TANGO: direct optimization of constrained synthesizability for generative molecular design

Summarize this content to 100 words: Gao, W. & Coley, C. W. The synthesizability of molecules proposed by generative models. J. Chem. Inf. Model. 60, 5714–5723 (2020).Article 

Google Scholar 
Stanley, M. & Segler, M. Fake it until you make it? Generative de novo design and virtual screening of synthesizable molecules. Curr. Opin. Struct. Biol. 82, 102658 (2023).Article 

Google Scholar 
Du, Y. et al. Machine learning-aided generative molecular design. Nat. Mach. Intell. 6, 589–604 (2024).Coley, C. W. et al. Autonomous discovery in the chemical sciences part I: progress. Angew. Chem. Int. Ed. 59, 22858–22893 (2020).Article 

Google Scholar 
Coley, C. W. et al. Autonomous discovery in the chemical sciences part II: outlook. Angew. Chem. Int. Ed. 59, 23414–23436 (2020).Article 

Google Scholar 
Tom, G. et al. Self-driving laboratories for chemistry and materials science. Chem. Rev. 124, 9633–9732 (2024).Article 

Google Scholar 
Sin, J. W. et al. Highly parallel optimisation of chemical reactions through automation and machine intelligence. Nat. Commun. 16, 6464 (2025).Article 

Google Scholar 
Neeser, R. M. et al. FSscore: a personalized machine learning-based synthetic feasibility score leveraging human expertise. Chem. Methods 4, e202400024 (2024).Bradshaw, J. et al. A model to search for synthesizable molecules. In Proc. 33rd International Conference on Neural Information Processing Systems 7937–7949 (Curran Associates Inc., 2019).Bradshaw, J. et al. Barking up the right tree: an approach to search over molecule synthesis DAGs. Adv. Neural Inf. Process. Syst 33, 6852–6866 (2020).
Google Scholar 
Gao, W. et al. Amortized tree generation for bottom-up synthesis planning and synthesizable molecular design. In Proc. 10th International Conference on Learning Representations (ICLR, 2022); https://openreview.net/forum?id=FRxhHdnxt1Koziarski, M. et al. RGFN: synthesizable molecular generation using GFlowNets. In Proc. 38th International Conference on Neural Information Processing Systems 46908–46955 (Curran Associates Inc., 2024).Cretu, M. et al. SynFlowNet: towards molecule design with guaranteed synthesis pathways. In Proc. 13th International Conference on Learning Representations 47101–47126 (ICLR, 2025).Seo, S. et al. Generative flows on synthetic pathway for drug design. In Proc. 13th International Conference on Learning Representations 14029–14060 (ICLR, 2025).Gao, W., Luo, S. & Coley, C. W. Generative AI for navigating synthesizable chemical space. Proc. Natl Acad. Sci. USA 122, e2415665122 (2025).Article 

Google Scholar 
Liu, B. et al. Retrosynthetic reaction prediction using neural sequence-to-sequence models. ACS Cent. Sci. 3, 1103–1113 (2017).Article 

Google Scholar 
Segler, M. H. & Waller, M. P. Neural-symbolic machine learning for retrosynthesis and reaction prediction. Chem. Eur. J. 23, 5966–5971 (2017).Article 

Google Scholar 
Coley, C. W. et al. Computer-assisted retrosynthesis based on molecular similarity. ACS Cent. Sci. 3, 1237–1245 (2017).Article 

Google Scholar 
Segler, M. H. et al. Planning chemical syntheses with deep neural networks and symbolic AI. Nature 555, 604–610 (2018).Article 

Google Scholar 
Schwaller, P. et al. Predicting retrosynthetic pathways using transformer-based models and a hyper-graph exploration strategy. Chem. Sci. 11, 3316–3325 (2020).Article 

Google Scholar 
Shields, J. D. et al. AiZynth impact on medicinal chemistry practice at AstraZeneca. RSC Med. Chem. 15, 1085–1095 (2024).Article 

Google Scholar 
Guo, J. & Schwaller, P. Directly optimizing for synthesizability in generative molecular design using retrosynthesis models. Chem. Sci. 16, 6943–6956 (2025).Article 

Google Scholar 
Vollmann, D. J. et al. Emerging concepts in the semisynthetic and mutasynthetic production of natural products. Curr. Opin. Biotechnol. 77, 102761 (2022).Article 

Google Scholar 
Li, L. et al. Divergent strategy in natural product total synthesis. Chem. Rev. 118, 3752–3832 (2018).Article 

Google Scholar 
Granda, J. M. et al. Controlling an organic synthesis robot with machine learning to search for new reactivity. Nature 559, 377–381 (2018).Article 

Google Scholar 
Wołos, A. et al. Synthetic connectivity, emergence, and self-regeneration in the network of prebiotic chemistry. Science 369, eaaw1955 (2020).Article 

Google Scholar 
Ża̧dło-Dobrowolska, A. et al. Computational synthesis design for controlled degradation and revalorization. Nat. Synth. 3, 643–654 (2024).Wołos, A. et al. Computer-designed repurposing of chemical wastes into drugs. Nature 604, 668–676 (2022).Article 

Google Scholar 
Shanks, B. H. & Keeling, A. P. Bioprivileged molecules: creating value from biomass. Green Chem. 19, 3177–3185 (2017).Article 

Google Scholar 
Johnson, A. P. et al. Starting material oriented retrosynthetic analysis in the LHASA program. 1. General description. J. Chem. Inf. Comput. Sci. 32, 411–417 (1992).Article 

Google Scholar 
Yu, Y. et al. GRASP: navigating retrosynthetic planning with goal-driven policy. Adv. Neural Inf. Process. Syst 35, 10257–10268 (2022).
Google Scholar 
Yu, K. et al. Double-ended synthesis planning with goal-constrained bidirectional search. Adv. Neural Inf. Process. Syst 37, 112919–112949 (2024).
Google Scholar 
Grzybowski, B. A. et al. Chematica: a story of computer code that started to think like a chemist. Chem 4, 390–398 (2018).Article 

Google Scholar 
Benhenda, M. ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity? Preprint at https://arxiv.org/abs/1708.08227 (2017).Guo, J. & Schwaller, P. Saturn: Sample-efficient generative molecular design using memory manipulation. Preprint at https://arxiv.org/abs/2405.17066 (2024).Bickerton, G. R. et al. Quantifying the chemical beauty of drugs. Nat. Chem. 4, 90–98 (2012).Article 

Google Scholar 
Castellino, N. J. et al. Late-stage functionalization for improving drug-like molecular properties. Chem. Rev. 123, 8127–8153 (2023).Article 

Google Scholar 
McInnes, L. et al. UMAP: uniform manifold approximation and projection for dimension reduction. J. Open Source Softw. 3, 861 (2018).Article 

Google Scholar 
Deb, P. K. et al. in Nonsteroidal Anti-Inflammatory Drugs (ed. Al-kaf, A. G. A.) Ch. 6 (IntechOpen, 2017).Sun, S. X. et al. Withdrawal of COX-2 selective inhibitors rofecoxib and valdecoxib: impact on NSAID and gastroprotective drug prescribing and utilization. Curr. Med. Res. Opin. 23, 1859–1866 (2007).Article 

Google Scholar 
Kurumbail, R. G. et al. Structural basis for selective inhibition of cyclooxygenase-2 by anti-inflammatory agents. Nature 384, 644–648 (1996).Article 

Google Scholar 
Sterling, T. & Irwin, J. J. ZINC 15—ligand discovery for everyone. J. Chem. Inf. Model. 55, 2324–2337 (2015).Article 

Google Scholar 
McNutt, A. T. et al. GNINA 1.0: molecular docking with deep learning. J. Cheminform. 3, 43 (2021).Article 

Google Scholar 
Trott, O. & Olson, A. J. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J. Comput. Chem. 31, 455–461 (2010).Article 

Google Scholar 
NameRxn v.3.7.3 (NextMove Software, 2024).Molga, K. et al. The logic of translating chemical knowledge into machine-processable forms: a modern playground for physical–organic chemistry. React. Chem. Eng. 4, 1506–1521 (2019).Article 

Google Scholar 
Genheden, S. et al. AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning. J. Cheminform. 12, 70 (2020).Article 

Google Scholar 
Saigiridharan, L. et al. AiZynthFinder 4.0: developments based on learnings from 3 years of industrial application. J. Cheminform. 16, 57 (2024).Article 

Google Scholar 
Maziarz, K. et al. Re-evaluating retrosynthesis algorithms with Syntheseus. Faraday Discuss. 31, 568–586 (2025).Article 

Google Scholar 
Tu, Z. et al. ASKCOS: an open source software suite for synthesis planning. Acc. Chem. Res. 58, 1764–1775 (2025).Ng, A. Y. et al. Policy invariance under reward transformations: theory and application to reward shaping. In ICML ’99: Proc. Sixteenth International Conference on Machine Learning (eds Bratko, I. & Dzeroski, S.) 278–287 (Morgan Kaufmann, 1999).Zhang, Y. et al. Evolutionary retrosynthetic route planning. IEEE Comput. Intell. Mag. 19, 58–72 (2024).Article 

Google Scholar 
Weininger, D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28, 31–36 (1988).Article 

Google Scholar 
Gu, A. & Dao, T. Mamba: linear-time sequence modeling with selective state spaces. In First Conference on Language Modeling (COLM, 2024); https://openreview.net/forum?id=tEYskw1VY2Bjerrum, E. J. SMILES enumeration as data augmentation for neural network modeling of molecules. Preprint at https://arxiv.org/abs/1703.07076 (2017).Lin, L.-J. Self-improving reactive agents based on reinforcement learning, planning and teaching. Mach. Learning 8, 293–321 (1992).Article 

Google Scholar 
Guo, J. & Schwaller, P. Augmented Memory: sample-efficient generative molecular design with reinforcement learning. JACS Au 4, 2160–2172 (2024).Article 

Google Scholar 
Kim, S. et al. PubChem 2023 update. Nucl. Acids Res. 51, D1373–D1380 (2023).Article 

Google Scholar 
Sacha, M. et al. Molecule Edit Graph Attention Network: modeling chemical reactions as sequences of graph edits. J. Chem. Inf. Model. 61, 3273–3284 (2021).Article 

Google Scholar 
Chen, B. et al. Retro*: learning retrosynthetic planning with neural guided A* search. Proc. Mach. Learning Res. 119, 1608–1616 (2020).Alhossary, A. et al. Fast, accurate, and reliable molecular docking with QuickVina 2. Bioinformatics 31, 2214–2216 (2015).Article 

Google Scholar 
Tang, S. et al. Vina-GPU 2.1: towards further optimizing docking speed and precision of AutoDock Vina and its derivatives. IEEE/ACM Trans. Comput. Biol. Bioinform. 21, 2382–2393 (2024).Mabanglo, M. F. et al. Potent ClpP agonists with anticancer properties bind with improved structural complementarity and alter the mitochondrial N-terminome. Structure 31, 185–200 (2023).Article 

Google Scholar 
Xie, Y. et al. How much space has been explored? Measuring the chemical space covered by databases and machine-generated molecules. In Proc. 11th International Conference on Learning Representations (ICLR, 2023); https://openreview.net/pdf?id=Yo06F8kfMa1Bemis, G. W. & Murcko, M. A. The properties of known drugs. 1. Molecular frameworks. J. Med. Chem. 39, 2887–2893 (1996).Article 

Google Scholar 
Guo, J. TANGO paper building blocks and code-base. figshare https://doi.org/10.6084/m9.figshare.27225483 (2025).



Source link