Automatic extraction, prioritization and analysis of gut microbial metabolites from biomedical literature

Abstract

Many diseases are driven by gene-environment interactions. one important environmental factor is the metabolic output of human gut microbiota. A comprehensive catalog of human metabolites originated in microbes is critical for data-driven approaches to understand how microbial metabolism contributes to human health and diseases. Here we present a novel integrated approach to automatically extract and analyze microbial metabolites from 28 million published biomedical records. First, we classified 28,851,232 MEDLINE records into microbial metabolism-related or not. Second, candidate microbial metabolites were extracted from the classified texts. Third, we developed signal prioritization algorithms to further differentiate microbial metabolites from metabolites originated from other resources. finally, we systematically analyzed the interactions between extracted microbial metabolites and human genes. A total of 11,846 metabolites were extracted from 28 million MEDLINE articles. The combined text classification and signal prioritization significantly enriched true positives among top: manual curation of top 100 metabolites showed a true precision of 0.55, representing a significant 38.3-fold enrichment as compared to the precision of 0.014 for baseline extraction. More importantly, 29% extracted microbial metabolites have not been captured by existing databases. We performed data-driven analysis of the interactions between the extracted microbial metabolite and human genetics. This study represents the first effort towards automatically extracting and prioritizing microbial metabolites from published biomedical literature, which can set a foundation for future tasks of microbial metabolite relationship extraction from literature and facilitate data-driven studies of how microbial metabolism contributes to human diseases. Genetic, epigenetic, and environmental factors contribute to the susceptibility, progression and outcomes of many common complex diseases 1-3. While significant progress has been made in understanding genetic, molecular, cellular aspects of human diseases, there is limited understanding how modifiable environmental factors such as food, nutrition, lifestyle, and physical activity are involved in human diseases and health. Human gut microbiota, an important modifiable intermediator between external environmental exposure and host genetics, exist in symbiotic relation with human hosts 4-8. Accumulating biomedical evidence indicates that gut microbiota and their metabolites strongly influence disease susceptibility and progression in humans 9-12. However, the underlying mechanisms remain largely unknown. We have recently developed data-driven computational approaches to understand how microbial metabolites are mechanistically involved in various common complex diseases including colorectal cancer 13,14 , Alzheimer's disease 15 , psoriasis 16 , and rheumatoid arthritis 17,18. For example, we developed network-based systems approaches to examine genetic interactions between microbial metabolites and huma...

Gut–microbiota–microglia–brain interactions in Alzheimer’s disease: knowledge-based, multi-dimensional characterization

“…Another rich resource for a list of validated microbial metabolites is the 30 million published biomedical literature. Many microbial metabolites already reported in the literature are not included in the list of 220 microbial metabolites from HMDB [ 60 , 61 ]. We have recently developed natural language processing, text classification, and network-based approaches to automatically extract and prioritize microbial metabolites from 28 million biomedical articles [ 60 , 61 ].…”

“…Many microbial metabolites already reported in the literature are not included in the list of 220 microbial metabolites from HMDB [ 60 , 61 ]. We have recently developed natural language processing, text classification, and network-based approaches to automatically extract and prioritize microbial metabolites from 28 million biomedical articles [ 60 , 61 ]. Currently, we are manually curating top-ranked microbial metabolites extracted from biomedical literature, in order to update the analysis of microglia–microbial metabolite–gene–pathway–phenotype interactions in AD using an updated list of microbial metabolites.…”

Leveraging pre-trained language models for mining microbiome-disease relationships

“…In recent years, the field of NLP has witnessed substantial advancements owing to the emergence of Large Language Models (LLMs) and Generative AI models [ 12 ]. Consequently, there has been a growing interest in leveraging these techniques to tackle problems in the microbiome field as well [ 13 , 14 ]. Of particular significance is the work presented by Badal et al [ 13 ], which highlights the key challenges that must be addressed to establish meaningful knowledge bases for the microbiome disease problem.…”