Medical Breakthrough! Using AI, Indian Researchers Identify Vaginal Microbiomes Causing Premature Births

In a path-breaking study carried out using artificial intelligence, researchers have found out the microbiomes responsible for causing premature births. Using data from 3757 women the researchers applied an artificial intelligence approach and discovered some bacterial species that were in higher amounts in women who delivered preterm.

In India, nearly 1 in every 6 babies born are premature and the cause in most of the premature deliveries are unknown. Many studies had shown that microbial infections in the vagina may cause preterm births but the kinds of organisms that cause this was not clear. The vaginal microbiome has a substantial role in the occurrence of preterm birth (PTB), which contributes substantially to neonatal mortality worldwide. However, current bioinformatics approaches mostly concentrate on the taxonomic classification and functional profiling of the microbiome, limiting their abilities to elucidate the complex factors that contribute to PTB.

To get more clarity on the kind of microbiomes that cause premature birth, a team of researchers from India have carried out a path-breaking research. Sudeepti Kulshrestha, Priyanka Narad, Brojen Singh, Somnath S. Pai, Pooja Vijayaraghavan, Ansh Tandon, Payal Gupta, Deepak Modi and Abhishek Sengupta carried out biomarker identification for preterm birth susceptibility where they conducted meta-analysis of vaginal microbiome using systems biology and machine learning. Their research was recently published in the American Journal of Reproductive Immunology.

The researchers obtained 3757 vaginal microbiome samples from five publicly available datasets and the samples were divided into two categories based on pregnancy outcome of preterm or term birth. Additionally, the samples were further categorized based on the participants’ race and trimester. They were subjected to taxonomic classification and functional profiling using the Parallel-META 3 software in Ubuntu environment. The obtained abundances were analyzed using an integrated systems biology and machine learning approach to determine the key microbes, pathways, and genes that contribute to PTB. The resulting features were further subjected to statistical analysis to identify the top nine features with the greatest effect sizes.

Dr. Abhishek Sengupta, the lead author of the research paper from Amity University said, “Using data from 3757 women we applied an artificial intelligence approach and discovered some bacterial species that were in higher amounts in women who delivered preterm. Further we also observed that the type of microbes that increases the succeptibility were not same across the world but differed by country of origin.”

The research identified nine significant features, namely Shuttleworthia, Megasphaera, Sneathia, proximal tubule bicarbonate reclamation pathway, systemic lupus erythematosus pathway, transcription machinery pathway, lepA gene, pepX gene, and rpoD gene. Their abundance variations were observed through the trimesters.

The research claimed that vaginal infections caused by Shuttleworthia, Megasphaera, and Sneathia and altered small metabolite biosynthesis pathways such as lipopolysaccharide folate and retinal may increase the susceptibility to PTB. The identification of these organisms, genes, pathways, and their networks can be specifically targeted for the treatment of bacterial infections that increase PTB risk.

“Using a systems biology  approach we found that these bacteria produce certain chemicals in high amounts which my ultimately cause preterm birth. We believe that the artificial intelligence approach will help researchers to analyse their data better and discover better the microbes cause preterm birth. This software can also be used by other researchers to study the involvement of microbiome in other diseases,” added Dr. Sengupta.