Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Esther Heid"'
Publikováno v:
Machine Learning: Science and Technology, Vol 5, Iss 3, p 035079 (2024)
The efficient generation and filtering of candidate structures for new materials is becoming increasingly important as starting points for computational studies. In this work, we introduce an approach to Wasserstein generative adversarial networks fo
Externí odkaz:
https://doaj.org/article/e427dde8dae44496b970e6c380085046
Publikováno v:
The Journal of Chemical Physics. 158
A reliable uncertainty estimator is a key ingredient in the successful use of machine-learning force fields for predictive calculations. Important considerations are correlation with error, overhead during training and inference, and efficient workfl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e618196c35c7df1bbc4a05f3331506c5
https://doi.org/10.1063/5.0146905
https://doi.org/10.1063/5.0146905
Enzymatic reactions are an ecofriendly, selective and versatile addition, sometimes even alternative to organic reactions for the synthesis of chemical compounds such as pharmaceuticals or fine chemicals. To identify suitable reactions, computational
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f402dc2a6204a6aa197026d7a02ffa06
https://doi.org/10.26434/chemrxiv-2023-jzw9w
https://doi.org/10.26434/chemrxiv-2023-jzw9w
Characterizing uncertainty in machine learning models has recently gained interest in the context of machine learning reliability, robustness, safety, and active learning. Here, we separate the total uncertainty into contributions from noise in the d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::beb33b4c4b983f395d90c0287956529d
https://doi.org/10.26434/chemrxiv-2023-00vcg-v2
https://doi.org/10.26434/chemrxiv-2023-00vcg-v2
Publikováno v:
Journal of Chemical Information and Modeling
Heuristic and machine learning models for rank-ordering reaction templates comprise an important basis for computer-aided organic synthesis regarding both product prediction and retrosynthetic pathway planning. Their viability relies heavily on the q
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::794bb66345f0f8a4f9ad68f81b855c99
http://europepmc.org/articles/PMC8757433
http://europepmc.org/articles/PMC8757433
The molecular structures synthesizable by organic chemists dictate the molecular functions they can create. The invention and development of chemical reactions are thus critical for chemists to access new and desirable functional molecules in all dis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::41d43533db044a7086a6b0f8159ecbcb
https://doi.org/10.26434/chemrxiv-2022-bjg1p
https://doi.org/10.26434/chemrxiv-2022-bjg1p
Autor:
Karthik Sankaranarayanan, Esther Heid, Connor W. Coley, Deeptak Verma, William H. Green, Klavs F. Jensen
Publikováno v:
Chemical science. 13(20)
Enzymes synthesize complex natural products effortlessly by catalyzing chemo-, regio-, and enantio-selective transformations. Further, biocatalytic processes are increasingly replacing conventional organic synthesis steps because they use mild solven
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f43755d689dd013bf8368dcedd9404c
https://pubmed.ncbi.nlm.nih.gov/35685792
https://pubmed.ncbi.nlm.nih.gov/35685792
Autor:
Ralf Ludwig, Philipp Honegger, Viviane Overbeck, Christian Schröder, Othmar Steinhauser, Esther Heid, Anne Strate, Marion Sappl, Andreas Appelhagen
Publikováno v:
The Journal of Physical Chemistry Letters. 11:2165-2170
Fast-field-cycling relaxometry is a nuclear magnetic resonance method growing in popularity; yet, theoretical interpretation is limited to analytical models of uncertain accuracy. We present the first study calculating fast-field-cycling dipolar coup
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bfba8f4c362f2a8ce9c07a08b509df0c
https://doi.org/10.1021/acs.jpclett.0c00087
https://doi.org/10.1021/acs.jpclett.0c00087
Multiparameter optimization, the heart of drug design, is still an open challenge. Thus, improved methods for automated compound design with multiple controlled properties are desired. Here, we present a significant extension to our previously descri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::017b1f1f510071f20c9c6bafeefc35c2
https://doi.org/10.33774/chemrxiv-2021-sqvv9-v2
https://doi.org/10.33774/chemrxiv-2021-sqvv9-v2
Autor:
William H. Green, Esther Heid
Publikováno v:
Journal of chemical information and modeling. 62(9)
The estimation of chemical reaction properties such as activation energies, rates or yields is a central topic of computational chemistry. In contrast to molecular properties, where machine learning approaches such as graph convolutional neural netwo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::508f0f7129e0fd68a83dec3de03e1275
https://pubmed.ncbi.nlm.nih.gov/34734699
https://pubmed.ncbi.nlm.nih.gov/34734699