Spremljaj
Marwin Segler
Marwin Segler
Microsoft Research AI for Science
Preverjeni e-poštni naslov na microsoft.com
Naslov
Navedeno
Navedeno
Leto
Opportunities and obstacles for deep learning in biology and medicine
T Ching, DS Himmelstein, BK Beaulieu-Jones, AA Kalinin, BT Do, ...
Journal of the royal society interface 15 (141), 20170387, 2018
23052018
Planning chemical syntheses with deep neural networks and symbolic AI
MHS Segler, M Preuss, MP Waller
Nature 555 (7698), 604-610, 2018
18532018
Generating focused molecule libraries for drug discovery with recurrent neural networks
MHS Segler, T Kogej, C Tyrchan, MP Waller
ACS central science 4 (1), 120-131, 2018
16282018
GuacaMol: benchmarking models for de novo molecular design
N Brown, M Fiscato, MHS Segler, AC Vaucher
Journal of chemical information and modeling 59 (3), 1096-1108, 2019
8752019
Neural‐symbolic machine learning for retrosynthesis and reaction prediction
MHS Segler, MP Waller
Chemistry–A European Journal 23 (25), 5966-5971, 2017
6102017
Machine learning the ropes: principles, applications and directions in synthetic chemistry
F Strieth-Kalthoff, F Sandfort, MHS Segler, F Glorius
Chemical Society Reviews 49 (17), 6154-6168, 2020
2502020
Modelling Chemical Reasoning to Predict and Invent Reactions
MHS Segler, MP Waller
Chemistry - A European Journal 23 (25), 6118-6128, 2016
2202016
Molecular representation learning with language models and domain-relevant auxiliary tasks
B Fabian, T Edlich, H Gaspar, M Segler, J Meyers, M Fiscato, M Ahmed
arXiv preprint arXiv:2011.13230, 2020
1662020
Artificial intelligence in drug discovery
MA Sellwood, M Ahmed, MHS Segler, N Brown
Future medicinal chemistry 10 (17), 2025-2028, 2018
1662018
Artificial intelligence for natural product drug discovery
MW Mullowney, KR Duncan, SS Elsayed, N Garg, JJJ van der Hooft, ...
Nature Reviews Drug Discovery 22 (11), 895-916, 2023
1522023
A model to search for synthesizable molecules
J Bradshaw, B Paige, MJ Kusner, M Segler, JM Hernández-Lobato
Advances in Neural Information Processing Systems 32, 2019
1362019
Improving few-and zero-shot reaction template prediction using modern hopfield networks
P Seidl, P Renz, N Dyubankova, P Neves, J Verhoeven, JK Wegner, ...
Journal of chemical information and modeling 62 (9), 2111-2120, 2022
117*2022
Evaluation guidelines for machine learning tools in the chemical sciences
A Bender, N Schneider, M Segler, W Patrick Walters, O Engkvist, ...
Nature Reviews Chemistry 6 (6), 428-442, 2022
1082022
Exploring deep recurrent models with reinforcement learning for molecule design
D Neil, M Segler, L Guasch, M Ahmed, D Plumbley, M Sellwood, N Brown
1012018
Learning to extend molecular scaffolds with structural motifs
K Maziarz, H Jackson-Flux, P Cameron, F Sirockin, N Schneider, N Stiefl, ...
arXiv preprint arXiv:2103.03864, 2021
972021
Fs-mol: A few-shot learning dataset of molecules
M Stanley, JF Bronskill, K Maziarz, H Misztela, J Lanini, M Segler, ...
Thirty-fifth Conference on Neural Information Processing Systems Datasets …, 2021
922021
A generative model for electron paths
J Bradshaw, MJ Kusner, B Paige, MHS Segler, JM Hernández-Lobato
arXiv preprint arXiv:1805.10970, 2018
91*2018
Barking up the right tree: an approach to search over molecule synthesis dags
J Bradshaw, B Paige, MJ Kusner, M Segler, JM Hernández-Lobato
Advances in neural information processing systems 33, 6852-6866, 2020
722020
Defactor: Differentiable edge factorization-based probabilistic graph generation
R Assouel, M Ahmed, MH Segler, A Saffari, Y Bengio
arXiv preprint arXiv:1811.09766, 2018
712018
RetroGNN: fast estimation of synthesizability for virtual screening and de novo design by learning from slow retrosynthesis software
CH Liu, M Korablyov, S Jastrzebski, P Włodarczyk-Pruszynski, Y Bengio, ...
Journal of Chemical Information and Modeling 62 (10), 2293-2300, 2022
66*2022
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–20