e200029; doi: 10.1148/ryai.2020200029
94.
TejaniAS, KlontzasME, GattiAA,et al.; CLAIM 2024 Update Panel. Checklist for artificial intelligence in medical imaging (CLAIM): 2024 update. Radiol Artif Intell2024;6(4):e240300; doi: 10.1148/ryai.240300
95.
WilkinsonMD, DumontierM, AalbersbergI, et al.The FAIR guiding principles for scientific data management and stewardship. Sci Data2016;3(1):160018; doi: 10.1038/sdata.2016.18
96.
WarrWA. Representation of chemical structures. WIREs Comput Mol Sci2011;1(4):557–579; doi: 10.1002/wcms.36
97.
WiswesserWJ. 107 years of line-formula notations (1861-1968). J Chem Doc1968;8(3):146–150; doi: 10.1021/c160030a007
98.
DysonGM, LynchMF, MorganHL. A modified IUPAC-Dyson notation system for chemical structures. Information Storage and Retrieval1968;4(1):27–83; doi: 10.1016/0020-0271(68)90004-1
99.
WeiningerD. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J Chem Inf Comput Sci1988;28(1):31–36; doi: 10.1021/ci00057a005
100.
MoretM, Pachon AngonaI, CotosL, et al.Leveraging molecular structure and bioactivity with chemical language models for de novo drug design. Nat Commun2023;14(1):114; doi: 10.1038/s41467-022-35692-6
101.
WangS, GuoY, WangY, et al.SMILES-BERT: Large scale unsupervised pre-training for molecular property prediction. In: Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics ACM2019; pp. 429–436; doi: 10.1145/3307339.3342186
102.
IkebataH, HongoK, IsomuraT, et al.Bayesian molecular design with a chemical language model. J Comput Aided Mol Des2017;31(4):379–391; doi: 10.1007/s10822-016-0008-z
103.
WuK, XiaY, DengP, et al.TamGen: Drug design with target-aware molecule generation through a chemical language model. Nat Commun2024;15(1):9360; doi: 10.1038/s41467-024-53632-4
104.
TrottO, OlsonAJ. AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J Comput Chem2010;31(2):455–461; doi: 10.1002/jcc.21334
105.
GuoJ, LiuQ, GuoH, et al.Ligandformer: A graph neural network for predicting compound property with robust interpretation. arXiv [Preprint]2022; doi: 10.48550/arXiv.2202.10873
106.
GrisoniF. Chemical language models for de novo drug design: Challenges and opportunities. Curr Opin Struct Biol2023;79:102527; doi: 10.1016/j.sbi.2023.102527
107.
WeiningerD, WeiningerA, WeiningerJL. SMILES. 2. Algorithm for generation of unique SMILES notation. J Chem Inf Comput Sci1989;29(2):97–101; doi: 10.1021/ci00062a008
108.
O’BoyleNM. Towards a universal SMILES representation—A standard method to generate canonical SMILES based on the InChI. J Cheminform2012;4(1):22; doi: 10.1186/1758-2946-4-22
109.
SkinniderMA. Invalid SMILES are beneficial rather than detrimental to chemical language models. Nat Mach Intell2024;6(4):437–448; doi: 10.1038/s42256-024-00821-x
110.
BjerrumEJ. SMILES enumeration as data augmentation for neural network modeling of molecules. arXiv [Preprint]2017; doi: 10.48550/arXiv.1703.07076
111.
MoretM, FriedrichL, GrisoniF, et al.Generative molecular design in low data regimes. Nat Mach Intell2020;2(3):171–180; doi: 10.1038/s42256-020-0160-y
112.
BornJ, MarkertG, JanakarajanN, et al.Chemical representation learning for toxicity prediction. Digit Discov2023;2(3):674–691; doi: 10.1039/D2DD00099G
113.
Arús-PousJ, JohanssonS, PrykhodkoO, et al.Improving Deep Generative Models with Randomized SMILES. In: TetkoIV, KůrkováV, KarpovP, et al., editors. Artificial Neural Networks and Machine Learning—ICANN 2019: Workshop and Special Sessions. Lecture Notes in Computer Science, vol 11731. Cham: Springer; 2019; pp. 747–751; doi: 10.1007/978-3-030-30493-5_68
114.
O’BoyleN, DalkeA. DeepSMILES: An adaptation of SMILES for use in machine-learning of chemical structures. ChemRxiv [Preprint]2018; doi: 10.26434/chemrxiv.7097960.v1
115.
BhadwalAS, KumarK, KumarN. GenSMILES: An enhanced validity conscious representation for inverse design of molecules. Knowl Based Syst2023;268:110429; doi: 10.1016/j.knosys.2023.110429
116.
KrennM, HäseF, NigamA, et al.Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation. Mach Learn: Sci Technol2020;1(4):045024; doi: 10.1088/2632-2153/aba947
117.
Gómez-BombarelliR, WeiJN, DuvenaudD, et al.Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent Sci2018;4(2):268–276; doi: 10.1021/acscentsci.7b00572
118.
SchoenmakerL, BéquignonOJM, JespersW, et al.UnCorrupt SMILES: A novel approach to de novo design. J Cheminform2023;15(1):22; doi: 10.1186/s13321-023-00696-x
119.
HellerSR, McNaughtA, PletnevI, et al.InChI, the IUPAC international chemical identifier. J Cheminform2015;7(1):23; doi: 10.1186/s13321-015-0068-4
120.
WinterR, MontanariF, NoéF, et al.Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations. Chem Sci2019;10(6):1692–1701; doi: 10.1039/C8SC04175J
121.
RajanK, SteinbeckC, ZielesnyA. Performance of chemical structure string representations for chemical image recognition using transformers. Digit Discov2022;1(2):84–90; doi: 10.1039/D1DD00013F
122.
DavidL, ThakkarA, MercadoR, et al.Molecular representations in AI-driven drug discovery: A review and practical guide. J Cheminform2020;12(1):56; doi: 10.1186/s13321-020-00460-5
DuvenaudD, MaclaurinD, Aguilera-IparraguirreJ, et al.Convolutional networks on graphs for learning molecular fingerprints. arXiv [Preprint]2015; doi: 10.48550/arXiv.1509.09292
125.
GilmerJ, SchoenholzSS, RileyPF, et al.Neural message passing for quantum chemistry. arXiv [Preprint]2017; doi: 10.48550/arXiv.1704.01212
126.
YangK, SwansonK, JinW, et al.Analyzing learned molecular representations for property prediction. J Chem Inf Model2019;59(8):3370–3388; doi: 10.1021/acs.jcim.9b00237
127.
StokesJM, YangK, SwansonK, et al.A deep learning approach to antibiotic discovery. Cell2020;180(4):688–702.e13; doi: 10.1016/j.cell.2020.01.021
128.
LiuG, CatacutanDB, RathodK, et al.Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii. Nat Chem Biol2023;19(11):1342–1350; doi: 10.1038/s41589-023-01349-8
129.
KrishnanA, AnahtarMN, ValeriJA, et al.A generative deep learning approach to de novo antibiotic design. Cell2025;188(21):5962–5979.e22; doi: 10.1016/j.cell.2025.07.033
130.
HeidE, GreenmanKP, ChungY, et al.Chemprop: A machine learning package for chemical property prediction. J Chem Inf Model2024;64(1):9–17; doi: 10.1021/acs.jcim.3c01250
131.
FangX, LiuL, LeiJ, et al.Geometry-enhanced molecular representation learning for property prediction. Nat Mach Intell2022;4(2):127–134; doi: 10.1038/s42256-021-00438-4
132.
MaatenL V D, HintonG. Visualizing Data using t-SNE. J Mach Learn Res2008;9(86):2579–2605.
133.
RamakrishnanR, DralPO, RuppM, et al.Quantum chemistry structures and properties of 134 kilo molecules. Sci Data2014;1(1):140022; doi: 10.1038/sdata.2014.22
134.
RuddigkeitL, Van DeursenR, BlumLC, et al.Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. J Chem Inf Model2012;52(11):2864–2875; doi: 10.1021/ci300415d
135.
CremerJ, Medrano SandonasL, TkatchenkoA, et al.Equivariant graph neural networks for toxicity prediction. Chem Res Toxicol2023;36(10):1561–1573; doi: 10.1021/acs.chemrestox.3c00032
136.
DobbelaereMR, LengyelI, StevensCV, et al.Geometric deep learning for molecular property predictions with chemical accuracy across chemical space. J Cheminform2024;16(1):99; doi: 10.1186/s13321-024-00895-0
GaoK, NguyenDD, SreshtV, et al.Are 2D fingerprints still valuable for drug discovery? Phys Chem Chem Phys2020;22(16):8373–8390; doi: 10.1039/D0CP00305K
LiJ, JiangX. Mol-BERT: An effective molecular representation with BERT for molecular property prediction. Wirel Commun Mob Comput2021;2021(1):7181815; doi: 10.1155/2021/7181815
142.
LiuY, ZhangR, LiT, et al.MolRoPE-BERT: An enhanced molecular representation with rotary position embedding for molecular property prediction. J Mol Graph Model2023;118:108344; doi: 10.1016/j.jmgm.2022.108344
143.
ZhengX, TomiuraY. A BERT-based pretraining model for extracting molecular structural information from a SMILES sequence. J Cheminform2024;16(1):71; doi: 10.1186/s13321-024-00848-7
144.
ScaliaG, RutherfordST, LuZ, et al.A high-throughput phenotypic screen combined with an ultra-large-scale deep learning-based virtual screening reveals novel scaffolds of antibacterial compounds. bioRxiv [Preprint]2024; doi: 10.1101/2024.09.11.612340
145.
DevlinJ, ChangM-W, LeeK, et al.BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv [Preprint]2019; doi: 10.48550/arXiv.1810.04805
146.
IrwinJJ, SterlingT, MysingerMM, et al.ZINC: A free tool to discover chemistry for biology. J Chem Inf Model2012;52(7):1757–1768; doi: 10.1021/ci3001277
147.
WuZ, RamsundarB, FeinbergEN, et al.MoleculeNet: A benchmark for molecular machine learning. Chem Sci2018;9(2):513–530; doi: 10.1039/C7SC02664A
148.
O’SheaR, MoserHE. Physicochemical properties of antibacterial compounds: Implications for drug discovery. J Med Chem2008;51(10):2871–2878; doi: 10.1021/jm700967e
149.
LipinskiCA, LombardoF, DominyBW, et al.Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Adv Drug Deliv Rev1997;23(1–3):3–25; doi: 10.1016/S0169-409X(96)00423-1
150.
HuangK, FuT, GaoW, et al.Therapeutics data commons: Machine learning datasets and tasks for drug discovery and development. arXiv [Preprint]2021; doi: 10.48550/arXiv.2102.09548arXiv:2102.09548v2,
151.
SwansonK, WaltherP, LeitzJ, et al.ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries. Bioinformatics2024;40(7):btae416; doi: 10.1093/bioinformatics/btae416
152.
HirschfeldL, SwansonK, YangK, et al.Uncertainty quantification using neural networks for molecular property prediction. J Chem Inf Model2020;60(8):3770–3780; doi: 10.1021/acs.jcim.0c00502
153.
NaikAW, KangasJD, SullivanDP, et al.Active machine learning-driven experimentation to determine compound effects on protein patterns. Elife2016;5:e10047; doi: 10.7554/eLife.10047
154.
RekerD, SchneiderP, SchneiderG. Multi-objective active machine learning rapidly improves structure–activity models and reveals new protein–protein interaction inhibitors. Chem Sci2016;7(6):3919–3927; doi: 10.1039/C5SC04272K
155.
RekerD, SchneiderG. Active-learning strategies in computer-assisted drug discovery. Drug Discov Today2015;20(4):458–465; doi: 10.1016/j.drudis.2014.12.004
156.
RekerD. Active learning for drug discovery and automated data curation. In: BrownN., editor. Artificial Intelligence in Drug Discovery. Drug Discovery Series. Cambridge: Royal Society of Chemistry; 2020. pp. 301–326; doi: 10.1039/9781788016841-00301
157.
van TilborgD, GrisoniF. Traversing chemical space with active deep learning for low-data drug discovery. Nat Comput Sci2024;4(10):786–796; doi: 10.1038/s43588-024-00697-2
158.
ThompsonJ, WaltersWP, FengJA, et al.Optimizing active learning for free energy calculations. Artif Intell Life Sci2022;2:100050; doi: 10.1016/j.ailsci.2022.100050
159.
FralishZ, RekerD. Taking a deep dive with active learning for drug discovery. Nat Comput Sci2024;4(10):727–728; doi: 10.1038/s43588-024-00704-6
160.
GusevF, GutkinE, KurnikovaMG, et al.Active learning guided drug design lead optimization based on relative binding free energy modeling. J Chem Inf Model2023;63(2):583–594; doi: 10.1021/acs.jcim.2c01052
161.
RekerD, SchneiderP, SchneiderG, et al.Active learning for computational chemogenomics. Future Med Chem2017;9(4):381–402; doi: 10.4155/fmc-2016-0197
162.
BaileyM, MoayedpourS, LiR, et al.Deep batch active learning for drug discovery. Elife2024:12; doi: 10.7554/eLife.89679.2
163.
GorantlaR, KubincováA, SuutariB, et al.Benchmarking active learning protocols for ligand-binding affinity prediction. J Chem Inf Model2024;64(6):1955–1965; doi: 10.1021/acs.jcim.4c00220
164.
LittmannM, SeligK, Cohen-LaviL, et al.Validity of machine learning in biology and medicine increased through collaborations across fields of expertise. Nat Mach Intell2020;2(1):18–24; doi: 10.1038/s42256-019-0139-8
