Language Models for Predicting Organic Synthesis Procedures

In optimizing organic chemical synthesis, researchers often face challenges in efficiently generating viable synthesis procedures that conserve time and resources in laboratory settings. This paper systematically analyzes multiple approaches to efficiently generate synthesis procedures for a wide va...

Full description

Saved in:
Bibliographic Details
Main Authors: Mantas Vaškevičius, Jurgita Kapočiūtė-Dzikienė
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/24/11526
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846106115221225472
author Mantas Vaškevičius
Jurgita Kapočiūtė-Dzikienė
author_facet Mantas Vaškevičius
Jurgita Kapočiūtė-Dzikienė
author_sort Mantas Vaškevičius
collection DOAJ
description In optimizing organic chemical synthesis, researchers often face challenges in efficiently generating viable synthesis procedures that conserve time and resources in laboratory settings. This paper systematically analyzes multiple approaches to efficiently generate synthesis procedures for a wide variety of organic synthesis reactions, aiming to decrease time and resource consumption in laboratory work. We investigated the suitability of different sizes of BART, T5, FLAN-T5, molT5, and classic sequence-to-sequence transformer models for our text-to-text task and utilized a large dataset prepared specifically for the task. Experimental investigations demonstrated that a fine-tuned molT5-large model achieves a BLEU score of 47.75. The results demonstrate the capability of LLMs to predict chemical synthesis procedures involving 24 possible distinct actions, many of which include various parameters like solvents, reaction agents, temperature, duration, solvent ratios, and other specific parameters. Our findings show that only when the core reactants are used as input, the models learn to correctly predict what ancillary components need to be included in the resulting procedure. These results are valuable for AI researchers and chemists, suggesting that curated datasets and large language model fine-tuning techniques can be tailored for specific reaction classes and practical applications. This research contributes to the field by demonstrating how deep-learning-based methods can be customized to meet the specific requirements of chemical synthesis, leading to more intelligent and resource-efficient laboratory processes.
format Article
id doaj-art-2225ea0fa2fa4c35b0b9353ec8ce3327
institution Kabale University
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2225ea0fa2fa4c35b0b9353ec8ce33272024-12-27T14:07:33ZengMDPI AGApplied Sciences2076-34172024-12-0114241152610.3390/app142411526Language Models for Predicting Organic Synthesis ProceduresMantas Vaškevičius0Jurgita Kapočiūtė-Dzikienė1Department of Applied Informatics, Vytautas Magnus University, Universiteto str. 10–202, LT-44404 Kaunas, LithuaniaDepartment of Applied Informatics, Vytautas Magnus University, Universiteto str. 10–202, LT-44404 Kaunas, LithuaniaIn optimizing organic chemical synthesis, researchers often face challenges in efficiently generating viable synthesis procedures that conserve time and resources in laboratory settings. This paper systematically analyzes multiple approaches to efficiently generate synthesis procedures for a wide variety of organic synthesis reactions, aiming to decrease time and resource consumption in laboratory work. We investigated the suitability of different sizes of BART, T5, FLAN-T5, molT5, and classic sequence-to-sequence transformer models for our text-to-text task and utilized a large dataset prepared specifically for the task. Experimental investigations demonstrated that a fine-tuned molT5-large model achieves a BLEU score of 47.75. The results demonstrate the capability of LLMs to predict chemical synthesis procedures involving 24 possible distinct actions, many of which include various parameters like solvents, reaction agents, temperature, duration, solvent ratios, and other specific parameters. Our findings show that only when the core reactants are used as input, the models learn to correctly predict what ancillary components need to be included in the resulting procedure. These results are valuable for AI researchers and chemists, suggesting that curated datasets and large language model fine-tuning techniques can be tailored for specific reaction classes and practical applications. This research contributes to the field by demonstrating how deep-learning-based methods can be customized to meet the specific requirements of chemical synthesis, leading to more intelligent and resource-efficient laboratory processes.https://www.mdpi.com/2076-3417/14/24/11526deep learninglarge language modelorganic synthesissynthesis proceduremachine learningartificial intelligence
spellingShingle Mantas Vaškevičius
Jurgita Kapočiūtė-Dzikienė
Language Models for Predicting Organic Synthesis Procedures
Applied Sciences
deep learning
large language model
organic synthesis
synthesis procedure
machine learning
artificial intelligence
title Language Models for Predicting Organic Synthesis Procedures
title_full Language Models for Predicting Organic Synthesis Procedures
title_fullStr Language Models for Predicting Organic Synthesis Procedures
title_full_unstemmed Language Models for Predicting Organic Synthesis Procedures
title_short Language Models for Predicting Organic Synthesis Procedures
title_sort language models for predicting organic synthesis procedures
topic deep learning
large language model
organic synthesis
synthesis procedure
machine learning
artificial intelligence
url https://www.mdpi.com/2076-3417/14/24/11526
work_keys_str_mv AT mantasvaskevicius languagemodelsforpredictingorganicsynthesisprocedures
AT jurgitakapociutedzikiene languagemodelsforpredictingorganicsynthesisprocedures