Artificial Intelligence News

The researchers developed an AI model to better predict which drug might induce birth

[ad_1]

New York, NY (July 17, 2023)—Data scientists at the Icahn School of Medicine at Mount Sinai in New York and colleagues have created an artificial intelligence model that may more accurately predict which drugs not currently classified as harmful may actually cause birth defects.

Credits: Ma’ayan et al., Communication Medicine https://creativecommons.org/licenses/by/4.0/.

New York, NY (July 17, 2023)—Data scientists at the Icahn School of Medicine at Mount Sinai in New York and colleagues have created an artificial intelligence model that may more accurately predict which drugs not currently classified as harmful may actually cause birth defects.

The model, or “knowledge graph,” is described in the July 17 issue of Natural journal Communication Medicine (DOI: 10.1038/s43856-023-00329-2), also has the potential to predict the involvement of pre-clinical compounds that may harm the developing fetus. This study is the first known to use knowledge graphs to integrate multiple data types to investigate the causes of congenital defects.

Birth defects are disorders that affect about 1 in 33 births in the United States. They can be functional or structural and are believed to be the result of a variety of factors, including genetics. However, the cause of most of these disabilities is still unknown. Certain substances found in medicines, cosmetics, food, and environmental pollutants have the potential to cause birth defects if exposed during pregnancy.

“We want to increase our understanding of reproductive health and fetal development, and most importantly, warn about the potential for new drugs to cause birth defects before these drugs are marketed and widely distributed,” said Avi Ma’ayan, PhD, Professor, Pharmacological Sciences, and Director of the Mount Sinai Center for Bioinformatics at Icahn Mount Sinai, and senior author of this paper. “While identifying underlying causes is a complex task, we offer hope that through complex data analysis such as this one which integrates evidence from multiple sources, we will be able, in some cases, to better predict, regulate, and protect against significant hazards that can cause birth defects.”

The researchers pooled knowledge across several data sets about birth defect associations noted in published work, including those produced by the NIH Common Fund program., to show how integrating data from these resources can lead to synergistic discoveries. In particular, aggregated data are derived from known reproductive health genetics, classification of drugs by risk during pregnancy, and how pre-clinical drugs and compounds affect biological mechanisms within human cells.

In particular, the data included studies on genetic associations, drug-induced gene expression changes and preclinical compounds in cell lines, known drug targets, genetic burden scores for human genes, and placental crossover scores for small molecule drugs.

Importantly, using ReproTox-KG, with semi-supervised learning (SSL), the research team prioritized 30,000 preclinical small molecule drugs because of their potential to cross the placenta and cause birth defects. SSL is a branch of machine learning that uses small amounts of labeled data to guide predictions for much larger unlabeled data. In addition, by analyzing the ReproTox-KG topology, more than 500 birth defect/gene/drug clicks were identified which could explain the molecular mechanisms underlying drug-induced birth defects. In graph theory terms, a click is a subset of a graph in which all vertices in a click are directly connected to all other vertices in the click.

The researchers caution that the findings of this study are preliminary and further trials are needed for validation.

Next, the researchers plan to use a similar graph-based approach for other projects focused on the relationship between genes, drugs, and disease. They also aim to use the processed data sets as training material for courses and workshops on bioinformatics analysis. In addition, they plan to expand the study to consider more complex data, such as gene expression of specific tissues and cell types collected at different stages of development.

“We hope our collaborative work will lead to a new global framework for assessing the potential toxicity of new drugs and elucidate the biological mechanisms by which some drugs, which are known to cause birth defects, may operate. It is possible that at some point in the future, regulatory agencies such as the US Food and Drug Administration and the US Environmental Protection Agency may use this approach to evaluate the risks of new drugs or other chemical applications,” said Dr. Ma’ayan.

This paper is entitled “Toxicology Knowledge Graph for Structural Birth Defects.”

Additional co-authors are John Erol Evangelista (Icahn of Mount Sinai), Daniel JB Clarke (Icahn of Mount Sinai), Zhuorui Xie (Icahn of Mount Sinai), Giacomo B. Marino, (Icahn of Mount Sinai), Vivian Utti (Icahn of Mount Sinai), Sherry L. Jenkins (Icahn Mount Sinai), Taha Mohseni Ahooyi (Children’s Hospital of Philadelphia), Cristian G. Bologa (University of New Mexico), Jeremy J. Yang (University of New Mexico), Jessica L. Binder (University of New Mexico), Praveen Kumar (University of New Mexico), Christophe G. Lambert (University of New Mexico), Jeffrey S. Grethe (University of California San Diego), Eric Wenger (Children’s Hospital of Philadelphia), Deanne Taylor, (Children’s Hospital of Philadelphia), Tudor I. Oprea (Children’s Hospital of Philadelphia), and Bernard de Bono (University of Auckland, New Zealand).

This project was supported by National Institutes of Health grants OT2OD030160, OT2OD030546, OT2OD032619, and OT2OD030162.

-####-

About the Icahn School of Medicine at Mount Sinai

The Icahn School of Medicine at Mount Sinai is internationally renowned for its outstanding research, education and clinical care programs. It is the only academic partner for the eight* member hospitals of the Mount Sinai Health System, one of the largest academic health systems in the United States, providing care to a large and diverse patient population.

Ranked 14th nationally in National Institutes of Health (NIH) funding and among the 99th percentile in research dollars per investigator according to the American Association of Medical Colleges, Icahn Mount Sinai has a talented, productive, and successful faculty. More than 3,000 full-time scientists, educators and clinicians work within and across 44 academic departments and 36 multidisciplinary institutions, a structure that facilitates exceptional collaboration and synergy. Our emphasis on translational research and proven therapeutics in areas such as genomics/big data, virology, neuroscience, cardiology, geriatrics, and gastrointestinal and liver diseases.

Icahn Mount Sinai offers highly competitive MD, PhD, and Masters degree programs, with a current enrollment of approximately 1,300 students. It has the largest postgraduate medical education program in the country, with more than 2,000 clinical residents and training associates across the Health System. In addition, more than 550 postdoctoral researchers are trained in Health Systems.

A culture of innovation and discovery permeates every Icahn Mount Sinai program. Mount Sinai’s technology transfer office, one of the largest in the nation, partners with faculty and trainees to pursue optimal intellectual property commercialization to ensure that Mount Sinai’s discoveries and innovations are translated into healthcare products and services that benefit society.

Icahn Mount Sinai’s commitment to scientific breakthroughs and clinical care is enhanced by academic affiliations that complement and complement the School’s programs.

Through the Mount Sinai Innovation Partner (MSIP), Health Systems facilitates the real-world application and commercialization of medical breakthroughs made at Mount Sinai. Additionally, MSIP develops research partnerships with industry leaders such as Merck & Co., AstraZeneca, Novo Nordisk and others.

The Icahn School of Medicine at Mount Sinai is located in New York City on the border between the Upper East Side and East Harlem, and classes take place on the campus overlooking Central Park. The Icahn Mount Sinai location offers many opportunities to interact and care for a diverse community. Learning extends beyond the boundaries of our physical campus, to the eight Mount Sinai Health System hospitals, our academic affiliates, and globally.

———————————————————-

* Mount Sinai Health System member hospitals: Mount Sinai Hospital; Mount Sinai Beth Israel; Brooklyn’s Mount Sinai; Morning Edge of Mount Sinai; Queen of Mount Sinai; South Nassau’s Mount Sinai; West Mount Sinai; and the New York Eye and Ear Hospital at Mount Sinai.


[ad_2]

Source link

Related Articles

Back to top button