(Press-News.org) Highlights:
Since its inception in 2014, Insilico Medicine has developed multiple AI models for predicting the probability of success of clinical trials focusing on Phase II to Phase III transition probabilities.
To validate the models, it pursued three strategies - retrospective, quasi-prospective, and prospective validation.
In 2016, it deposited on a preprint server the first date-stamped article with the predictions of clinical trials.
The publication titled “Prediction of clinical trials outcomes based on target choice and clinical trial design with multi‐modal artificial intelligence” presents the results of this multi-year multi-model validation.
The SaaS software platform incorporating the AI models presented in the study is available for use in pilots, collaboration programs, as well as for use by analysts, hedge funds, and banks to evaluate the clinical trials of small and medium-sized biotechnology companies.
Insilico Medicine (“Insilico”), a clinical-stage end-to-end generative artificial intelligence (AI) drug discovery company, has demonstrated that it can predict the outcome of Phase II to Phase III clinical trial success using its proprietary transformer-based AI clinical trial prediction tool called inClinico with a high degree of accuracy. The research has been published in Clinical Pharmacology and Therapeutics, an authoritative cross-disciplinary journal in experimental and clinical medicine.
The AI engines used in the study are integrated into Insilico’s inClinico system designed to predict the outcomes of clinical trials and is a part of the Medicine42 clinical trials analysis and planning platform.
The inClinico system is now available for use in pilots, collaboration programs, as well as for use by qualifying industry analysts, hedge funds, and banks interested in comparing human analytical performance with the performance of multiple AI algorithms. The research paper included three types of validation of AI engines trained to predict the probability of success of Phase II trials including retrospective, quasi-prospective, and prospective validation.
The transformer-based AI software platform inClinico combines various engines leveraging generative AI and multimodal data (including text, omics, clinical trial design, and small molecule properties), and was trained on over 55,600 unique Phase II clinical trials over the last 7 years. The subsequent model for clinical trial probability of success developed by Insilico researchers demonstrated 79% accuracy on the outcomes of real-world trials in the prospective validation set where those outcomes were able to be measured.
Around 90% of drug development fails at the clinical stage for reasons including inability to show efficacy, safety concerns, and the complexity of diseases and data, resulting in the loss of trillions of dollars and decades of work.
“Clinical trial failures are complex problems that AI is uniquely positioned to solve,” says Alex Aliper, PhD, president of Insilico Medicine and one of the paper’s authors. “With this tool, we can help companies determine which programs to prioritize and give investors critical insights into the drug discovery programs that are most likely to succeed.”
The inClinico platform was validated in retrospective, quasi-prospective, and prospective validation studies internally and with pharmaceutical companies and financial institutions. The platform achieved 0.88 ROC AUC in predicting the Phase II to Phase III transition on a quasi-prospective validation dataset, a measure of performance in machine learning indicating a high level of discrimination capability.
The first prospective predictions were made and placed on date-stamped preprint servers in 2016. In addition to forecasting outcomes for several Phase II clinical trials and achieving 79% accuracy for the recently completed trials in the prospective validation set, inClinico also demonstrated the platform’s usefulness to investors – using a date stamped virtual trading portfolio demonstrating 35% 9-month return on investment (ROI). The paper notes that investment portfolios’ performance is dependent on numerous factors, many of which are very hard to foresee or model, and that these findings are intended to instead serve as proof-of-concept based on empirical evidence.
“Currently, more than half of Phase II trials fail, resulting in the loss of ten of millions of dollars and decades of effort. Accurate prediction of the likelihood of success of Phase II to Phase III transitions could be a game changer, giving biotech and pharma companies the opportunity to steer clinical trials toward successful outcomes earlier in the drug discovery process, and providing investors with valuable insights about which drugs in development are most likely to succeed,” says Alex Zhavoronkov, PhD, founder and CEO of Insilico Medicine and the study’s co-author.
The findings indicate that target choice is much more likely to impact clinical trial outcome prediction than trial design, underscoring that lack of efficacy is the primary driver of clinical trial failures. And the tool’s successful prediction included that of LNP023, a first-in-class factor B inhibitor for the rare, life-threatening blood disease paroxysmal nocturnal hemoglobinuria, indicating that inClinico could be useful even without prior information on the clinical relevance of the mechanism of the drug’s action in the disease.
The findings also demonstrate that inClinico could provide technical due diligence insights for investors, as well as help pharma companies prioritize their drug development programs.
“This promising outcome gives us much to build on,” says Petrina Kamya, PhD, Head of AI Platforms, President of Insilico Medicine Canada and co-author. “We plan to continue to refine this tool by identifying even more granular components of clinical trial protocol affecting clinical success as well as developing generative AI models that can create optimal clinical protocols from scratch and generate the most relevant criteria for patient selection.”
About Insilico Medicine
Insilico Medicine, a clinical stage biotech company powered by generative AI, is connecting biology, chemistry, and clinical trials analysis using next-generation AI systems. The company has developed AI platforms that utilize deep generative models, reinforcement learning, transformers, and other modern machine learning techniques for novel target discovery and the generation of novel molecular structures with desired properties. Insilico Medicine is developing breakthrough solutions to discover and develop innovative drugs for cancer, fibrosis, immunity, central nervous system diseases, infectious diseases, autoimmune diseases, and aging-related diseases. www.insilico.com
END
After 7 years, generative AI succeeds in predicting clinical trial outcomes
2023-08-03
[Attachments] See images for this press release:
ELSE PRESS RELEASES FROM THIS DATE:
Study highlights importance of mineral iron in ocean ecosystems
2023-08-03
New research published today in Nature has revealed the importance of mineral forms of iron in regulating the cycling of this bio-essential nutrient in the ocean.
The findings pave the way for new work on the relationship between the iron and carbon cycles and how changing ocean oxygen levels may interact.
The study, led by the University of Liverpool and involving collaborators in the United States, Australia and France, addresses a knowledge gap in ocean research.
Principal Investigator Professor Alessandro Tagliabue said: “To date we have not fully appreciated ...
NUS study: A patchwork of Wnt signalling ligands and receptors pattern the colours on the wings of butterflies
2023-08-03
Wnt signalling is a well-known mode of cell-to-cell communication in multicellular biological organisms. It involves the secretion of small Wnt glycoproteins, by signalling cells, that bind to receptor proteins in the membrane of receiving cells. This signal modifies proteins on the inside of these receiving cells to make cells grow, divide or differentiate. This mode of communication is fundamental in both normal and altered cellular development, such as in cancer and wound healing, and has remained in the limelight ...
University of Ottawa research team finds window into mechanisms of rare disease
2023-08-03
A University of Ottawa-led research team has published rigorous new research that advances a quest to understand a puzzling – and heartbreaking – ultra-rare disease that’s found almost exclusively in boys.
XLP-2 is a genetic X-linked lymphoproliferative disease first described in 2006. It typically has severe complications among patients who become infected with the Epstein-Barr virus, an exceedingly common virus that infects most people without problems in their teenage years or young adulthood. But when the few individuals with XLP-2 encounter the Epstein-Barr virus the experience is often fatal ...
Three out of every ten meals ordered from the main food delivery app in Brazil come from dark kitchens
2023-08-03
About a third of the restaurants listed on iFood, the food delivery app most used by Brazilians, are “dark kitchens”, according to the first study of the topic conducted in Brazil, and one of only a few worldwide.
An article on the study is published in the journal Food Research International. It has eight authors; the first three and the last are researchers at the State University of Campinas (UNICAMP) in São Paulo state.
Defined in the article as delivery-only restaurants that have no direct contact with consumers, have no premises for local consumption and sell solely ...
Butterfly-inspired films create vibrant colors while passively cooling objects
2023-08-03
WASHINGTON —On a hot summer day, white clothing feels cooler than other colors due to reflecting—not absorbing—sunlight. Other colors like blue or black, will undergo a heating effect as they absorb light. To circumvent this heating effect in colored cooling films, researchers drew inspiration from nanostructures in butterfly wings.
The new films, which don’t absorb any light, could be used on the outside of buildings, vehicles and equipment to reduce the energy needed for cooling while preserving vivid color properties.
“In buildings, large amounts of energy are used for cooling and ventilation, and running ...
MIT Press's Direct to Open (D2O) achieves second year goal, opens access to 82 new books in 2023
2023-08-03
Thanks to the support of libraries participating in Direct to Open (D2O), the MIT Press will publish its full list (see below) of 2023 scholarly monographs and edited collections open access on the MIT Press Direct platform.
Launched in 2021, D2O is a sustainable framework that harnesses the collective power of libraries to support open and equitable access to vital, leading scholarship. D2O moves scholarly books from a solely market-based, purchase model, where individuals and libraries buy ...
CMS Innovation Center new care, payment model influenced by Eskenazi Health, Regenstrief Institute, IU School of Medicine
2023-08-03
INDIANAPOLIS -- A team including Eskenazi Health, Indiana University School of Medicine and Regenstrief Institute has helped guide a new dementia care and payment model announced by the Centers for Medicare and Medicaid Services (CMS) Innovation Center.
Guiding an Improved Dementia Experience (GUIDE) is the first model established by the Innovation Center that directly addresses the needs of unpaid caregivers, usually family, of individuals living with Alzheimer’s disease and related dementia. The model will provide a comprehensive ...
Scientists warn about decoupling warming trend when detecting marine heat waves
2023-08-03
The climate crisis is severely affecting marine ecosystems around the world and the Mediterranean is not an exception. Marine heat waves associated with this crisis are causing massive mortality events throughout the basin. Given this scenario, their correct definition and characterization become a key element in defining possible future scenarios.
Now, a new study by the Institut de Ciències del Mar (ICM-CSIC) and the Institute of Marine Sciences of the National Research Council (CNR-ISMAR) has revealed how decoupling global warming trends affects the definition of marine heat waves characteristics. ...
On-off switch for enzymes
2023-08-03
Light affects living organisms in many different ways: for example, plants orient their growth direction towards the sun, while circadian rhythms in humans are controlled by daylight. These processes always involve photoreceptors, which are proteins that can sense different colours and intensities of light.
10,000-fold increase in enzymatic activity
Now, researchers at Graz University of Technology (TU Graz) have deciphered the function of a highly efficient photoreceptor. Their findings have been published in the journal Science Advances. The research ...
New-generation geostationary satellite reveals widespread midday depression in dryland photosynthesis during 2020 western US heatwave
2023-08-03
The western U.S., particularly the Southwest, has experienced a notable increase in record-breaking high temperatures over recent decades, with recurring drought and heatwaves. These conditions have resulted in severe consequences for both human and nature systems, including dire water shortages, rampant wildfires, substantial agricultural losses, and increased human mortality. These regions, dominated by water-limited ecosystems, face exacerbated water stress due to more frequent and protracted droughts and heatwaves, which can profoundly impair ecosystem ...