An evaluation of unconditional 3D molecular generation methods
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916716043304960 |
|---|---|
| author | Buttenschoen, Martin Ziv, Yael Morris, Garrett M. Deane, Charlotte M. |
| author_facet | Buttenschoen, Martin Ziv, Yael Morris, Garrett M. Deane, Charlotte M. |
| contents | Unconditional molecular generation is a stepping stone for conditional molecular generation, which is important in \emph{de novo} drug design. Recent unconditional 3D molecular generation methods report saturated benchmarks, suggesting it is time to re-evaluate our benchmarks and compare the latest models. We assess five recent high-performing 3D molecular generation methods (EQGAT-diff, FlowMol, GCDM, GeoLDM, and SemlaFlow), in terms of both standard benchmarks and chemical and physical validity. Overall, the best method, SemlaFlow, has a success rate of 87% in generating valid, unique, and novel molecules without post-processing and 92.4% with post-processing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_00518 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An evaluation of unconditional 3D molecular generation methods Buttenschoen, Martin Ziv, Yael Morris, Garrett M. Deane, Charlotte M. Chemical Physics Quantitative Methods Unconditional molecular generation is a stepping stone for conditional molecular generation, which is important in \emph{de novo} drug design. Recent unconditional 3D molecular generation methods report saturated benchmarks, suggesting it is time to re-evaluate our benchmarks and compare the latest models. We assess five recent high-performing 3D molecular generation methods (EQGAT-diff, FlowMol, GCDM, GeoLDM, and SemlaFlow), in terms of both standard benchmarks and chemical and physical validity. Overall, the best method, SemlaFlow, has a success rate of 87% in generating valid, unique, and novel molecules without post-processing and 92.4% with post-processing. |
| title | An evaluation of unconditional 3D molecular generation methods |
| topic | Chemical Physics Quantitative Methods |
| url | https://arxiv.org/abs/2505.00518 |