Towards equilibrium molecular conformation generation with GFlowNets
Sampling diverse, thermodynamically feasible molecular conformations plays a crucial role in predicting properties of a molecule. In this paper we propose to use GFlowNet for sampling conformations of small molecules from the Boltzmann distribution, as determined by the molecule's energy. The proposed approach can be used in combination with energy estimation methods of different fidelity and discovers a diverse set of low-energy conformations for highly flexible drug-like molecules. We demonstrate that GFlowNet can reproduce molecular potential energy surfaces by sampling proportionally to the Boltzmann distribution..
Medienart: |
Preprint |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
arXiv.org - (2023) vom: 20. Okt. Zur Gesamtaufnahme - year:2023 |
---|
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Volokhova, Alexandra [VerfasserIn] |
---|
Links: |
Volltext [kostenfrei] |
---|
Themen: |
000 |
---|
Förderinstitution / Projekttitel: |
|
---|
PPN (Katalog-ID): |
XAR041301463 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | XAR041301463 | ||
003 | DE-627 | ||
005 | 20231025080408.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231025s2023 xx |||||o 00| ||eng c | ||
035 | |a (DE-627)XAR041301463 | ||
035 | |a (arXiv)2310.14782 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Volokhova, Alexandra |e verfasserin |4 aut | |
245 | 1 | 0 | |a Towards equilibrium molecular conformation generation with GFlowNets |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a Sampling diverse, thermodynamically feasible molecular conformations plays a crucial role in predicting properties of a molecule. In this paper we propose to use GFlowNet for sampling conformations of small molecules from the Boltzmann distribution, as determined by the molecule's energy. The proposed approach can be used in combination with energy estimation methods of different fidelity and discovers a diverse set of low-energy conformations for highly flexible drug-like molecules. We demonstrate that GFlowNet can reproduce molecular potential energy surfaces by sampling proportionally to the Boltzmann distribution. | ||
650 | 4 | |a Computer Science - Machine Learning |7 (dpeaa)DE-84 | |
650 | 4 | |a Computer Science - Artificial Intelligence |7 (dpeaa)DE-84 | |
650 | 4 | |a 000 |7 (dpeaa)DE-84 | |
700 | 1 | |a Koziarski, Michał |4 aut | |
700 | 1 | |a Hernández-García, Alex |4 aut | |
700 | 1 | |a Liu, Cheng-Hao |4 aut | |
700 | 1 | |a Miret, Santiago |4 aut | |
700 | 1 | |a Lemos, Pablo |4 aut | |
700 | 1 | |a Thiede, Luca |4 aut | |
700 | 1 | |a Yan, Zichao |4 aut | |
700 | 1 | |a Aspuru-Guzik, Alán |4 aut | |
700 | 1 | |a Bengio, Yoshua |4 aut | |
773 | 0 | 8 | |i Enthalten in |t arXiv.org |g (2023) vom: 20. Okt. |
773 | 1 | 8 | |g year:2023 |g day:20 |g month:10 |
856 | 4 | 0 | |u https://arxiv.org/abs/2310.14782 |z kostenfrei |3 Volltext |
912 | |a GBV_XAR | ||
951 | |a AR | ||
952 | |j 2023 |b 20 |c 10 |