A microRNA-based dynamic risk score for type 1 diabetes
Mugdha V. Joglekar, Wilson K. M. Wong, Pooja Kunte, Hrishikesh P. Hardikar, Reshmi A. Kulkarni, Ikhlak Ahmed, Ryan J. Farr, Nhan Ho Trong Pham, Madilyn Coles, Simranjeet Kaur, Cody L. Maynard, Riley Hayward, Vinod Thorat, Aniruddha Pant, Ammira Al‐Shabeeb Akil, Kim C. Donaghue, Alicia J. Jenkins, Milan K. Piya, Maria E. Craig, William M. Hague, Chittaranjan S. Yajnik, Juliana C.N. Chan, A. M. James Shapiro, Elizabeth A. Davis, Timothy W. Jones, Stephen E. Gitelman, Ronald C.W., Flemming Pociot, Anandwardhan A. Hardikar, on behalf of the PREDICT T1D Study Group, Caroline J. Taylor, Maria Virginia Pereira E Cotta, Nirupa Sachithanandan, Charlotte X. Dong, FAHMIDA KHAN EMA, Sathya Perera, Sarang N. Satoor, Sharda Bapat, Yoon Hi Cho, Andrzej S. Januszewski, Emma Scott, Pamela Acosta Reyes, Ritesh Chimoriya, Sonia R. Isaacs, Suzette Coat, Dattatray Bhat, Aboli Bhalerao, Alma Baptist, Rucha Wagh, Smita Dhadge, Vidya Gokhale, Kalpana Jog, Tejas Limaye, Neelima Thuse, Guozhi Jiang, Indri N. Purwana, Saira Qureshi, Peter Senior, Nirubasini Paramalingam, Chontiey Saxon, Gilles J. Guillemin, Thomas Loudovaris, Helen E. Thomas, David Martin, Jennifer R. Gamble, David N. O’Neal, Martha Lappas, Sandy R. Shultz, Stuart J. McDonald, Elham Hosseini‐Beheshti, Georges E. Grau, Wayne J. Hawthorne, Amita Limaye, Ralph Bright, Rohan R. Patil, Mahesh Karandikar, Sheela V. Joglekar, Vinay M. Joglekar, Janet Rowan, Noha Lim
Abstract
Identifying individuals at high risk of type 1 diabetes (T1D) is crucial as disease-delaying medications are available. Here we report a microRNA (miRNA)-based dynamic (responsive to the environment) risk score developed using multicenter, multiethnic and multicountry ('multicontext') cohorts for T1D risk stratification. Discovery (wet and dry lab) analysis identified 50 miRNAs associated with functional β cell loss, which is a hallmark of T1D. These miRNAs measured across n = 2,204 individuals from four contexts (4C: Australia, Denmark, Hong Kong SAR People's Republic of China, India) led to a four-context, miRNA-based dynamic risk score (DRS) that effectively stratified individuals with and without T1D. Generative artificial intelligence was used to create an enhanced four-context, miRNA-based DRS, which offered good predictive power (area under the curve = 0.84) for T1D stratification in a separate multicontext validation dataset (n = 662), and accurately predicted future exogenous insulin requirement at 1 hour of islet transplantation. In a clinical trial assessing the imatinib drug therapy, baseline miRNA signature, rather than clinical characteristics, distinguished drug responders from nonresponders at 1 year. This study harnessed machine learning/generative artificial intelligence approaches, identifying and validating a miRNA-based DRS for T1D discrimination and treatment efficacy prediction.