Enabling multi-target drug discovery through potential evolutionary optimization and synthesis-aware prioritization (EVOSYNTH)

Machine Learning


  • Ramsay, RR, Popovic-Nikolic, MR, Nikolic, K., Uliassi, E. & Bolognesi, ML Perspectives on multi-target drug discovery and design for complex diseases. Clin. translation. medicine. 73 (2018).

    Google Scholar

  • Halli-Tierney, AD, Scarbrough, C. & Carroll, D. Polypharmacy: Assessing risk and deprescribing. morning. Fam. doctor 10032–38 (2019).

    Google Scholar

  • Makhaba, XH, Viegas Jr, C., Mosa, RA, Viegas, FP & Pooe, OJ Potential impact of multitargeted drug approaches in the treatment of several complex diseases. Research and develop drugs. So. 143235–3249 (2020).

  • Katsoulaki, E.-E., Dimopoulos, D. & Hadjipavlou-Litina, D. Multitargeted compounds designed for Alzheimer’s disease, Parkinson’s disease, and Huntington’s neurodegenerative disease. pharmaceuticals 18831 (2025).

    Google Scholar

  • Doostmohammadi, A., Jooya, H., Ghorbanian, K., Gohari, S., Dadashpour, M. Potential and future prospects of multitargeted drugs in cancer treatment: Next generation anticancer drugs. cell commune. signal. twenty two228 (2024).

    Google Scholar

  • Zhang, K. et al. Artificial intelligence in drug development. nut. medicine. 3145–59 (2025).

    Google Scholar

  • Tanoli, Z. et al. Computational drug repurposing: approaches, in silico resource evaluation, and case studies. nut. Rev.DrugDiscov. twenty four521–542 (2025).

  • Savander, S. et al. Data-driven strategies for drug repurposing: Insights, recommendations, and case studies. Easy. Bioinformatics. 26bbaf625 (2025).

    Google Scholar

  • Reinshagen, J. et al. From library to landscape: an integrated annotation workflow for compound libraries in drug repurposing. database 2025baaf081 (2025).

    Google Scholar

  • Ianevski, A. et al. RePurposedrugs: an interactive web portal and predictive platform for repurposing monotherapies and combination therapies. Easy. Bioinformatics. twenty fivebbae328 (2024).

    Google Scholar

  • Aldahdooh, J., Tanoli, Z., and Tang, J. Mining drug-target interactions from the biomedical literature using ensemble transformer models based on chemical and genetic descriptions. Bioinformatics. advanced 4vbae106 (2024).

    Google Scholar

  • Aldahdooh, J., Vähä-Koskela, M., Tang, J., Tanoli, Z. Identifying drug-target interactions across PubMed using bert. BMC bioinformatics. twenty three245 (2022).

    Google Scholar

  • Legehar, A. et al. Ecodrug plus: an advanced database for conservation analysis and environmental risk assessment of pharmaceutical targets. Nucleic acid research institute 54D1397–D1404 (2026).

    Google Scholar

  • Tang, X. et al. Exploring generative AI for novel drug design: new frontiers in molecular and protein production. Easy. bioinf. twenty fivebbae338 (2024).

  • Kang, SI, Shin, JH, Wu, BM & Choi, HS Deep generative AI for multi-target therapy design: Towards a self-improving drug discovery framework. internal. J. Mol. Science. 2611443 (2025).

    Google Scholar

  • Zou, Y. et al. A structure-based framework for selective inhibitor design and optimization. common. Biol. 8422 (2025).

    Google Scholar

  • Stiller, T., Duensing-Kropp, S., Marschner, JA & Merk, D. Fragment-based discovery of dual-ligand pharmacophores of lipid-sensing transcription factors for engineered polypharmacology. RSC Medicine. Chemistry. 165012–5024 (2025).

    Google Scholar

  • Isigkeit, L. et al. Automatic design of multitarget ligands by generative deep learning. nut. common. 157946 (2024).

    Google Scholar

  • Liu, X. et al. Drugex v2: Novel design of drug molecules using Pareto-based multi-objective reinforcement learning in polypharmacology. J. Cheminf. 1385 (2021).

    Google Scholar

  • Li, Y., Lin, X., Hao, Y., Zhang, J. & Gao, YQ Molsculptor: A diffusion evolution framework for multisite inhibitor design. ChemRxiv (2025).

  • Ertl, P. & Schuffenhauer, A. Estimating the synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. J. Cheminf. 18 (2009).

    Google Scholar

  • Bickerton, GR, Paolini, GV, Besnard, J., Muresan, S., Hopkins, AL Quantifying the chemical beauty of drugs. nut. Chemistry. 490–98 (2012).

    Google Scholar

  • Swanson, K. and others. Generative AI for designing and validating easily synthesizable and structurally novel antibiotics. nut. Mach. intelligence. 6338–353 (2024).

    Google Scholar

  • Koziarski, M. et al. Rgfn: Synthesizable molecule generation using gflownet. Advanced neural information processes. system. 3746908–46955 (2024).

    Google Scholar

  • Coley, CW, Barzilay, R., Jaakkola, TS, Green, WH & Jensen, KF Predicting organic reaction outcomes using machine learning. ACS St. Science. 3434–443 (2017).

    Google Scholar

  • Genheden, S. et al. Aizynthfinder: Fast, robust, and flexible open-source software for retrosynthesis planning. J. Cheminf. 1270 (2020).

    Google Scholar

  • Fromer, JC & Coley, CW An algorithmic framework for synthetic cost-aware decision making in molecular design. nut. Calculate. Science. 4440–450 (2024).

    Google Scholar

  • Kim, H. et al. Targeting jnk3 against Alzheimer’s disease: Design and synthesis of novel inhibitors with wide pocket aryl group diversity. EUR. J.Med.Chemistry. 285117209 (2025).

    Google Scholar

  • Wang, D. et al. Combined inhibition of pi3k and parp is effective in treating ovarian cancer cells with wild-type PIK3CA gene. Guinecole. Oncor. 142548–556 (2016).

    Google Scholar

  • Schertens, P. et al. Alzheimer’s disease. lancet 3971577–1590 (2021).

    Google Scholar

  • Gong, C.-X., Liu, F. & Iqbal, K. Multifactorial hypothesis and multiple targets of Alzheimer’s disease. J. Alzheimer’s disease. Dis. 64S107–S117 (2018).

    Google Scholar

  • Probst, GD et al. Highly selective c-jun N-terminal kinase (JNK) 2 and 3 inhibitors with in vitro CNS-like pharmacokinetic properties prevent neurodegeneration. Bioorg. medicine. Chemistry. Let. twenty one315–319 (2011).

    Google Scholar

  • Buonfiglio, R. et al. Discovery of a novel imidazopyridine gsk-3β Inhibitors supported by computational approaches. molecule twenty five2163 (2020).

    Google Scholar

  • Shuai, W. et al. Discovery of a novel indazole chemotype as an isoform-selective JNK3 inhibitor for the treatment of Parkinson’s disease. J.Med.Chemistry. 661273–1300 (2023).

    Google Scholar

  • Jason, GC, Cohn, EC, Kitchener, HC, Lederman, JA Ovarian cancer. lancet 3841376–1388 (2014).

    Google Scholar

  • Murawski, M., Jagodziński, A., Bielawska-Pohl, A. & Klimczak, A. Complexity of the genetic background of carcinogenesis in ovarian cancer – genetic instability and clinical impact. cell 13345 (2024).

    Google Scholar

  • Walker, E.H. et al. Structural determinants of phosphoinositide 3-kinase inhibition by wortmannin, ly294002, quercetin, myricetin, and staurosporine. Mol. cell 6909–919 (2000).

    Google Scholar

  • Ogden, TE et al. Dynamics of the hd regulatory subdomain of parp-1. Substrate access and allostery in parp activation and inhibition. Nucleic acid research institute 492266–2288 (2021).

    Google Scholar

  • Oord, A. vd, Li, Y., Vinyals, O. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018).

  • Castro, E. et al. Transformer-based protein generation with normalized latent space optimization. nut. Mach. intelligence. 4840–851 (2022).

    Google Scholar

  • Schulman, A., Rousu, J., Aittokallio, T., Tanoli, Z. An attention-based approach to predicting drug-target interactions across seven target superfamilies. bioinformatics 40btae496 (2024).

    Google Scholar

  • McNutt, AT et al. Sprint enables interpretable, ultra-fast virtual screening of thousands of proteomes. arXiv electronic print arXiv–2411 (2024).

  • Passaro, S. et al. Voltz-2: Towards accurate and efficient binding affinity prediction. BioRxiv 2025-2006 (2025).

  • Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. in International Conference on Procedural Machine Learning1597–1607 (PMLR, 2020).

  • Huang, Y. et al. Dsdp: GPU-accelerated blind docking strategy. J. Chem. information model. 634355–4363 (2023).

    Google Scholar

  • RDKit — rdkit.org. https://www.rdkit.org/.

  • Deb, K., Pratap, A., Agarwal, S. & Meyarivan, T. A fast and elitist multi-objective genetic algorithm: Nsga-ii. IEEE Trans. Evolute. Calculate. 6182–197 (2002).

    Google Scholar

  • Chemspace Services: Compound sourcing and sourcing, hit discovery, molecular docking, custom synt — chem-space.com. https://chem-space.com/services.



  • Source link