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.

Deep representation learning of chemical-induced transcriptional profile for phenotype-based drug discovery.

Artificial intelligence transforms drug discovery, with phenotype-based approaches emerging as a promising alternative to target-based methods, overcoming limitations like lack of well-defined targets. While chemical-induced transcriptional profiles offer a comprehensive view of drug mechanisms, inherent noise often obscures the true signal, hindering their potential for meaningful insights. Here, we highlight the development of TranSiGen, a deep generative model employing self-supervised representation learning. TranSiGen analyzes basal cell gene expression and molecular structures to reconstruct chemical-induced transcriptional profiles with high accuracy. By capturing both cellular and compound information, TranSiGen-derived representations demonstrate efficacy in diverse downstream tasks like ligand-based virtual screening, drug response prediction, and phenotype-based drug repurposing. Notably, in vitro validation of TranSiGen's application in pancreatic cancer drug discovery highlights its potential for identifying effective compounds. We envisage that integrating TranSiGen into the drug discovery and mechanism research holds significant promise for advancing biomedicine.

TG468: a text graph convolutional network for predicting clinical response to immune checkpoint inhibitor therapy.

Enhancing cancer treatment efficacy remains a significant challenge in human health. Immunotherapy has witnessed considerable success in recent years as a treatment for tumors. However, due to the heterogeneity of diseases, only a fraction of patients exhibit a positive response to immune checkpoint inhibitor (ICI) therapy. Various single-gene-based biomarkers and tumor mutational burden (TMB) have been proposed for predicting clinical responses to ICI; however, their predictive ability is limited. We propose the utilization of the Text Graph Convolutional Network (GCN) method to comprehensively assess the impact of multiple genes, aiming to improve the predictive capability for ICI response. We developed TG468, a Text GCN model framing drug response prediction as a text classification task. By combining natural language processing (NLP) and graph neural network techniques, TG468 effectively handles sparse and high-dimensional exome sequencing data. As a result, TG468 can distinguish survival time for patients who received ICI therapy and outperforms single gene biomarkers, TMB and some classical machine learning models. Additionally, TG468's prediction results facilitate the identification of immune status differences among specific patient types in the Cancer Genome Atlas dataset, providing a rationale for the model's predictions. Our approach represents a pioneering use of a GCN model to analyze exome data in patients undergoing ICI therapy and offers inspiration for future research using NLP technology to analyze exome sequencing data.

Tora3D: an autoregressive torsion angle prediction model for molecular 3D conformation generation.

Three-dimensional (3D) conformations of a small molecule profoundly affect its binding to the target of interest, the resulting biological effects, and its disposition in living organisms, but it is challenging to accurately characterize the conformational ensemble experimentally. Here, we proposed an autoregressive torsion angle prediction model Tora3D for molecular 3D conformer generation. Rather than directly predicting the conformations in an end-to-end way, Tora3D predicts a set of torsion angles of rotatable bonds by an interpretable autoregressive method and reconstructs the 3D conformations from them, which keeps structural validity during reconstruction. Another advancement of our method over other conformational generation methods is the ability to use energy to guide the conformation generation. In addition, we propose a new message-passing mechanism that applies the Transformer to the graph to solve the difficulty of remote message passing. Tora3D shows superior performance to prior computational models in the trade-off between accuracy and efficiency, and ensures conformational validity, accuracy, and diversity in an interpretable way. Overall, Tora3D can be used for the quick generation of diverse molecular conformations and 3D-based molecular representation, contributing to a wide range of downstream drug design tasks.

The protective effects of Zhi-Gan-Cao-Tang against diabetic myocardial infarction injury and identification of its effective constituents.

ETHNOPHARMACOLOGICAL RELEVANCE: Cardiovascular complications are highly prevalent in patients with diabetes. Zhi-Gan-Cao-Tang (ZGCT), a famous traditional Chinese medicine (TCM) prescription, can be used for the treatment of diabetes with cardiovascular disease complications. ZGCT is composed of nine Chinese herbs: the radix and rhizoma of Glycyrrhiza uralensis Fisch. (Gancao in Chinese, 12 g), the radix of Rehmannia glutinosa Libosch. (Dihuang in Chinese, 50 g), the radix and rhizoma of Panax ginseng C. A. Mey. (Renshen in Chinese, 6 g), the radix of Ophiopogon japonicus (L. f.) Ker-Gawl. (Maidong in Chinese, 10 g), the fructus of Ziziphus jujuba Mill. (Dazao in Chinese, 18 g), the fructus of Cannabis sativa L. (Maren in Chinese, 10 g), Donkey-hide gelatine (Ejiao in Chinese, 6 g), the ramulus of Cinnamomum cassia Presl (Guizhi in Chinese, 9 g), and the fresh rhizoma of Zingiber officinale Rosc. (Shengjiang in Chinese, 9 g). Many of these Chinese herbs are also used in other systems of medicine (Japan, India, European, etc.). However, the effects and effective constituents of ZGCT against diabetic cardiovascular disease remain unclear. AIM OF THE STUDY: This study aimed to investigate the protective effect of ZGCT against diabetic myocardial infarction (DMI) injury in vivo and in vitro and to identify the effective constituents of ZGCT. MATERIALS AND METHODS: The in vivo effect on DMI injury was evaluated in a DMI mouse model. The in vitro effect and effective constituent screening experiments were conducted in an H9c2 cardiomyocyte injury model induced by high glucose and hypoxia. RESULTS: It was found that ZGCT significantly reduced myocardial infarction size and serum lactate dehydrogenase (LDH) levels in DMI mice. Myocardial histopathological experiments showed that ZGCT alleviated the disordered arrangement and fracture of muscle fibers and cell disappearance and reduced inflammatory cell infiltration. Cellular experiments showed that ZGCT inhibited cardiomyocyte apoptosis by decreasing the expression of the proapoptotic factor Bax. In addition, it inhibited inflammatory reactions by suppressing the activation of the IκBα/NF-κB pathway and the expression of iNOS. Eight constituents from six Chinese herbs in the recipe of ZGCT were found to enhance the viability of injured cardiomyocytes, and six effective constituents played protective roles through anti-apoptotic and/or anti-inflammatory activities. In addition, one of the effective constituents, glycyrrhizic acid, was verified in vivo to have cardioprotective effect on DMI mice. CONCLUSIONS: The TCM prescription ZGCT protects against DMI by inhibiting cardiomyocyte apoptosis and reducing inflammatory reactions. Eight effective constituents of ZGCT were identified. This study provides a scientific basis for the clinical application of ZGCT and is valuable for quality marker research on this prescription.