A unified, pre-trained deep learning framework for predicting and integrated planning of cross-task responsive performance.

Machine Learning


  • churański, am, martinez alvarado, ji, shields, bj & doyle, ag predicts the yield of responses via monitored learning. acc. Chemistry. res. 541856–1865 (2021).

    Google Scholar

  • Quantitative Structures of Zahrt, AF, Athavale, SV & Denmark, SE – Selectivity Relationships in Enantioselective Catalysts: Past, Present, and Future. Chemistry. Pastor 1201620–1689 (2020).

    Google Scholar

  • Computer-aided analysis in Corey, EJ, Long, AK & Rubenstein, SD Organic Synthesis. Science 228408–418 (1985).

    Google Scholar

  • Todd, MH Computer-Aided Organic Synthesis. Chemistry. Soc. Pastor 34247 (2005).

    Google Scholar

  • Cheong, Ph-Y. , Legault, Cy, Um, JM, çelebi-Ölçüm, N. & Houk, kn Quantum mechanical investigation: mechanism, reactivity, and selectivity. Chemistry. Pastor 1115042–5137 (2011).

    Google Scholar

  • Klucznik, T. Etal. Efficient synthesis of a variety of drug-related targets planned and performed in the laboratory, computer-designed. Chemistry 4522–532 (2018).

    Google Scholar

  • Crawford, J.M., Kingston, C., Toste, F.D. & Sigman, MS Data Science meets physical organic chemistry. acc. Chemistry. res. 543136–3148 (2021).

    Google Scholar

  • Rinehart, Ni, Zahrt, AF, Henle, JJ & Denmark, Se Dreams, False Starts, Dead End, and Redemption: a record of the evolution of chemical workflows for enantioselective catalyst optimization. acc. Chemistry. res. 542041–2054 (2021).

    Google Scholar

  • Rinehart, Ni et al. Machine learning tool for predicting substrate adaptation conditions for PD catalyst C-N coupling. Science 381965–972 (2023).

    Google Scholar

  • Zahrt, Af et al. Prediction of highly selective catalysts through computer-driven workflows and machine learning. Science 363EAAU5631 (2019).

    Google Scholar

  • Reid, JP & Sigman, Overall Prediction of Enantioselectivity in MS Asymmetric Catalysts. Nature 571343–348 (2019).

    Google Scholar

  • Ahneman, DT, Estrada, JG, Lin, S., Dreher, SD & Doyle, AG predicts reaction performance in C–N cross-coupling using machine learning. Science 360186–190 (2018).

    Google Scholar

  • Sandfort, F., Strieth-Kalthoff, F., Kühnemund, M., Beecks, C. & Glorius, F. A structure-based platform for predicting chemical reactivity. Chemistry 61379–1390 (2020).

    Google Scholar

  • Schwaller, P., Vaucher, AC, Laino, T. & Reymond, J.-L. Chemical reaction predictions are generated using deep learning. Mach. learn. SCI. Technor. 2015016 (2021).

    Google Scholar

  • Li, B. Etal. A deep learning framework for accurate response prediction and its application on high-throughput experimental data. J. ChemInformatics 1572 (2023).

    Google Scholar

  • Coley, CW, Green, WH & Jensen, Machine Learning in KF Computer-Aided Synthesis Plans. acc. Chemistry. res. 511281–1289 (2018).

    Google Scholar

  • Segler, MHS, Preuss, M. & Waller, MP Planning Chemical Syntheses features deep neural networks and symbolic AI. Nature 555604–610 (2018).

    Google Scholar

  • Coley, CW, Barzilay, R., Jaakkola, TS, Green, WH & Jensen, Prediction of organic reaction outcomes using machine learning. ACS CENT. SCI. 3434–443 (2017).

    Google Scholar

  • Tu, Z. & Coley, Sequence model from invariant graphs of retrosynthesis and reaction prediction without CW ordering templates. J. Chem. Inf. Model. 623503–3513 (2022).

    Google Scholar

  • Schwaller, P. Etal. Molecular transformers: A model for uncertainty-kinetic-rate chemical reaction prediction. ACS CENT. SCI. 51572–1583 (2019).

    Google Scholar

  • Lin, K., Xu, Y., Pei, J. & Lai, L. Automatic retrosynthetic route planning using template-free models. Chemistry. SCI. 113355–3364 (2020).

    Google Scholar

  • Zheng, S., Rao, J., Zhang, Z., Xu, J. & Yang, Y. J. Chem. Inf. Model. 6047–55 (2020).

    Google Scholar

  • Kim, E. , Lee, D. , Kwon, Y. , Park, MS & Che, Y.-S. Effective, plausible, diverse retrosynthesis using bidirectional transformers with latent variables. J. Chem. Inf. Model. 61123–133 (2021).

    Google Scholar

  • Sacha, M. et al. Molecular Editing Graph Note Network: Models chemical reactions as sequences for graph editing. J. Chem. Inf. Model. 613273–3284 (2021).

    Google Scholar

  • Mao, K. et al. Molecular graphs enhanced transformers for retrosynthesis prediction. Neural calculations 457193–202 (2021).

    Google Scholar

  • Irwin, R., Dimitriadis, S., He, J. & Bjerrum, EJ Chemformer: Pre-trained transformers for computational chemistry. Mach. learn. SCI. Technor. 3015022 (2022).

    Google Scholar

  • Zhu, J. Etal. Dual view molecular training. in Proc. 29th ACM SIGKDD Knowledge Discovery and Data Mining Conference (eds Singh, Ak et al.) 3615–3627 (ACM, 2023).

  • Lu, J. & Zhang, Y. A unified deep learning model for multitasking response prediction with explanation. J. Chem. Inf. Model. 621376–1387 (2022).

    Google Scholar

  • Li, S.-W., Xu, L. C., Zhang, C., Zhang, S.-Q. & Hong, X. Reaction performance prediction with surrogate and interpretable graph models based on chemical knowledge. nut. commune. 143569 (2023).

    Google Scholar

  • Shi, R., Yu, G., Huo, X. & Yang, Y. Prediction of chemical reactions through large-scale multiview pretraining. J. ChemInformatics 1622 (2024).

    Google Scholar

  • Xia, J. Etal. Mole-Bert: A rethink of graph neural networks before molecular training. in Proc. 11th International Conference on Learning Expressions (eds Yan, L. et al.) https://openreview.net/pdf?id=jevy-dtiztr (ICLR 2023).

  • Ying, C. Etal. Does Trans really work badly for graphical representations? in 35th Conference on Neuroin Information Processing Systems (New Rip 2021) https://openreview.net/pdf?id=oewoooxfwda (Neurips, 2021).

  • Shi, Y. Etal. Benchmark graph mothers for large molecular modeling data sets. Preprinted at https://arxiv.org/abs/2203.04810 (2023).

  • Vaswani, A. Etal. Care is required. in Conference 31 on Neural Information Processing Systems (NIPS 2017) https://papers.nips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-paper.pdf (2017).

  • Perera, D. Etal. Platform for automated nanomole-scale reaction screening and micromole-scale synthesis in flows. Science 359429–434 (2018).

    Google Scholar

  • Li, X., Zhang, S., Xu, L. & Hong, X. Angew. Chemistry. int. Edited 5913253–13259 (2020).

    Google Scholar

  • Schneider, N., Stiefl, N. & Landrum, Ga What's What: The (almost) Response role assignment guide. J. Chem. Inf. Model. 562336–2346 (2016).

    Google Scholar

  • Dai, H., Li, C., Coley, C., Dai, Song, L. Retrosynthesis prediction using conditional graph logic networks. in 33rd Conference on Neuroin Information Processing Systems (Neurips 2019) https://proceedings.neurips.cc/paper_files/paper/2019/file/0d2b2061826a5df322116a5085a6052-paper.pdf (Neurips, 2019).

  • Schwaller, P., Gaudin, T., Lányi, D., Bekas, C. & Laino, T. Chemistry. SCI. 96091–6098 (2018).

    Google Scholar

  • Jin, W., Coley, C., Barzilay, R. & Jaakkola, T. Prediction of organic reaction results by the Weisfeiler-Lehman network. in Conference 31 on Neural Information Processing Systems (NIPS 2017) https://papers.nips.cc/paper_files/paper/2017/file/ced556cd9f9c0c8315cfbe0744a3baf0-paper.pdf (2017).

  • Arjovsky, M., Bottou, L., Gulrajani, I. & Lopez-Paz, D. Minimizing unchanging risk. Prelint at https://arxiv.org/abs/1907.02893 (2020).

  • Schwaller, P. Etal. Maps the space of chemical reactions using attention-based neural networks. nut. Mach. Intel. 3144–152 (2021).

    Google Scholar

  • Schneider, N., Lowe, DM, Sayle, Ra & Landrum, GA, development of new fingerprints for chemical reactions and applications to large-scale reaction classification and similarity. J. Chem. Inf. Model. 5539–53 (2015).

    Google Scholar

  • Schleinitz, J. Etal. Machine learning yields are predicted from Nicolit, a small literature data set for nickel catalyst C-O coupling. J. Am. Chemistry. Soc. 14414722–14730 (2022).

    Google Scholar

  • Xu, L. Etal. Towards a data-driven design of asymmetric hydrogenation of olefins: databases and hierarchical learning. Angew. Chemistry. int. Edited 6022804–22811 (2021).

    Google Scholar

  • Xu, L.-C. et al. Enantioselectivity prediction of paradada electrocatalyst C-H activation using knowledge of transition states in machine learning. nut. Synth. 2321–330 (2023).

    Google Scholar

  • Xu, L. C., Tang, M.-J., An, J., Cao, F. &Qi, Y. Xenod https://doi.org/10.5281/zenodo.15770470 (2025).

  • Xu, L. C., Tang, M.-J., An, J., Cao, F. &Qi, Y. figshare https://doi.org/10.6084/m9.figshare.28356077 (2025).



  • Source link

    Leave a Reply

    Your email address will not be published. Required fields are marked *