BioPrint Meets the AI Age: Development of Artificial Intelligence-Based ADMET Models for the Drug-Discovery Platform SAFIRE

References

• Göller AH , KuhnkeL, MontanariFet al. Bayer’s in silico ADMET platform: a journey of machine learning over the past two decades. Drug Discov. Today25(9), 1702–1709 (2020).
   PubMed Web of Science ®Google Scholar
• Kumar K , ChupakhinV, VosAet al. Development and implementation of an enterprise-wide predictive model for early absorption, distribution, metabolism and excretion properties. Future Med. Chem.13(19), 1639–1654 (2021).
   PubMed Web of Science ®Google Scholar
• Daina A , MichielinO, ZoeteV. SwissADME: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules. Sci. Rep.7(1), 42717 (2017).
   PubMed Web of Science ®Google Scholar
• Xiong G , WuZ, YiJet al. ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties. Nucleic Acids Res.49(W1), W5–W14 (2021).
   PubMed Web of Science ®Google Scholar
• Yang H , LouC, SunLet al. admetSAR 2.0: web-service for prediction and optimization of chemical ADMET properties. Bioinformatics35(6), 1067–1069 (2019).
   PubMed Web of Science ®Google Scholar
• Pires DEV , BlundellTL, AscherDB. pkCSM: predicting small-molecule pharmacokinetic and toxicity properties using graph-based signatures. J. Med. Chem.58(9), 4066–4072 (2015).
   PubMed Web of Science ®Google Scholar
• Banerjee P , DunkelM, KemmlerE, PreissnerR. SuperCYPsPred – a web server for the prediction of cytochrome activity. Nucleic Acids Res.48(W1), W580–W585 (2020).
   PubMed Web of Science ®Google Scholar
• Optibrium . StarDrop: small molecule drug discovery & data visualisation software. https://optibrium.com/stardrop/
   Google Scholar
• Krejsa CM , HorvathD, RogalskiSLet al. Predicting ADME properties and side effects: the BioPrint approach. Curr. Opin. Drug Discov. Devel.6(4), 470–480 (2003).
   PubMed Web of Science ®Google Scholar
• Reymond J-L . The Chemical Space Project. Acc. Chem. Res.48(3), 722–730 (2015).
   PubMed Web of Science ®Google Scholar
• Volkamer A , RinikerS, NittingerEet al. Machine learning for small molecule drug discovery in academia and industry. Artif. Intell. Life Sci.3, 100056 (2023).
   Google Scholar
• Lombardo F , DesaiPV, ArimotoRet al. In silico absorption, distribution, metabolism, excretion, and pharmacokinetics (ADME-PK): utility and best practices. An industry perspective from the International Consortium for Innovation through Quality in Pharmaceutical Development. J. Med. Chem.60(22), 9097–9113 (2017).
   PubMed Web of Science ®Google Scholar
• Rácz A , BajuszD, Miranda-QuintanaRA, HébergerK. Machine learning models for classification tasks related to drug safety. Mol. Divers.25(3), 1409–1424 (2021).
   PubMed Web of Science ®Google Scholar
• Fromer JC , ColeyCW. Computer-aided multi-objective optimization in small molecule discovery. Patterns4(2), 100678 (2023).
   PubMedGoogle Scholar
• Tran TTV , TayaraH, ChongKT. Artificial intelligence in drug metabolism and excretion prediction: recent advances, challenges, and future perspectives. Pharmaceutics15(4), 1260 (2023).
   PubMed Web of Science ®Google Scholar
• Maltarollo VG , GertrudesJC, OliveiraPR, HonorioKM. Applying machine learning techniques for ADME-Tox prediction: a review. Expert Opin. Drug Metab. Toxicol.11(2), 259–271 (2015).
   PubMed Web of Science ®Google Scholar
• Dara S , DhamercherlaS, JadavSS, BabuCM, AhsanMJ. Machine learning in drug discovery: a review. Artif. Intell. Rev.55(3), 1947–1999 (2022).
   PubMed Web of Science ®Google Scholar
• Jiménez-Luna J , GrisoniF, SchneiderG. Drug discovery with explainable artificial intelligence. Nat. Mach. Intell.2(10), 573–584 (2020).
   Google Scholar
• Mendez D , GaultonA, BentoAPet al. ChEMBL: towards direct deposition of bioassay data. Nucleic Acids Res.47(D1), D930–D940 (2019).
   PubMed Web of Science ®Google Scholar
• Cui Q , LuS, NiBet al. Improved prediction of aqueous solubility of novel compounds by going deeper with deep learning. Front. Oncol.10, (2020).
   Web of Science ®Google Scholar
• Lou C , YangH, WangJet al. IDL-PPBopt: a strategy for prediction and optimization of human plasma protein binding of compounds via an interpretable deep learning method. J. Chem. Inf. Model.62(11), 2788–2799 (2022).
   PubMed Web of Science ®Google Scholar
• Ingle BL , VeberBC, NicholsJW, Tornero-VelezR. Informing the human plasma protein binding of environmental chemicals by machine learning in the pharmaceutical space: applicability domain and limits of predictability. J. Chem. Inf. Model.56(11), 2243–2252 (2016).
   PubMed Web of Science ®Google Scholar
• Du F , YuH, ZouB, BabcockJ, LongS, LiM. hERGCentral: a large database to store, retrieve, and analyze compound-human Ether-à-go-go related gene channel interactions to facilitate cardiotoxicity assessment in drug development. Assay Drug Dev. Technol.9(6), 580–588 (2011).
   PubMed Web of Science ®Google Scholar
• National Center for Biotechnology Information . PubChem bioassay record for AID 1851, cytochrome panel assay with activity outcomes (2009). https://pubchem.ncbi.nlm.nih.gov/bioassay/1851
   Google Scholar
• XGBoost parameters – xgboost 2.0.3 documentation (2022). https://xgboost.readthedocs.io/en/stable/parameter.html
   Google Scholar
• Chawla NV , BowyerKW, HallLO, KegelmeyerWP. SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res.16, 321–357 (2002).
   Web of Science ®Google Scholar
• Pedregosa F , VaroquauxG, GramfortAet al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res.12(85), 2825–2830 (2011).
   Google Scholar
• Landrum G . RDKit: open-source cheminformatics software (2023). https://rdkit.org/
   Google Scholar
• Rogers D , HahnM. Extended-connectivity fingerprints. J. Chem. Inf. Model.50(5), 742–754 (2010).
   PubMed Web of Science ®Google Scholar
• Breiman L . Random forests. Mach. Learn.45(1), 5–32 (2001).
   Web of Science ®Google Scholar
• Cortes C , VapnikV. Support-vector networks. Mach. Learn.20(3), 273–297 (1995).
   Web of Science ®Google Scholar
• Zhang H . The optimality of Naive Bayes (2024).
   Google Scholar
• Chen T , GuestrinC. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Association for Computing Machinery, NY, USA, 785–794 (2016). 10.1145/2939672.2939785
   Google Scholar
• Berthold MR , CebronN, DillFet al. KNIME: the Konstanz information miner. In: Data Analysis, Machine Learning and Applications.PreisachC, BurkhardtH, Schmidt-ThiemeL, DeckerR ( Eds). Springer, Berlin, Germany, 319–326 (2008).
   Google Scholar
• Chicco D , JurmanG. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics21(1), 6 (2020).
   PubMed Web of Science ®Google Scholar
• Jaworska J , Nikolova-JeliazkovaN, AldenbergT. QSAR applicability domain estimation by projection of the training set in descriptor space: a review. Altern. Lab. Anim.33(5), 445–459 (2005).
   PubMed Web of Science ®Google Scholar
• Delaney JS . ESOL: estimating aqueous solubility directly from molecular structure. J. Chem. Inf. Comput. Sci.44(3), 1000–1005 (2004).
   PubMedGoogle Scholar
• Ruddigkeit L , van DeursenR, BlumLC, ReymondJ-L. Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. J. Chem. Inf. Model.52(11), 2864–2875 (2012).
   PubMed Web of Science ®Google Scholar