CoChat

Empowering Molecule Discovery for Molecule-Caption Translation With Large Language Models: A ChatGPT Perspective

Open access
Li, Jiatong, Liu, Yunqing, Fan, Wenqi, Wei, Xiao-Yong, Liu, Hui, Tang, Jiliang, Li, Qing · 2024 · IEEE Transactions on Knowledge and Data Engineering
Cited by 83

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Abstract

Molecule discovery plays a crucial role in various scientific fields, advancing the design of tailored materials and drugs, which contributes to the development of society and human well-being. Specifically, molecule-caption translation is an important task for molecule discovery, aligning human understanding with molecular space. However, most of the existing methods heavily rely on domain experts, require excessive computational cost, or suffer from sub-optimal performance. On the other hand, Large Language Models (LLMs), like ChatGPT, have shown remarkable performance in various cross-modal tasks due to their powerful capabilities in natural language understanding, generalization, and in-context learning (ICL), which provides unprecedented opportunities to advance molecule discovery. Despite several previous works trying to apply LLMs in this task, the lack of domain-specific corpus and difficulties in training specialized LLMs still remain challenges. In this work, we propose a novel LLM-based framework (MolReGPT) for molecule-caption translation, where an In-Context Few-Shot Molecule Learning paradigm is introduced to empower molecule discovery with LLMs like ChatGPT to perform their in-context learning capability without domain-specific pre-training and fine-tuning. MolReGPT leverages the principle of molecular similarity to retrieve similar molecules and their text descriptions from a local database to enable LLMs to learn the task knowledge from context examples. We evaluate the effectiveness of MolReGPT on molecule-caption translation, including molecule understanding and text-based molecule generation. Experimental results show that compared to fine-tuned models, MolReGPT outperforms MolT5-base and is comparable to MolT5-large without additional training. To the best of our knowledge, MolReGPT is the first work to leverage LLMs via in-context learning in molecule-caption translation for advancing molecule discovery. Our work expands the scope of LLM applications, as well as providing a new paradigm for molecule discovery and design.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tkde.2024.3393356

Cites

15 of 15 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 26

  1. 10.1016/j.ijbiomac.2023.123257 · DOI
  2. 10.1021/acs.orglett.1c00609 · DOI
  3. 10.1002/ejoc.201901572 · doi:10.1002/ejoc.201901572
  4. 10.1080/15583724.2022.2106490 · DOI
  5. 10.1016/j.ailsci.2022.100031 · DOI
  6. 10.1186/s13321-019-0393-0 · DOI · Paper page
  7. 10.18653/v1/2021.emnlp-main.47 · DOI · Paper page
  8. Edwards, Translation between molecules and natural language, 375
  9. 10.1109/TAI.2023.3251977 · DOI
  10. 10.1021/acs.jcim.9b00732 · DOI
  11. 10.1016/j.ab.2019.03.017 · DOI
  12. 10.1021/acs.jcim.9b00943 · DOI · Paper page
  13. 10.1021/acs.jcim.0c00343 · DOI
  14. 10.1021/acs.jcim.1c00600 · DOI · Paper page
  15. 10.1038/s42256-021-00403-1 · DOI · Paper page
  16. 10.1038/s41467-022-28494-3 · DOI
  17. Radford, 2018, Improving language understanding by generative pre-training, OpenAI
  18. Radford, 2019, Language models are unsupervised multitask learners, OpenAI Blog, 1
  19. 10.1038/s41570-023-00502-0 · DOI
  20. 10.1038/s42256-023-00759-6 · DOI · Paper page
  21. 10.1186/s13321-016-0130-x · DOI · Paper page
  22. 10.1021/ci9803381 · DOI · Paper page
  23. 10.1561/1500000019 · DOI · Paper page
  24. 10.2307/1932409.JSTOR1932409 · doi:10.2307/1932409.jstor1932409
  25. 10.1186/s13321-022-00595-7 · DOI
  26. Vaswani, Attention is all you need

Cited by

See all 83

Metadata

Authors
Li, J., Liu, Y., Fan, W., Wei, X.-Y., Liu, H., Tang, J., & Li, Q.
Venue
IEEE Transactions on Knowledge and Data Engineering
Published
2024-11
Volume
36
Issue
11
Pages
6071-6083
ISSN
  • 1041-4347 (ISSN-L)
  • 1558-2191
  • 2326-3865
OpenAlex
W4396597709
Cited by
83
References
15
FWCI
15.88
Type
journal article
Language
en
Open access
green
Funders
  • National Natural Science Foundation of China (62102335)
  • General Research Funds
  • Hong Kong Research Grants Council (PolyU 15200021, 15207322, 15200023)
  • Hong Kong Polytechnic University (P0036200, P0042693, P0048625, P0048752)
  • Research Collaborative (P0041282)
  • SHTM Interdisciplinary Large (P0043302)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.