How AI systems can help people by predicting diseases and discovering cures

The quest to discover how diseases develop in humans is hampered by high costs and access to large enough data sets. Scientists are rushing to change that.

It would be a

moment: discovering exactly how the origin of diseases is related to lifestyle, environment and genetics. But reaching that milestone requires an enormous amount of scientific research. Artificial intelligence (AI) helps lay the groundwork for the breakthrough by streamlining research to create a fully automated system that can predict disease and discover cures on its own.

In April 2022 Japanese Okinawa Institute of Science and Technology (OIST) and Tokyo-based Corundum Systems Biology Inc began collaborating on a three-year project to establish an automated analytical system for microbiome and multi-omics data (data from various biological fields). The project is called MANTA: Multi-omics Analysis platform for the Nobel Turing challenge to develop AI scientists.

In addition to genetics, lifestyle factors such as dietary habits and sleep and environmental considerations such as exposure to pathogens and toxins are considered important determinants of human health. It is complicated to understand this mix, so it requires epidemiological studies with large sample sizes to detect and quantify the impact of each factor.

To date, many projects, including case-control studies and prospective cohort studies for certain risk factors, have aimed to identify the causes of disease.

« Back to recommendation stories

In many of these “phenotype” studies, biological samples such as blood, stool, urine, and oral swab samples are collected and tested. The resulting data leads further studies, linking a particular disease, lifestyle, location of residence or living environment to the microbiome in many parts of the world.

With more research, the involvement of the gut microbiome in the development and progression of multiple diseases, such as psychiatric disorders, metabolic disorders, brain diseases and cancer, is gradually becoming clearer.

In the long run, the MANTA project aims to better understand how living environments and factors unique to ethnic groups can be linked to causes of certain diseases.

To date, plans to expand in-depth phenotype studies have been challenged by the high cost and time required to obtain the necessary biological data. Another major hurdle has been the standardization of data quality: The number of participants required for each study is enormous, and the amount of data — from genomics, transcriptomics, proteomics and metabolomics to each study participant’s microbiome — is vast.

This makes AI-assisted analysis critical for taking the next steps. Automated gut microbiome systems and multi-omics data analysis can provide globally consistent, replicable, mass-reproducible assays.

It provides the basis for comprehensive data building, as the same participants in the study can be tracked over a longer period of time and periodically at intervals of 10 to 20 years and in any location in the world. The automated nature of AI allows huge groups of volunteer participants to be tracked over long periods of time, as it doesn’t involve the same cost and dedication as assigning people to perform the monitoring.

The goal and expectation is that when fully integrating AI into disease development research, many unknowns will become known. What causes diseases to spread, worsen and change, and additional early signs or symptoms yet to be discovered through research should reveal themselves with the new frontiers enabled by automated AI.

The MANTA project aims to achieve full automation by March 2025, leading a clear path for AI-assisted analysis that – if successful – will accelerate discoveries that benefit both longevity and quality of life.

Leave a Comment

Your email address will not be published.