{"id":25471,"date":"2021-10-22T00:00:00","date_gmt":"2024-09-13T08:48:48","guid":{"rendered":"https:\/\/wordpress-583806-4798031.cloudwaysapps.com\/leveling-up-life-sciences-ai-and-in-silico-research\/"},"modified":"2024-11-15T16:21:26","modified_gmt":"2024-11-15T15:21:26","slug":"leveling-up-life-sciences-ai-and-in-silico-research","status":"publish","type":"post","link":"https:\/\/informator.se\/en\/leveling-up-life-sciences-ai-and-in-silico-research\/","title":{"rendered":"Leveling Up Life Sciences: AI and In-Silico Research"},"content":{"rendered":"
\n

My post in March focused on AI in vaccine R&D<\/a>, for obvious reasons. Half a year later, it\u2019s time for a wider perspective: Where do we go from here? How much of R&D experiments do bio-scientists expect to go from \u201cin vivo\u201d to other methods? Their hints indicate that new methods will accelerate, and in silico is getting hot; which in turn creates an urgent need to train<\/strong> the teams upfront before training the ML models. Importantly for CIOs and IT architects, a cross-connected multimodel-experiment ecosystem in silico will also require a more architected infrastructure<\/strong> than islands of single-model single-disease projects did.<\/em><\/p>\n\n\n\n

A paper from September 2021 on In Silico Modeling<\/a> of Biochemical Pathways compared traditional numerical integration techniques to an interaction-pattern based approach. The trend is similar in other domains; e.g. in flow models for wind tunnels or pipelines, focus shifts from differential equations to interaction patterns and event-series patterns. <\/p>\n\n\n\n

Searching PubMed.gov for \u201cartificial intelligence\u201d today returned 140,820 results. \u201cMachine learning\u201d returned 71,723. Searching a single med-research institution website in Sweden (Karolinska) for \u201cAI\u201d returned 311 hits. \u201cMachine learning\u201d returned 182.<\/p>\n\n\n\n

DeepMind AlphaFold2<\/a> has predicted the shapes of nearly every protein in the human body, and is expected to predict, in the coming months, practically all proteins known<\/em> to science. This takes in Silico research to a new era. As professor Luca Jovine put it in Karolinska Institutets KI News<\/a> this month: AI may allow us, in the future, to accurately simulate highly complex biological scenarios in silico<\/em> as well as leverage this information for therapeutic intervention<\/em>. <\/p>\n\n\n\n

KI\/IMM toxicologist Mattias \u00d6berg\u2019s recent report<\/a> (in Swedish) states that new methods without animal experiments are of strategic importance for the country\u2019s research and innovation<\/em>. You can hear \u201chis take\u201d on future multimodel experiments cross-connected by an IT infrastructure, in a (Swedish) radio interview<\/a> from Monday this week.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

There are dozens of ways AI transforms life sciences. An article by Dr. Shweta Murudkar three weeks ago pinpoints the Big Ten ways<\/a>, in an outlook consistent with those of other life-sciences industry experts<\/a>. Like toxicologist Mattias \u00d6berg and many others, Murudkar also underlines the emerging \u201c2.0\u201d of the long-lasting win-win relationship between gene-based models and AI (see also diagram example<\/a> from Informator\u2019s course, 2020).<\/p>\n\n\n\n

What about the standard architectural question: which barriers can slow down<\/em> the life science ecosystem\u2019s benefit from its ever-growing data? They\u2019re similar to other domains: Training an ML model is a minor part work in an ML project. The non-profit Pistoia Alliance<\/a> found bottlenecks in culture, application landscape & organizational landscape, interoperability, data quality\/formats and access. Hence an urgent need to further educate<\/em> the domain experts as well as the architects, data experts, and IT experts. AI or data\/analytics skills are in demand<\/em>, while forecasts for apps in life sciences are pointing upward.<\/p>\n\n\n\n

Milan’s courses at Informator<\/h4>\n\n\n\n