A unified pre-trained deep learning framework for cross-task reaction performance prediction and synthesis planning

żrański, AM, Martinez alvarado, Ji, Shields, BJ & Doyle, AG expect revenue revenue through the learning subject to supervision. ACC. Chemical. Accuracy. 541856-1865 (2021).

The scientific researcher from Google

Zahrt, AF, ATHAVALE, SV & Denmark, SE quantitative structure and order in selective incentive: past, present and future. Chemical. pastor 1201620-1689 (2020).

The scientific researcher from Google

Corey, EJ, Long, AK & Rubenstein, SD analysis with the help of the computer in organic synthesis. sciences 228408-418 (1985).

The scientific researcher from Google

Todd, MH Concrete membership with the help of the computer. Chemical. Suk. pastor 34247 (2005).

The scientific researcher from Google

Cheong, PH-Y. , Legaut, CY, UM, JM, çelebi-Oulçüm, N. & Houk, Kn Quantum Mechanical Investigations of Morticocatalysion: Mechanisms, Interactions, and Specifications. Chemical. pastor 1115042-5137 (2011).

The scientific researcher from Google

Klucznik, T. et al. Effective combinations of various goals related to the planned doctor by the computer and implementing them in the laboratory. Chemical 4522-532 (2018).

The scientific researcher from Google

Crawford, JM, Kingston, C., Toste, FD & Sigman, MS Data Science meet physical organic chemistry. ACC. Chemical. Accuracy. 543136-3148 (2021).

The scientific researcher from Google

RineHart, Ni, Zahrt, AF, Henle, JJ & Denmark, SE DREAMS, false beginnings, closed ends, and redemption: a date for the development of chemical workflow to improve selective stimuli. ACC. Chemical. Accuracy. 542041-2054 (2021).

The scientific researcher from Google

Renhardt, Ni and others. Automated learning tool to predict the conditions that adapt the substrate to the CN connections stimulated by PD. sciences 381965-972 (2023).

The scientific researcher from Google

Zahrt, AF et al. Predicting the higher stimuli in the workflow that depends on computer and machine learning. sciences 363Eau5631 (2019).

The scientific researcher from Google

Reid, JP & Sigman, MS Comprehensive Fading from EnanTIOSELECTIVITIVITIVITION in the asymmetric stimulus. nature 571343-348 (2019).

The scientific researcher from Google

Ahneman, DT, Estrada, JG, LIN, S., Dreher, SD & Doyle, AG predicts the performance of the reaction in the cross -off using machine learning. sciences 360186-190 (2018).

The scientific researcher from Google

SANDFORT, F., Strieth-Klethoff, F., Kühnemund, M., Beecks, C. & Glorius, F. Plastic Template to predict chemical reaction. Chemical 61379-1390 (2020).

The scientific researcher from Google

Schwaller, P., Vaucher, AC, Laino, T. & Reymond, J.-L. Chemical reaction predictions using deep learning. Mach. Learn. Sci. technique. 2015016 (2021).

The scientific researcher from Google

To me, b. And others. A deep educational work frame for the accurate prediction of interaction and its application to highly productive experience. J. Chemical Information 1572 (2023).

The scientific researcher from Google

Coley, CW, Green, Who & Jensen, KF Machine Learning in Complement Synthesis playsisis. ACC. Chemical. Accuracy. 511281-1289 (2018).

The scientific researcher from Google

Segler, MHS, Press, M. & Waller, MP MP Chemical Planning with Deep Nervous Networks and Avoid AI. nature 555604-610 (2018).

The scientific researcher from Google

Coley, CW, Barzilay, R., Jaakkola, TS, Green, Who & Jensen, KF organic reaction predictions using machine learning. ACS Center. Sci. 3434-443 (2017).

The scientific researcher from Google

Tu, Z. & Coley, the sneaking chart form to the CW sequence for the affected by the prediction of molds and the prediction of the response. J. Chem. Inf. model. 623503-3513 (2022).

The scientific researcher from Google

Schwaller, P. et al. Molecular transformer: a model for predicting normative chemical reaction. ACS Center. Sci. 51572-1583 (2019).

The scientific researcher from Google

Lynn, k. Chemical. Sci. 113355-3364 (2020).

The scientific researcher from Google

Zheng, S., RAO, J., Zhang, Z., Xu, J J. Chem. Inf. model. 6047-55 (2020).

The scientific researcher from Google

Kim, E., Lee, D., KWON, Y., Park, MS & Choi, Y.-S. Health, reasonable, and the diversity of cracker Retrospiesis using dual -directional transformers associated with the underlying variables. J. Chem. Inf. model. 61123-133 (2021).

The scientific researcher from Google

Sasha, M. And others. The editing of the Point Point Network: Chemical Reactions Modeling as Series of the Liberation of the Graphic. J. Chem. Inf. model. 613273-3284 (2021).

The scientific researcher from Google

Mao, K. And others. The molecular graph is converter to predict the creation columns. Nervous computing 457193-202 (2021).

The scientific researcher from Google

Irwin, R., Dimitriadis, S., He, J Mach. Learn. Sci. technique. 3015022 (2022).

The scientific researcher from Google

Zhu, J. et al. Double molecular display before training. in Brook. ACM Sigkdd 29 Conference to discover knowledge and extract data (Eds Singh, AK Et Al.) 3615-3627 (ACM, 2023).

Lu, J J. Chem. Inf. model. 621376-1387 (2022).

The scientific researcher from Google

LI, S.-w. , XU, L.-C. , Zhang, C., Zhang, S.-Q. & Hong, X. Prediction to perform interaction with an investment and interpretation graphic form based on chemical knowledge. Nat. communication. 143569 (2023).

The scientific researcher from Google

SHI, R., Yu, G., HUO, X. & Yang, Y. Chemical Interaction Fores with multiple wide training. J. Chemical Information 1622 (2024).

The scientific researcher from Google

Xia, c. And others. Mall-Bert: Reflection on the graph before training the nerve networks of the particles. in Brook. The eleventh international conference on learning representations (Eds Yan, L. Et al

Ying, C and others. Is the transformer really badly to represent the graph? in The thirty -fifth conference for neurological information processing systems (Neurips 2021) https://openreview.net/pdf?

Shi, j. And others. Graphormer measurement on wide molecular modeling collections. Preprint at https://arxiv.org/abs/2203.04810 (2023).

Vaswani, a. And others. Attention is all you need. in The thirty -first conference for neurological information processing systems (NIPS 2017) https://papers.nips.cc/paper_files/Paper/2017/file/3f5ee243547deee 91fbd053c1c4a845aa-paper.pdf (2017).

Pearlra, D. et al. A platform to examine automatic reaction and the synthesis of the micromol in the flow. sciences 359429-434 (2018).

The scientific researcher from Google

LI, X., Zhang, S., XU, L. & Hong, X. Prediction to re -detect the Root -H – H of heterogeneous bikes through machine learning. Ango. Chemical. int. Mr. Dr. 5913253-13259 (2020).

The scientific researcher from Google

Schneider, n. Stepl, n. J. Chem. Inf. model. 562336-2346 (2016).

The scientific researcher from Google

Dai, H., LI, C., Coley, C., Dai, B. & Song, L. Retrosynthesis predicting with a police graph logic network. in The thirty -third conference for neurological information processing systems (Neurips 2019) https://proceds.neurips.cc/Paper_files/paper/2019/file/0D2B2061826A5df3221116A5085a6052-paper.pdf (neups, 2019).

Schwaller, P., Gaudin, T., Lányi, D. Chemical. Sci. 96091-6098 (2018).

The scientific researcher from Google

Jin, and. in The thirty -first conference for neurological information processing systems (NIPS 2017) https://papers.nips.cc/paper_files/paper/2017/file/ced556cd9f9c0c8315cfbe0744A3BAF0-paper.pdf (2017).

Arjovsky, M., Bottou, L., Gullrajani, I. & Lopez-paz, D. Preprint in https://arxiv.org/abs/1907.02893 (2020).

Schwaller, P. et al. Set the space of chemical reactions using attention -based nerve networks. Nat. Mach. Minds. 3144-152 (2021).

The scientific researcher from Google

Schneider, n. J. Chem. Inf. model. 5539-53 (2015).

The scientific researcher from Google

Schleinitz, J. et al. Nicolit learning predictions of Nicolit, a group of small literature data from Co stimulating nickel. J. AM. Chemical. Suk. 14414722-14730 (2022).

The scientific researcher from Google

Xu, L. et al. Towards the design of data from the asymmetric hydrogenity of the OLC: database and hierarchical learning. Ango. Chemical. int. Mr. Dr. 6022804-22811 (2021).

The scientific researcher from Google

Xu, L.-C. And others. Enantioselectivity by activating Christhh using the knowledge of the state of transition in machine learning. Nat. Informed. 2321-330 (2023).

The scientific researcher from Google

Xu, L.-C. , Tang, M.-J. , A, j. Zenudo https://doi.org/10.5281/zenodo.15770470 (2025).

Xu, L.-C. , Tang, M.-J. , A, j. Figshare https://doi.org/10.6084/m9.figshare.28356077 (2025).