---
title: "LlaSMol — paper by Yu et al. (2024) — summary and ideas"
description: "They build SMolInstruct, an instruction-tuning resource focused on small molecules. 73 references, cited by 37 papers here."
authors: ["Botao Yu", "Frazier N. Baker", "Ziqi Chen", "Xia Ning", "Huan Sun"]
year: 2024
venue: "arXiv:2402.09391"
source: "https://arxiv.org/abs/2402.09391"
doi: "10.48550/arxiv.2402.09391"
arxiv: "2402.09391"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yu-2024-llasmol-advancing-large-language-models/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yu-2024-llasmol-advancing-large-language-models/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/8/) / LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset

# LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset

**Authors:** [Botao Yu](https://md.research.elamur.ai/free/en/authors/botao-yu/), Frazier N. Baker, Ziqi Chen, Xia Ning and [Huan Sun](https://md.research.elamur.ai/free/en/authors/huan-sun/) · **Year:** 2024 · **Venue:** arXiv:2402.09391 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2402.09391) · [PDF](https://arxiv.org/pdf/2402.09391) · [DOI 10.48550/arxiv.2402.09391](https://doi.org/10.48550/arxiv.2402.09391) · [arXiv 2402.09391](https://arxiv.org/abs/2402.09391) · [OpenAlex](https://openalex.org/W4391871462)

**Citations:** 14 citations (OpenAlex, 2026-10-14) · [37](https://md.research.elamur.ai/free/en/papers/yu-2024-llasmol-advancing-large-language-models/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
General-purpose LLMs such as GPT-4 have performed poorly on chemistry, especially on tasks that require precise handling of SMILES strings. Earlier chemistry instruction data, notably Mol-Instructions, brought only small improvements. The authors argue that the main bottleneck is data, not model capacity.

They build SMolInstruct, an instruction-tuning resource focused on small molecules. It covers 14 tasks:
- conversions between IUPAC names, SMILES and molecular formulas,
- six property-prediction benchmarks,
- molecule captioning and generation,
- forward synthesis and retrosynthesis.

The tasks total more than three million curated examples. Four open models (Galactica, Llama 2, Code Llama, Mistral) are fine-tuned on it with LoRA, producing the LlaSMol family.

The Mistral-based variant performs best and clearly beats GPT-4 and Claude 3 Opus across the benchmark. It still trails dedicated single-task systems but comes close while updating only a small fraction of its weights. Ablations attribute most of the gains to the new dataset and give practical guidance on molecular representations. Together, the dataset and models serve as a reusable baseline for chemistry LLMs.

## Key points
- **SMolInstruct composition:** 14 tasks and over 3M samples.
  - Name conversion: NC-I2F, NC-I2S, NC-S2F, NC-S2I.
  - Property prediction: PP-ESOL, PP-Lipo, PP-BBBP, PP-ClinTox, PP-HIV, PP-SIDER.
  - Molecule description and generation: MC, MG.
  - Reactions: FS, RS.
- **LlaSMol training and results:** LoRA fine-tuning touches about 0.58% of parameters.
  - Mistral is the strongest base model.
  - LlaSMol outperforms GPT-4 and Claude 3 Opus but does not yet surpass task-specific SoTA models.
- **Molecular representation:**
  - Canonical SMILES helps, especially on reactions. Exact match on FS is 63.3% with canonicalization vs 53.7% without; on RS it is 32.9% vs 23.8%.
  - SELFIES gives slightly higher validity but worse accuracy overall, contradicting earlier claims in favour of SELFIES.
- **Dataset comparison:** With the same Mistral setup, training on Mol-Instructions instead of SMolInstruct sharply lowers performance.
  - FS exact match: 3.9% vs 63.3%.
  - RS exact match: 7.4% vs 32.9%.
  - MC METEOR: 0.195 vs 0.452.
- **Further findings and limitations:**
  - Multi-task training beats single-task training.
  - Adding more LoRA modules improves results.
  - Limitations: MC/MG evaluation is imprecise, and generalization beyond the trained tasks is not tested.
  - Data and models are available at osu-nlp-group.github.io/LLM4Chem.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [The Ohio State University](https://md.research.elamur.ai/free/en/universities/the-ohio-state-university/) — University, Columbus, United States · 96 works · 19,285 citations

📚 Shelves (7): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works · [🧮 Computational Theory and Mathematics](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · 496 works · [🧱 Materials Science](https://md.research.elamur.ai/free/en/shelves/materials-science/) · 58 works · [🧱 Materials Chemistry](https://md.research.elamur.ai/free/en/shelves/materials-science/materials-chemistry/) · 58 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 4,145 works

## Cite

Cite as: Botao Yu, Frazier N. Baker, Ziqi Chen, Xia Ning and Huan Sun. 2024. LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset. arXiv:2402.09391.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{yu2024llasmol,
  title = {{LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset}},
  author = {Botao Yu, Frazier N. Baker, Ziqi Chen, Xia Ning and Huan Sun},
  year = {2024},
  doi = {10.48550/arxiv.2402.09391},
  eprint = {2402.09391},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2402.09391}
}
```

- [← previous Lean-STaR: Learning to Interleave Thinking and Proving](https://md.research.elamur.ai/free/en/papers/lin-2024-lean-star-learning-interleave-thinking/)
- [next → MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://md.research.elamur.ai/free/en/papers/cao-2024-moe-lightning-high-throughput-moe/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/8/)

## References

73 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mikhail Andronov, Varvara Voinarovska, Natalia Andronova, Michael Wand, Djork-Arné Clevert, and Jürgen Schmidhuber. Reagent prediction with a molecular transformer improves reaction data quality. Chemical Science, 14(12):3235–3246, 2023. [find](https://scholar.google.com/scholar?q=Mikhail+Andronov%2C+Varvara+Voinarovska%2C+Natalia+Andronova%2C+Michael+Wand%2C+Djork%2DArne%CC%81+Clevert%2C+and+Ju%CC%88rgen+Schmidhuber%2E+Reagent+prediction+with+a+molecular+transformer+improves+reaction+data+quality%2E+Ch)
2. Anthropic. The claude 3 model family: Opus, sonnet, haiku. Anthropic, 2024. [find](https://scholar.google.com/scholar?q=Anthropic%2E+The+claude+3+model+family%3A+Opus%2C+sonnet%2C+haiku%2E+Anthropic%2C+2024%2E)
3. Theodore L. Brown. Chemistry: the central science. Pearson, 14th edition edition, 2018. [find](https://scholar.google.com/scholar?q=Theodore+L%2E+Brown%2E+Chemistry%3A+the+central+science%2E+Pearson%2C+14th+edition+edition%2C+2018%2E)
4. Andrew R. Burns, Trevor C. Y. Kwok, Al Howard, Ed Houston, Karl Johanson, Anthony Chan, Sean R. Cutler, Peter McCourt, and Peter J. Roy. High-throughput screening of small molecules for bioactivity and target identification in Caenorhabditis elegans. Nature Protocols, 1:1906–1914, 2006. [find](https://scholar.google.com/scholar?q=Andrew+R%2E+Burns%2C+Trevor+C%2E+Y%2E+Kwok%2C+Al+Howard%2C+Ed+Houston%2C+Karl+Johanson%2C+Anthony+Chan%2C+Sean+R%2E+Cutler%2C+Peter+McCourt%2C+and+Peter+J%2E+Roy%2E+High%2Dthroughput+screening+of+small+molecules+for+bioactivity+an)
5. He Cao, Zijing Liu, Xingyu Lu, Yuan Yao, and Yu Li. [Instructmol: Multi-modal integration for building a versatile and reliable molecular assistant in drug discovery](https://md.research.elamur.ai/free/en/papers/cao-2025-instructmol-multi-modal-integration-building/). arXiv preprint arXiv:2311.16208, 2023.
6. Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Linyi Yang, Kaijie Zhu, Hao Chen, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, Wei Ye, Yue Zhang, Yi Chang, Philip S. Yu, Qiang Yang, and Xing Xie. [A survey on evaluation of large language models](https://md.research.elamur.ai/free/en/papers/chang-2023-survey-evaluation-large-language-models/). ACM Transactions on Intelligent Systems and Technology, 2024.
7. Heng-Yi Chen, Michael Hsu, and Chan-Wang Jerry Lio. Micro but mighty - Micronutrients in the epigenetic regulation of adaptive immune responses. Immunological reviews, 305: 152–164, 2022. [find](https://scholar.google.com/scholar?q=Heng%2DYi+Chen%2C+Michael+Hsu%2C+and+Chan%2DWang+Jerry+Lio%2E+Micro+but+mighty+%2D+Micronutrients+in+the+epigenetic+regulation+of+adaptive+immune+responses%2E+Immunological+reviews%2C+305%3A+152%E2%80%93164%2C+2022%2E)
8. Ziqi Chen, Martin Renqiang Min, Srinivasan Parthasarathy, and Xia Ning. A deep generative model for molecule optimization via one fragment modification. Nature machine intelligence, 3(12):1040–1049, 2021. [find](https://scholar.google.com/scholar?q=Ziqi+Chen%2C+Martin+Renqiang+Min%2C+Srinivasan+Parthasarathy%2C+and+Xia+Ning%2E+A+deep+generative+model+for+molecule+optimization+via+one+fragment+modification%2E+Nature+machine+intelligence%2C+3%2812%29%3A1040%E2%80%931049%2C+2)
9. Ziqi Chen, Oluwatosin R Ayinde, James R Fuchs, Huan Sun, and Xia Ning. G2retro as a two-step graph generative models for retrosynthesis prediction. Communications Chemistry, 6 (1):102, 2023. [find](https://scholar.google.com/scholar?q=Ziqi+Chen%2C+Oluwatosin+R+Ayinde%2C+James+R+Fuchs%2C+Huan+Sun%2C+and+Xia+Ning%2E+G2retro+as+a+two%2Dstep+graph+generative+models+for+retrosynthesis+prediction%2E+Communications+Chemistry%2C+6+%281%29%3A102%2C+2023%2E)
10. Connor W. Coley, William H. Green, and Klavs F. Jensen. Machine learning in computer-aided synthesis planning. Accounts of Chemical Research, 51(5):1281–1289, 2018. [find](https://scholar.google.com/scholar?q=Connor+W%2E+Coley%2C+William+H%2E+Green%2C+and+Klavs+F%2E+Jensen%2E+Machine+learning+in+computer%2Daided+synthesis+planning%2E+Accounts+of+Chemical+Research%2C+51%285%29%3A1281%E2%80%931289%2C+2018%2E)
11. Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, and Yu Su. [Mind2web: Towards a generalist agent for the web](https://md.research.elamur.ai/free/en/papers/deng-2023-mind2web-towards-generalist-agent-web/). In Proceedings of Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2023.
12. Joseph L Durant, Burton A Leland, Douglas R Henry, and James G Nourse. Reoptimization of mdl keys for use in drug discovery. Journal of chemical information and computer sciences, 42(6):1273–1280, 2002. [find](https://scholar.google.com/scholar?q=Joseph+L+Durant%2C+Burton+A+Leland%2C+Douglas+R+Henry%2C+and+James+G+Nourse%2E+Reoptimization+of+mdl+keys+for+use+in+drug+discovery%2E+Journal+of+chemical+information+and+computer+sciences%2C+42%286%29%3A1273%E2%80%931280%2C+200)
13. Carl Edwards, ChengXiang Zhai, and Heng Ji. [Text2mol: Cross-modal molecule retrieval with natural language queries](https://md.research.elamur.ai/free/en/papers/edwards-2021-text2mol-cross-modal-molecule-retrieval/). In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 595–607, 2021.
14. Carl Edwards, Tuan Lai, Kevin Ros, Garrett Honke, Kyunghyun Cho, and Heng Ji. [Translation between molecules and natural language](https://md.research.elamur.ai/free/en/papers/edwards-2022-translation-between-molecules-natural-language/). In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 375–413, 2022.
15. Yin Fang, Xiaozhuan Liang, Ningyu Zhang, Kangwei Liu, Rui Huang, Zhuo Chen, Xiaohui Fan, and Huajun Chen. [Mol-instructions: A large-scale biomolecular instruction dataset for large language models](https://md.research.elamur.ai/free/en/papers/fang-2023-mol-instructions-large-scale-biomolecular/). arXiv preprint arXiv:2306.08018, 2023.
16. Henri A. Favre and Warren H. Powell. Nomenclature of organic chemistry: IUPAC recommendations and preferred names 2013. Royal Society of Chemistry, 2014. [find](https://scholar.google.com/scholar?q=Henri+A%2E+Favre+and+Warren+H%2E+Powell%2E+Nomenclature+of+organic+chemistry%3A+IUPAC+recommendations+and+preferred+names+2013%2E+Royal+Society+of+Chemistry%2C+2014%2E)
17. Kaitlyn M. Gayvert, Neel S. Madhukar, and Olivier Elemento. A data-driven approach to predicting successes and failures of clinical trials. Cell Chemical Biology, 23(10):1294–1301, 2016. [find](https://scholar.google.com/scholar?q=Kaitlyn+M%2E+Gayvert%2C+Neel+S%2E+Madhukar%2C+and+Olivier+Elemento%2E+A+data%2Ddriven+approach+to+predicting+successes+and+failures+of+clinical+trials%2E+Cell+Chemical+Biology%2C+23%2810%29%3A1294%E2%80%931301%2C+2016%2E)
18. Taicheng Guo, Kehan Guo, Bozhao Nan, Zhenwen Liang, Zhichun Guo, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. What can large language models do in chemistry? a comprehensive benchmark on eight tasks. In Proceedings of Conference on Neural Information Processing Systems (NeurIPS) Datasets and B… [find](https://scholar.google.com/scholar?q=Taicheng+Guo%2C+Kehan+Guo%2C+Bozhao+Nan%2C+Zhenwen+Liang%2C+Zhichun+Guo%2C+Nitesh+V+Chawla%2C+Olaf+Wiest%2C+and+Xiangliang+Zhang%2E+What+can+large+language+models+do+in+chemistry%3F+a+comprehensive+benchmark+on+eight+t)
19. Shen Han, Haitao Fu, Yuyang Wu, Ganglan Zhao, Zhenyu Song, Feng Huang, Zhongfei Zhang, Shichao Liu, and Wen Zhang. Himgnn: a novel hierarchical molecular graph representation learning framework for property prediction. Briefings in Bioinformatics, 24 (5):bbad305, 2023. [find](https://scholar.google.com/scholar?q=Shen+Han%2C+Haitao+Fu%2C+Yuyang+Wu%2C+Ganglan+Zhao%2C+Zhenyu+Song%2C+Feng+Huang%2C+Zhongfei+Zhang%2C+Shichao+Liu%2C+and+Wen+Zhang%2E+Himgnn%3A+a+novel+hierarchical+molecular+graph+representation+learning+framework+for+pr)
20. Kan Hatakeyama-Sato, Naoki Yamane, Yasuhiko Igarashi, Yuta Nabae, and Teruaki Hayakawa. Prompt engineering of gpt-4 for chemical research: what can/cannot be done? Science and Technology of Advanced Materials: Methods, 3(1), 2023. [find](https://scholar.google.com/scholar?q=Kan+Hatakeyama%2DSato%2C+Naoki+Yamane%2C+Yasuhiko+Igarashi%2C+Yuta+Nabae%2C+and+Teruaki+Hayakawa%2E+Prompt+engineering+of+gpt%2D4+for+chemical+research%3A+what+can%2Fcannot+be+done%3F+Science+and+Technology+of+Advanced+M)
21. Jiazhen He, Huifang You, Emil Sandström, Eva Nittinger, Esben Jannik Bjerrum, Christian Tyrchan, Werngard Czechtizky, and Ola Engkvist. Molecular optimization by capturing chemist’s intuition using deep neural networks. Journal of cheminformatics, 13(1):1–17, 2021. [find](https://scholar.google.com/scholar?q=Jiazhen+He%2C+Huifang+You%2C+Emil+Sandstro%CC%88m%2C+Eva+Nittinger%2C+Esben+Jannik+Bjerrum%2C+Christian+Tyrchan%2C+Werngard+Czechtizky%2C+and+Ola+Engkvist%2E+Molecular+optimization+by+capturing+chemist%E2%80%99s+intuition+using+d)
22. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. [LoRA: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In International Conference on Learning Representations (ICLR), 2022.
23. National Cancer Institute. AIDS antiviral screen data, 2004. URL [https://wiki.nci.nih](https://wiki.nci.nih). gov/display/NCIDTPdata/AIDS+Antiviral+Screen+Data. Accessed on 1 Fec 2024. [↗](https://wiki.nci.nih)
24. Ross Irwin, Spyridon Dimitriadis, Jiazhen He, and Esben Jannik Bjerrum. Chemformer: a pre-trained transformer for computational chemistry. Machine Learning: Science and Technology, 3(1):015022, 2022. [find](https://scholar.google.com/scholar?q=Ross+Irwin%2C+Spyridon+Dimitriadis%2C+Jiazhen+He%2C+and+Esben+Jannik+Bjerrum%2E+Chemformer%3A+a+pre%2Dtrained+transformer+for+computational+chemistry%2E+Machine+Learning%3A+Science+and+Technology%2C+3%281%29%3A015022%2C+2022%2E)
25. Kevin Maik Jablonka, Philippe Schwaller, and Berend Smit. Is gpt-3 all you need for machine learning for chemistry? In AI for Accelerated Materials Design NeurIPS 2022 Workshop, 2022. [find](https://scholar.google.com/scholar?q=Kevin+Maik+Jablonka%2C+Philippe+Schwaller%2C+and+Berend+Smit%2E+Is+gpt%2D3+all+you+need+for+machine+learning+for+chemistry%3F+In+AI+for+Accelerated+Materials+Design+NeurIPS+2022+Workshop%2C+2022%2E)
26. Kevin Maik Jablonka, Philippe Schwaller, Andres Ortega-Guerrero, and Berend Smit. [Leveraging large language models for predictive chemistry](https://md.research.elamur.ai/free/en/papers/jablonka-2024-leveraging-large-language-models-predictive/). ChemRxiv, 2023. doi: 10.26434/chemrxiv-2023-fw8n4-v3.
27. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. Mistral 7b. arXiv preprint arXiv:2310.06825, 2023. [find](https://scholar.google.com/scholar?q=Albert+Q+Jiang%2C+Alexandre+Sablayrolles%2C+Arthur+Mensch%2C+Chris+Bamford%2C+Devendra+Singh+Chaplot%2C+Diego+de+las+Casas%2C+Florian+Bressand%2C+Gianna+Lengyel%2C+Guillaume+Lample%2C+Lucile+Saulnier%2C+et+al%2E+Mistral+7b)
28. Sunghwan Kim, Jie Chen, Tiejun Cheng, Asta Gindulyte, Jia He, Siqian He, Qingliang Li, Benjamin A Shoemaker, Paul A Thiessen, Bo Yu, et al. Pubchem 2019 update: improved access to chemical data. Nucleic acids research, 47:D1102–D1109, 2019. [find](https://scholar.google.com/scholar?q=Sunghwan+Kim%2C+Jie+Chen%2C+Tiejun+Cheng%2C+Asta+Gindulyte%2C+Jia+He%2C+Siqian+He%2C+Qingliang+Li%2C+Benjamin+A+Shoemaker%2C+Paul+A+Thiessen%2C+Bo+Yu%2C+et+al%2E+Pubchem+2019+update%3A+improved+access+to+chemical+data%2E+Nucle)
29. Thomas N. Kipf and Max Welling. [Semi-supervised classification with graph convolutional networks](https://md.research.elamur.ai/free/en/papers/kipf-2016-semi-supervised-classification-graph-convolutional/). In International Conference on Learning Representations (ICLR), 2017.
30. Mario Krenn, Florian Häse, A Nigam, Pascal Friederich, and Alán Aspuru-Guzik. Selfies: a robust representation of semantically constrained graphs with an example application in chemistry. arXiv preprint arXiv:1905.13741, 1(3), 2019. — [arXiv:1905.13741](https://arxiv.org/abs/1905.13741) [find](https://scholar.google.com/scholar?q=Mario+Krenn%2C+Florian+Ha%CC%88se%2C+A+Nigam%2C+Pascal+Friederich%2C+and+Ala%CC%81n+Aspuru%2DGuzik%2E+Selfies%3A+a+robust+representation+of+semantically+constrained+graphs+with+an+example+application+in+chemistry%2E+arXiv+prep)
31. Michael Kuhn, Ivica Letunic, Lars Juhl Jensen, and Peer Bork. The sider database of drugs and side effects. Nucleic Acids Research, 44:D1075–D1079, 2015. [find](https://scholar.google.com/scholar?q=Michael+Kuhn%2C+Ivica+Letunic%2C+Lars+Juhl+Jensen%2C+and+Peer+Bork%2E+The+sider+database+of+drugs+and+side+effects%2E+Nucleic+Acids+Research%2C+44%3AD1075%E2%80%93D1079%2C+2015%2E)
32. Alon Lavie and Abhaya Agarwal. [Meteor: an automatic metric for mt evaluation with high levels of correlation with human judgments](https://md.research.elamur.ai/free/en/papers/lavie-2007-meteor-automatic-metric-mt-evaluation/). In Proceedings of the Second Workshop on Statistical Machine Translation, StatMT ’07, pp. 228–231. Association for Computational Linguistics, 2007.
33. Elena Lenci and Andrea Trabocchi. Chapter 1 - Synthetic approaches toward small molecule libraries. In Small Molecule Drug Discovery, pp. 1–34. Elsevier, 2020. [find](https://scholar.google.com/scholar?q=Elena+Lenci+and+Andrea+Trabocchi%2E+Chapter+1+%2D+Synthetic+approaches+toward+small+molecule+libraries%2E+In+Small+Molecule+Drug+Discovery%2C+pp%2E+1%E2%80%9334%2E+Elsevier%2C+2020%2E)
34. Sihang Li, Zhiyuan Liu, Yanchen Luo, Xiang Wang, Xiangnan He, Kenji Kawaguchi, Tat-Seng Chua, and Qi Tian. Towards 3d molecule-text interpretation in language models. In Proceedings of International Conference on Learning Representations (ICLR), 2024. [find](https://scholar.google.com/scholar?q=Sihang+Li%2C+Zhiyuan+Liu%2C+Yanchen+Luo%2C+Xiang+Wang%2C+Xiangnan+He%2C+Kenji+Kawaguchi%2C+Tat%2DSeng+Chua%2C+and+Qi+Tian%2E+Towards+3d+molecule%2Dtext+interpretation+in+language+models%2E+In+Proceedings+of+International+C)
35. Youwei Liang, Ruiyi Zhang, Li Zhang, and Pengtao Xie. Drugchat: towards enabling chatgpt-like capabilities on drug molecule graphs. arXiv preprint arXiv:2309.03907, 2023. — [arXiv:2309.03907](https://arxiv.org/abs/2309.03907) [find](https://scholar.google.com/scholar?q=Youwei+Liang%2C+Ruiyi+Zhang%2C+Li+Zhang%2C+and+Pengtao+Xie%2E+Drugchat%3A+towards+enabling+chatgpt%2Dlike+capabilities+on+drug+molecule+graphs%2E+arXiv+preprint+arXiv%3A2309%2E03907%2C+2023%2E+%E2%80%94+%5BarXiv%3A2309%2E03907%5D%28https%3A%2F%2F)
36. Shengchao Liu, Jiongxiao Wang, Yijin Yang, Chengpeng Wang, Ling Liu, Hongyu Guo, and Chaowei Xiao. Chatgpt-powered conversational drug editing using retrieval and domain feedback. arXiv preprint arXiv:2305.18090, 2023a. — [arXiv:2305.18090](https://arxiv.org/abs/2305.18090) [find](https://scholar.google.com/scholar?q=Shengchao+Liu%2C+Jiongxiao+Wang%2C+Yijin+Yang%2C+Chengpeng+Wang%2C+Ling+Liu%2C+Hongyu+Guo%2C+and+Chaowei+Xiao%2E+Chatgpt%2Dpowered+conversational+drug+editing+using+retrieval+and+domain+feedback%2E+arXiv+preprint+arXiv)
37. Zhiyuan Liu, Sihang Li, Yanchen Luo, Hao Fei, Yixin Cao, Kenji Kawaguchi, Xiang Wang, and Tat-Seng Chua. MolCA: Molecular graph-language modeling with cross-modal projector and uni-modal adapter. In Houda Bouamor, Juan Pino, and Kalika Bali (eds.), Proceedings of Conference on Empirical Methods in N… [find](https://scholar.google.com/scholar?q=Zhiyuan+Liu%2C+Sihang+Li%2C+Yanchen+Luo%2C+Hao+Fei%2C+Yixin+Cao%2C+Kenji+Kawaguchi%2C+Xiang+Wang%2C+and+Tat%2DSeng+Chua%2E+MolCA%3A+Molecular+graph%2Dlanguage+modeling+with+cross%2Dmodal+projector+and+uni%2Dmodal+adapter%2E+In+H)
38. Daniel Lowe. Chemical reactions from us patents (1976-sep2016), 2017. URL https://doi.org/10.6084/m9.figshare.5104873.v1. — [doi:10.6084/m9.figshare.5104873.v1](https://doi.org/10.6084/m9.figshare.5104873.v1) [↗](https://doi.org/10.6084/m9.figshare.5104873.v1)
39. Ines Filipa Martins, Ana L. Teixeira, Luis Pinheiro, and Andre O. Falcao. A bayesian approach to in silico blood-brain barrier penetration modeling. Journal of Chemical Information and Modeling, 52(6):1686–1697, 2012. [find](https://scholar.google.com/scholar?q=Ines+Filipa+Martins%2C+Ana+L%2E+Teixeira%2C+Luis+Pinheiro%2C+and+Andre+O%2E+Falcao%2E+A+bayesian+approach+to+in+silico+blood%2Dbrain+barrier+penetration+modeling%2E+Journal+of+Chemical+Information+and+Modeling%2C+52%286%29)
40. Brian W Matthews. Comparison of the predicted and observed secondary structure of t4 phage lysozyme. Biochimica et Biophysica Acta (BBA)-Protein Structure, 405(2):442–451, 1975. [find](https://scholar.google.com/scholar?q=Brian+W+Matthews%2E+Comparison+of+the+predicted+and+observed+secondary+structure+of+t4+phage+lysozyme%2E+Biochimica+et+Biophysica+Acta+%28BBA%29%2DProtein+Structure%2C+405%282%29%3A442%E2%80%93451%2C+1975%2E)
41. Monica P McNerney and Mark P Styczynski. Small molecule signaling, regulation, and potential applications in cellular therapeutics. Wiley Interdisciplinary Reviews: Systems Biology and Medicine, 10:e1405, 2018. [find](https://scholar.google.com/scholar?q=Monica+P+McNerney+and+Mark+P+Styczynski%2E+Small+molecule+signaling%2C+regulation%2C+and+potential+applications+in+cellular+therapeutics%2E+Wiley+Interdisciplinary+Reviews%3A+Systems+Biology+and+Medicine%2C+10%3Ae1)
42. David L. Mobley and J. Peter Guthrie. Freesolv: a database of experimental and calculated hydration free energies, with input files. Journal of Computer-Aided Molecular Design, 28(7): 711–720, 2014. [find](https://scholar.google.com/scholar?q=David+L%2E+Mobley+and+J%2E+Peter+Guthrie%2E+Freesolv%3A+a+database+of+experimental+and+calculated+hydration+free+energies%2C+with+input+files%2E+Journal+of+Computer%2DAided+Molecular+Design%2C+28%287%29%3A+711%E2%80%93720%2C+2014%2E)
43. H. L. Morgan. The generation of a unique machine description for chemical structures-a technique developed at chemical abstracts service. Journal of Chemical Documentation, 5(2): 107–113, 1965. [find](https://scholar.google.com/scholar?q=H%2E+L%2E+Morgan%2E+The+generation+of+a+unique+machine+description+for+chemical+structures%2Da+technique+developed+at+chemical+abstracts+service%2E+Journal+of+Chemical+Documentation%2C+5%282%29%3A+107%E2%80%93113%2C+1965%2E)
44. Ohio Supercomputer Center. Ohio supercomputer center, 1987. URL [http://osc.edu/ark:/19495/f5s1ph73](http://osc.edu/ark:/19495/f5s1ph73). [↗](http://osc.edu/ark:/19495/f5s1ph73)
45. OpenAI. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774, 2023.
46. Salwa K Poole and Colin F Poole. Separation methods for estimating octanol–water partition coefficients. Journal of Chromatography B, 797(1–2):3–19, 2003. [find](https://scholar.google.com/scholar?q=Salwa+K+Poole+and+Colin+F+Poole%2E+Separation+methods+for+estimating+octanol%E2%80%93water+partition+coefficients%2E+Journal+of+Chromatography+B%2C+797%281%E2%80%932%29%3A3%E2%80%9319%2C+2003%2E)
47. Kohulan Rajan, Achim Zielesny, and Christoph Steinbeck. Stout: Smiles to iupac names using neural machine translation. Journal of Cheminformatics, 13(1):1–14, 2021. [find](https://scholar.google.com/scholar?q=Kohulan+Rajan%2C+Achim+Zielesny%2C+and+Christoph+Steinbeck%2E+Stout%3A+Smiles+to+iupac+names+using+neural+machine+translation%2E+Journal+of+Cheminformatics%2C+13%281%29%3A1%E2%80%9314%2C+2021%2E)
48. RDKit. Rdkit: Open-source cheminformatics, 2023. URL https://doi.org/10.5281/zenodo. 8254217. Accessed on 27 Jan 2024. — [doi:10.5281/zenodo](https://doi.org/10.5281/zenodo) [↗](https://doi.org/10.5281/zenodo)
49. Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, Jérémy Rapin, et al. [Code llama: Open foundation models for code](https://md.research.elamur.ai/free/en/papers/roziere-2024-code-llama-open-foundation-models/). arXiv preprint arXiv:2308.12950, 2023.
50. Nadine Schneider, Roger A Sayle, and Gregory A Landrum. Get your atoms in order: An open-source implementation of a novel and robust molecular canonicalization algorithm. Journal of chemical information and modeling, 55(10):2111–2120, 2015. [find](https://scholar.google.com/scholar?q=Nadine+Schneider%2C+Roger+A+Sayle%2C+and+Gregory+A+Landrum%2E+Get+your+atoms+in+order%3A+An+open%2Dsource+implementation+of+a+novel+and+robust+molecular+canonicalization+algorithm%2E+Journal+of+chemical+informati)
51. Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Christopher A Hunter, Costas Bekas, and Alpha A Lee. Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS central science, 5(9):1572–1583, 2019. [find](https://scholar.google.com/scholar?q=Philippe+Schwaller%2C+Teodoro+Laino%2C+The%CC%81ophile+Gaudin%2C+Peter+Bolgar%2C+Christopher+A+Hunter%2C+Costas+Bekas%2C+and+Alpha+A+Lee%2E+Molecular+transformer%3A+a+model+for+uncertainty%2Dcalibrated+chemical+reaction+pre)
52. T. W. Graham Solomons, Craig B. Fryhle, and Scott A. Snyder. Organic Chemistry, Integrated E-Text with E-Solutions Manual. Wiley, 13th edition, 2022. [find](https://scholar.google.com/scholar?q=T%2E+W%2E+Graham+Solomons%2C+Craig+B%2E+Fryhle%2C+and+Scott+A%2E+Snyder%2E+Organic+Chemistry%2C+Integrated+E%2DText+with+E%2DSolutions+Manual%2E+Wiley%2C+13th+edition%2C+2022%2E)
53. Vignesh Ram Somnath, Charlotte Bunne, Connor Coley, Andreas Krause, and Regina Barzilay. Learning graph models for retrosynthesis prediction. Advances in Neural Information Processing Systems, 34:9405–9415, 2021. [find](https://scholar.google.com/scholar?q=Vignesh+Ram+Somnath%2C+Charlotte+Bunne%2C+Connor+Coley%2C+Andreas+Krause%2C+and+Regina+Barzilay%2E+Learning+graph+models+for+retrosynthesis+prediction%2E+Advances+in+Neural+Information+Processing+Systems%2C+34%3A9405)
54. Ross Taylor, Marcin Kardas, Guillem Cucurull, Thomas Scialom, Anthony Hartshorn, Elvis Saravia, Andrew Poulton, Viktor Kerkez, and Robert Stojnic. [Galactica: A large language model for science](https://md.research.elamur.ai/free/en/papers/taylor-2022-galactica-large-language-model-science/). arXiv preprint arXiv:2211.09085, 2022.
55. Arun James Thirunavukarasu, Darren Shu Jeng Ting, Kabilan Elangovan, Laura Gutierrez, Ting Fang Tan, and Daniel Shu Wei Ting. Large language models in medicine. Nature Medicine, 29(8):1930–1940, 2023. [find](https://scholar.google.com/scholar?q=Arun+James+Thirunavukarasu%2C+Darren+Shu+Jeng+Ting%2C+Kabilan+Elangovan%2C+Laura+Gutierrez%2C+Ting+Fang+Tan%2C+and+Daniel+Shu+Wei+Ting%2E+Large+language+models+in+medicine%2E+Nature+Medicine%2C+29%288%29%3A1930%E2%80%931940%2C+2023%2E)
56. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971, 2023a.
57. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288, 2023b.
58. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Proceedings of Conference on Advances in neural information processing systems (NeurIPS), volume 30, 2017.
59. Yuyang Wang, Zijie Li, and Amir Barati Farimani. Graph Neural Networks for Molecules. In Chen Qu and Hanchao Liu (eds.), Machine Learning in Molecular Sciences, pp. 21–66. Springer International Publishing, Cham, 2023. ISBN 978-3-031-37196-7. doi: 10.1007/ 978-3-031-37196-7 2. URL https://doi.org/10… — [doi:10.1007/978-3-031-37196-7](https://doi.org/10.1007/978-3-031-37196-7) [find](https://scholar.google.com/scholar?q=Yuyang+Wang%2C+Zijie+Li%2C+and+Amir+Barati+Farimani%2E+Graph+Neural+Networks+for+Molecules%2E+In+Chen+Qu+and+Hanchao+Liu+%28eds%2E%29%2C+Machine+Learning+in+Molecular+Sciences%2C+pp%2E+21%E2%80%9366%2E+Springer+International+Publi)
60. David Weininger. Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules. Journal of chemical information and computer sciences, 28 (1):31–36, 1988. [find](https://scholar.google.com/scholar?q=David+Weininger%2E+Smiles%2C+a+chemical+language+and+information+system%2E+1%2E+introduction+to+methodology+and+encoding+rules%2E+Journal+of+chemical+information+and+computer+sciences%2C+28+%281%29%3A31%E2%80%9336%2C+1988%2E)
61. Andrew D. White, Glen M. Hocky, Heta A. Gandhi, Mehrad Ansari, Sam Cox, Geemi P. Wellawatte, Subarna Sasmal, Ziyue Yang, Kangxin Liu, Yuvraj Singh, and Willmor J. Peña Ccoa. Assessment of chemistry knowledge in large language models that generate code. Digital Discovery, 2(2):368–376, 2023. [find](https://scholar.google.com/scholar?q=Andrew+D%2E+White%2C+Glen+M%2E+Hocky%2C+Heta+A%2E+Gandhi%2C+Mehrad+Ansari%2C+Sam+Cox%2C+Geemi+P%2E+Wellawatte%2C+Subarna+Sasmal%2C+Ziyue+Yang%2C+Kangxin+Liu%2C+Yuvraj+Singh%2C+and+Willmor+J%2E+Pen%CC%83a+Ccoa%2E+Assessment+of+chemistry+k)
62. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, et al. [Transformers: State-of-the-art natural language processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). In Proceedings of conference on empirical methods in natural language processing: syst…
63. Zhenqin Wu, Bharath Ramsundar, Evan N Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S Pappu, Karl Leswing, and Vijay Pande. Moleculenet: a benchmark for molecular machine learning. Chemical science, 9(2):513–530, 2018. [find](https://scholar.google.com/scholar?q=Zhenqin+Wu%2C+Bharath+Ramsundar%2C+Evan+N+Feinberg%2C+Joseph+Gomes%2C+Caleb+Geniesse%2C+Aneesh+S+Pappu%2C+Karl+Leswing%2C+and+Vijay+Pande%2E+Moleculenet%3A+a+benchmark+for+molecular+machine+learning%2E+Chemical+science%2C+)
64. Kevin Yang, Kyle Swanson, Wengong Jin, Connor Coley, Philipp Eiden, Hua Gao, Angel Guzman-Perez, Timothy Hopper, Brian Kelley, Miriam Mathea, Andrew Palmer, Volker Settels, Tommi Jaakkola, Klavs Jensen, and Regina Barzilay. Analyzing Learned Molecular Representations for Property Prediction. Journal… [find](https://scholar.google.com/scholar?q=Kevin+Yang%2C+Kyle+Swanson%2C+Wengong+Jin%2C+Connor+Coley%2C+Philipp+Eiden%2C+Hua+Gao%2C+Angel+Guzman%2DPerez%2C+Timothy+Hopper%2C+Brian+Kelley%2C+Miriam+Mathea%2C+Andrew+Palmer%2C+Volker+Settels%2C+Tommi+Jaakkola%2C+Klavs+Jense)
65. Geyan Ye, Xibao Cai, Houtim Lai, Xing Wang, Junhong Huang, Longyue Wang, Wei Liu, and Xiangxiang Zeng. Drugassist: A large language model for molecule optimization. arXiv preprint arXiv:2401.10334, 2023. — [arXiv:2401.10334](https://arxiv.org/abs/2401.10334) [find](https://scholar.google.com/scholar?q=Geyan+Ye%2C+Xibao+Cai%2C+Houtim+Lai%2C+Xing+Wang%2C+Junhong+Huang%2C+Longyue+Wang%2C+Wei+Liu%2C+and+Xiangxiang+Zeng%2E+Drugassist%3A+A+large+language+model+for+molecule+optimization%2E+arXiv+preprint+arXiv%3A2401%2E10334%2C+20)
66. Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen. [Mammoth: Building math generalist models through hybrid instruction tuning](https://md.research.elamur.ai/free/en/papers/yue-2023-mammoth-building-math-generalist-models/). arXiv preprint arXiv:2309.05653, 2023.
67. Di Zhang, Wei Liu, Qian Tan, Jingdan Chen, Hang Yan, Yuliang Yan, Jiatong Li, Weiran Huang, Xiangyu Yue, Dongzhan Zhou, et al. [Chemllm: A chemical large language model](https://md.research.elamur.ai/free/en/papers/zhang-2024-chemllm-chemical-large-language-model/). arXiv preprint arXiv:2402.06852, 2024.
68. Tianshu Zhang, Xiang Yue, Yifei Li, and Huan Sun. [Tablellama: Towards open large generalist models for tables](https://md.research.elamur.ai/free/en/papers/zhang-2023-tablellama-towards-open-large-generalist/). arXiv preprint arXiv:2311.09206, 2023.
69. Yangtian Zhang, Huiyu Cai, Chence Shi, and Jian Tang. E3bind: An end-to-end equivariant network for protein-ligand docking. In The Eleventh International Conference on Learning Representations, 2022a. [find](https://scholar.google.com/scholar?q=Yangtian+Zhang%2C+Huiyu+Cai%2C+Chence+Shi%2C+and+Jian+Tang%2E+E3bind%3A+An+end%2Dto%2Dend+equivariant+network+for+protein%2Dligand+docking%2E+In+The+Eleventh+International+Conference+on+Learning+Representations%2C+2022a%2E)
70. Zaixi Zhang, Yaosen Min, Shuxin Zheng, and Qi Liu. Molecule generation for target protein binding with structural motifs. In The Eleventh International Conference on Learning Representations, 2022b. [find](https://scholar.google.com/scholar?q=Zaixi+Zhang%2C+Yaosen+Min%2C+Shuxin+Zheng%2C+and+Qi+Liu%2E+Molecule+generation+for+target+protein+binding+with+structural+motifs%2E+In+The+Eleventh+International+Conference+on+Learning+Representations%2C+2022b%2E)
71. Zipeng Zhong, Jie Song, Zunlei Feng, Tiantao Liu, Lingxiang Jia, Shaolun Yao, Min Wu, Tingjun Hou, and Mingli Song. Root-aligned smiles: a tight representation for chemical reaction prediction. Chemical Science, 13(31):9023–9034, 2022. [find](https://scholar.google.com/scholar?q=Zipeng+Zhong%2C+Jie+Song%2C+Zunlei+Feng%2C+Tiantao+Liu%2C+Lingxiang+Jia%2C+Shaolun+Yao%2C+Min+Wu%2C+Tingjun+Hou%2C+and+Mingli+Song%2E+Root%2Daligned+smiles%3A+a+tight+representation+for+chemical+reaction+prediction%2E+Chemic)
72. Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, and Guolin Ke. Uni-mol: A universal 3d molecular representation learning framework. In International Conference on Learning Representations (ICLR), 2023. [find](https://scholar.google.com/scholar?q=Gengmo+Zhou%2C+Zhifeng+Gao%2C+Qiankun+Ding%2C+Hang+Zheng%2C+Hongteng+Xu%2C+Zhewei+Wei%2C+Linfeng+Zhang%2C+and+Guolin+Ke%2E+Uni%2Dmol%3A+A+universal+3d+molecular+representation+learning+framework%2E+In+International+Confere)
73. Table of Contents in Appendix A Preliminaries [find](https://scholar.google.com/scholar?q=Table+of+Contents+in+Appendix+A+Preliminaries)

*Updated 3 November 2026*