Transcription Between Human-readable Synthetic Descriptions and Machine-executable Instructions: an Application of the Latest Pre-training Technology

Overview

Journal Chem Sci

Publisher Royal Society of Chemistry

Specialty Chemistry

Date 2023 Sep 15

PMID 37712039

Authors

Zheni Zeng

Yi-Chen Nie

Ning Ding

Qian-Jun Ding

Wei-Ting Ye

Cheng Yang

Maosong Sun

Weinan E

Rong Zhu

Zhiyuan Liu

Affiliations

Soon will be listed here.

Abstract

AI has been widely applied in scientific scenarios, such as robots performing chemical synthetic actions to free researchers from monotonous experimental procedures. However, there exists a gap between human-readable natural language descriptions and machine-executable instructions, of which the former are typically in numerous chemical articles, and the latter are currently compiled manually by experts. We apply the latest technology of pre-trained models and achieve automatic transcription between descriptions and instructions. We design a concise and comprehensive schema of instructions and construct an open-source human-annotated dataset consisting of 3950 description-instruction pairs, with 9.2 operations in each instruction on average. We further propose knowledgeable pre-trained transcription models enhanced by multi-grained chemical knowledge. The performance of recent popular models and products showing great capability in automatic writing (, ChatGPT) has also been explored. Experiments prove that our system improves the instruction compilation efficiency of researchers by at least 42%, and can generate fluent academic paragraphs of synthetic descriptions when given instructions, showing the great potential of pre-trained models in improving human productivity.

References

Swain M, Cole J . ChemDataExtractor: A Toolkit for Automated Extraction of Chemical Information from the Scientific Literature. J Chem Inf Model. 2016; 56(10):1894-1904. DOI: 10.1021/acs.jcim.6b00207. View

Walters W, Murcko M . Assessing the impact of generative AI on medicinal chemistry. Nat Biotechnol. 2020; 38(2):143-145. DOI: 10.1038/s41587-020-0418-2. View

Zeng Z, Yao Y, Liu Z, Sun M . A deep-learning system bridging molecule structure and biomedical text with comprehension comparable to human professionals. Nat Commun. 2022; 13(1):862. PMC: 8844428. DOI: 10.1038/s41467-022-28494-3. View

MERRIFIELD R . Automated synthesis of peptides. Science. 1965; 150(3693):178-85. DOI: 10.1126/science.150.3693.178. View

Rohrbach S, Siauciulis M, Chisholm G, Pirvan P, Saleeb M, M Mehr S . Digitization and validation of a chemical synthesis literature database in the ChemPU. Science. 2022; 377(6602):172-180. DOI: 10.1126/science.abo0058. View

M Mehr S, Craven M, Leonov A, Keenan G, Cronin L . A universal system for digitization and automatic execution of the chemical synthesis literature. Science. 2020; 370(6512):101-108. DOI: 10.1126/science.abc2986. View

Angelone D, Hammer A, Rohrbach S, Krambeck S, Granda J, Wolf J . Convergence of multiple synthetic paradigms in a universally programmable chemical synthesis machine. Nat Chem. 2020; 13(1):63-69. DOI: 10.1038/s41557-020-00596-9. View

Zhu Q, Zhang F, Huang Y, Xiao H, Zhao L, Zhang X . An all-round AI-Chemist with a scientific mind. Natl Sci Rev. 2022; 9(10):nwac190. PMC: 9674120. DOI: 10.1093/nsr/nwac190. View

Steiner S, Wolf J, Glatzel S, Andreou A, Granda J, Keenan G . Organic synthesis in a modular robotic system driven by a chemical programming language. Science. 2018; 363(6423). DOI: 10.1126/science.aav2211. View

10.

Eddy S . Hidden Markov models. Curr Opin Struct Biol. 1996; 6(3):361-5. DOI: 10.1016/s0959-440x(96)80056-x. View

11.

Burger B, Maffettone P, Gusev V, Aitchison C, Bai Y, Wang X . A mobile robotic chemist. Nature. 2020; 583(7815):237-241. DOI: 10.1038/s41586-020-2442-2. View

12.

Kim E, Huang K, Tomala A, Matthews S, Strubell E, Saunders A . Machine-learned and codified synthesis parameters of oxide materials. Sci Data. 2017; 4:170127. PMC: 5595045. DOI: 10.1038/sdata.2017.127. View

13.

Granda J, Donina L, Dragone V, Long D, Cronin L . Controlling an organic synthesis robot with machine learning to search for new reactivity. Nature. 2018; 559(7714):377-381. PMC: 6223543. DOI: 10.1038/s41586-018-0307-8. View

14.

Kononova O, Huo H, He T, Rong Z, Botari T, Sun W . Text-mined dataset of inorganic materials synthesis recipes. Sci Data. 2019; 6(1):203. PMC: 6794279. DOI: 10.1038/s41597-019-0224-1. View

15.

Vaucher A, Zipoli F, Geluykens J, Nair V, Schwaller P, Laino T . Automated extraction of chemical synthesis actions from experimental procedures. Nat Commun. 2020; 11(1):3601. PMC: 7367864. DOI: 10.1038/s41467-020-17266-6. View

16.

Coley C, Thomas 3rd D, Lummiss J, Jaworski J, Breen C, Schultz V . A robotic platform for flow synthesis of organic compounds informed by AI planning. Science. 2019; 365(6453). DOI: 10.1126/science.aax1566. View

17.

Shetty P, Rajan A, Kuenneth C, Gupta S, Panchumarti L, Holm L . A general-purpose material property data extraction pipeline from large polymer corpora using natural language processing. NPJ Comput Mater. 2023; 9(1):52. PMC: 10073792. DOI: 10.1038/s41524-023-01003-w. View

18.

Sathe G, Liu W, Gillen M, Duck P, Bender R, Ogilvie K . Automated synthesis of gene fragments. Science. 1981; 214(4518):270-4. DOI: 10.1126/science.6169150. View

19.

Ley S, Fitzpatrick D, Ingham R, Myers R . Organic synthesis: march of the machines. Angew Chem Int Ed Engl. 2015; 54(11):3449-64. DOI: 10.1002/anie.201410744. View