A Multi-Omic “Digital Embryo” Framework to Model Early Human Preimplantation Development In Silico

Overview

Nearly 50% of IVF embryos arrest before they become viable pregnancies, and the molecular mechanisms causing this failure remain poorly understood. The Digital Embryo is the first multi-omic framework integrating 6 omics — transcriptomics, proteomics, metabolomics, secretomics, genomics, and epigenomics — into a shared molecular-state system spanning 1,963 cells. A machine learning model trained on these omics predicts embryo arrest, achieving an AUC of 0.870 on unseen datasets. Beyond prediction, the Digital Embryo can map any individual embryo as a one-to-one molecular replica in silico. Its perturbation engine then allows for the modification of that embryo’s omic profile, culture conditions, and environmental exposures, and recalculates its arrest risk. Validated against 85 compounds, 37/40 of the strongest predicted effects on arrest matched known in vitro results. The Digital Embryo also generated 35 candidate treatment combinations against arrest, demonstrating the capacity for computational treatment discovery and personalized, multi-omic-guided reproductive medicine.

Awards (3)

• Young Scientist Award
• Gold Medal
• Selected for CWSF 2026

Competition history

• CWSF 2026 Disease & Illness

Related projects

Closest projects by meaning, across every fair and year in the corpus.