Generating Synthetic Molecular Time Series Data for ML and AI Applications: Considerations

University of Vermont The use of synthetic data is a crucial step in the development of neural network-based Artificial Intelligence (AI). While the methods for generating synthetic data for AI applications in other domains have a role in certain biomedical AI systems, primarily related to image processing, there is a critical gap in the generation of time series data for AI tasks where it is necessary to know how the system works. This is most pronounced in the ability to generate synthetic multi-dimensional molecular time series data (or synthetic mediator trajectories, or SMT); this data underpins research into biomarkers and mediator signatures for forecasting various diseases and is an essential component of the drug development pipeline. We argue the insufficiency of statistical and data-centric machine learning (ML) means of generating this type of synthetic data is due to a combination of factors: perpetual data sparsity due to the Curse of Dimensionality, the inapplicability of the Central Limit Theorem in terms of making assumptions about the statistical distributions of this type of data, and the Causal Hierarchy Theorem, which intrinsically limits the ability of data-centric methods to make statements about generative mechanisms that cross-scales (as is the case from cellular-molecular biology to an individual person’s state of health and disease). Alternatively, we present a rationale for using complex multi-scale mechanism-based simulation models, constructed and operated on to account for perpetual epistemic incompleteness and the need to provide maximal expansiveness in concordance with the Principle of Maximal Entropy. These procedures provide for the generation of SMT that minimizes the known shortcomings associated with neural network AI systems, namely overfitting and lack of generalizability. The generation of synthetic data that accounts for the identified factors of multi-dimensional time series data is an essential capability for the development of mediator-biomarker based AI forecasting systems, and therapeutic control development and optimization through systems like Drug Development Digital Twins. For more information visit: https://arxiv.org/abs/2303.09056 *Contents* 00:00 - Introduction 04:42 - Presentation: Gary An: Generating synthetic molecular time series data for ML and AI applications: Considerations 49:29 - Questions Moderator: James A. Glazier, PhD, Indiana University, Bloomington To view the slides for this video, please visit: https://docs.google.com/presentation/d/1IiEnt53ur3ZHSJkVDNe9iYTigvEcL2HA If you found this video useful, please check out our other videos on computational modeling, infection and immunology: https://youtube.com/playlist?list=PLiEtieOeWbMKh9VcQoinSwODcSZKMTGat Please consider joining our IMAG/MSM WG on Multiscale Modeling and Viral Pandemics: https://www.imagwiki.nibib.nih.gov/content/msm-viral-pandemics-meetings Please also consider joining the Global Alliance for Immune Prediction and Intervention: http://glimprint.org/