Geometry Informed Tokenization of Molecules for Language Model Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909290815553536 |
|---|---|
| author | Li, Xiner Wang, Limei Luo, Youzhi Edwards, Carl Gui, Shurui Lin, Yuchao Ji, Heng Ji, Shuiwang |
| author_facet | Li, Xiner Wang, Limei Luo, Youzhi Edwards, Carl Gui, Shurui Lin, Yuchao Ji, Heng Ji, Shuiwang |
| contents | We consider molecule generation in 3D space using language models (LMs), which requires discrete tokenization of 3D molecular geometries. Although tokenization of molecular graphs exists, that for 3D geometries is largely unexplored. Here, we attempt to bridge this gap by proposing the Geo2Seq, which converts molecular geometries into $SE(3)$-invariant 1D discrete sequences. Geo2Seq consists of canonical labeling and invariant spherical representation steps, which together maintain geometric and atomic fidelity in a format conducive to LMs. Our experiments show that, when coupled with Geo2Seq, various LMs excel in molecular geometry generation, especially in controlled generation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10120 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Geometry Informed Tokenization of Molecules for Language Model Generation Li, Xiner Wang, Limei Luo, Youzhi Edwards, Carl Gui, Shurui Lin, Yuchao Ji, Heng Ji, Shuiwang Artificial Intelligence We consider molecule generation in 3D space using language models (LMs), which requires discrete tokenization of 3D molecular geometries. Although tokenization of molecular graphs exists, that for 3D geometries is largely unexplored. Here, we attempt to bridge this gap by proposing the Geo2Seq, which converts molecular geometries into $SE(3)$-invariant 1D discrete sequences. Geo2Seq consists of canonical labeling and invariant spherical representation steps, which together maintain geometric and atomic fidelity in a format conducive to LMs. Our experiments show that, when coupled with Geo2Seq, various LMs excel in molecular geometry generation, especially in controlled generation tasks. |
| title | Geometry Informed Tokenization of Molecules for Language Model Generation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2408.10120 |