ReactionDataExtractor 2.0: A Deep Learning Approach for Data Extraction from Chemical Reaction Schemes

Automated electrosynthesis reaction mining with multimodal large language models (MLLMs)

Leveraging the chemical data available in legacy formats such as publications and patents is a significant challenge for the community. Automated reaction mining offers a promising solution to unleash this knowledge into a learnable digital form and therefore help expedite materials and reaction discovery. However, existing reaction mining toolkits are limited to single input modalities (text or images) and cannot effectively integrate heterogeneous data that is scattered across text, tables, and figures. In this work, we go beyond single input modalities and explore multimodal large language models (MLLMs) for the analysis of diverse data inputs for automated electrosynthesis reaction mining. We compiled a test dataset of 65 articles (MERMES-T24 set) and employed it to benchmark five prominent MLLMs against two critical tasks: (i) reaction diagram parsing and (ii) resolving cross-modality data interdependencies. The frontrunner MLLM achieved ≥96% accuracy in both tasks, with the strategic integration of single-shot visual prompts and image pre-processing techniques. We integrate this capability into a toolkit named MERMES (multimodal reaction mining pipeline for electrosynthesis). Our toolkit functions as an end-to-end MLLM-powered pipeline that integrates article retrieval, information extraction and multimodal analysis for streamlining and automating knowledge extraction. This work lays the groundwork for the increased utilization of MLLMs to accelerate the digitization of chemistry knowledge for data-driven research.

Extracting structured data from organic synthesis procedures using a fine-tuned large language model

The popularity of data-driven approaches and machine learning (ML) techniques in the field of organic chemistry and its various subfields has increased the value of structured reaction data. Most data in chemistry is represented by unstructured text, and despite the vastness of the organic chemistry literature (papers, patents), manual conversion from unstructured text to structured data remains a largely manual endeavor. Software tools for this task would facilitate downstream applications such as reaction prediction and condition recommendation. In this study, we fine-tune a large language model (LLM) to extract reaction information from organic synthesis procedure text into structured data following the Open Reaction Database (ORD) schema, a comprehensive data structure designed for organic reactions. The fine-tuned model produces syntactically correct ORD records with an average accuracy of 91.25% for ORD "messages" (e.g., full compound, workups, or condition definitions) and 92.25% for individual data fields (e.g., compound identifiers, mass quantities), with the ability to recognize compound-referencing tokens and to infer reaction roles. We investigate its failure modes and evaluate performance on specific subtasks such as reaction role classification.

EnzChemRED, a rich enzyme chemistry relation extraction dataset

Expert curation is essential to capture knowledge of enzyme functions from the scientific literature in FAIR open knowledgebases but cannot keep pace with the rate of new discoveries and new publications. In this work we present EnzChemRED, for Enzyme Chemistry Relation Extraction Dataset, a new training and benchmarking dataset to support the development of Natural Language Processing (NLP) methods such as (large) language models that can assist enzyme curation. EnzChemRED consists of 1,210 expert curated PubMed abstracts where enzymes and the chemical reactions they catalyze are annotated using identifiers from the protein knowledgebase UniProtKB and the chemical ontology ChEBI. We show that fine-tuning language models with EnzChemRED significantly boosts their ability to identify proteins and chemicals in text (86.30% F1 score) and to extract the chemical conversions (86.66% F1 score) and the enzymes that catalyze those conversions (83.79% F1 score). We apply our methods to abstracts at PubMed scale to create a draft map of enzyme functions in literature to guide curation efforts in UniProtKB and the reaction knowledgebase Rhea.

OpenChemIE: An Information Extraction Toolkit for Chemistry Literature

Information extraction from chemistry literature is vital for constructing up-to-date reaction databases for data-driven chemistry. Complete extraction requires combining information across text, tables, and figures, whereas prior work has mainly investigated extracting reactions from single modalities. In this paper, we present OpenChemIE to address this complex challenge and enable the extraction of reaction data at the document level. OpenChemIE approaches the problem in two steps: extracting relevant information from individual modalities and then integrating the results to obtain a final list of reactions. For the first step, we employ specialized neural models that each address a specific task for chemistry information extraction, such as parsing molecules or reactions from text or figures. We then integrate the information from these modules using chemistry-informed algorithms, allowing for the extraction of fine-grained reaction data from reaction condition and substrate scope investigations. Our machine learning models attain state-of-the-art performance when evaluated individually, and we meticulously annotate a challenging dataset of reaction schemes with R-groups to evaluate our pipeline as a whole, achieving an F1 score of 69.5%. Additionally, the reaction extraction results of OpenChemIE attain an accuracy score of 64.3% when directly compared against the Reaxys chemical database. OpenChemIE is most suited for information extraction on organic chemistry literature, where molecules are generally depicted as planar graphs or written in text and can be consolidated into a SMILES format. We provide OpenChemIE freely to the public as an open-source package, as well as through a web interface.

Fine-tuning large language models for chemical text mining

Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental and computational chemists. The task is still considered to be extremely challenging due to the complexity of the chemical language and scientific literature. This study explored the power of fine-tuned large language models (LLMs) on five intricate chemical text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data extraction, and the conversion of reaction paragraphs to action sequences. The fine-tuned LLMs demonstrated impressive performance, significantly reducing the need for repetitive and extensive prompt engineering experiments. For comparison, we guided ChatGPT (GPT-3.5-turbo) and GPT-4 with prompt engineering and fine-tuned GPT-3.5-turbo as well as other open-source LLMs such as Mistral, Llama3, Llama2, T5, and BART. The results showed that the fine-tuned ChatGPT models excelled in all tasks. They achieved exact accuracy levels ranging from 69% to 95% on these tasks with minimal annotated data. They even outperformed those task-adaptive pre-training and fine-tuning models that were based on a significantly larger amount of in-domain data. Notably, fine-tuned Mistral and Llama3 show competitive abilities. Given their versatility, robustness, and low-code capability, leveraging fine-tuned LLMs as flexible and effective toolkits for automated data acquisition could revolutionize chemical knowledge extraction.

Text Mining the Literature to Inform Experiments and Rationalize Impurity Phase Formation for BiFeO3

We used data-driven methods to understand the formation of impurity phases in BiFeO3 thin-film synthesis through the sol-gel technique. Using a high-quality dataset of 331 synthesis procedures and outcomes extracted manually from 177 scientific articles, we trained decision tree models that reinforce important experimental heuristics for the avoidance of phase impurities but ultimately show limited predictive capability. We find that several important synthesis features, identified by our model, are often not reported in the literature. To test our ability to correctly impute missing synthesis parameters, we attempted to reproduce nine syntheses from the literature with varying degrees of "missingness". We demonstrate how a text-mined dataset can be made useful by informing new controlled experiments and forming a better understanding for impurity phase formation in this complex oxide system.