Replication timing is a costly but powerful tool for characterizing cellular mechanisms underlying chromatin organization cancer epigenetics and genomic instability. Genome wide replication timing profiles reflect the temporal order of DNA synthesis during S phase and are linked to chromatin accessibility transcriptional activity and proliferative state. Prior work has demonstrated a robust inverse relationship between replication timing and DNA methylation at the domain scale enabling methylation based proxies to approximate replication timing in large cohorts where direct experimental measurement is impractical. Given the coupling between replication timing chromatin structure and cellular phenotype we hypothesized that histologic morphology encodes information consistent with replication timing states. To test this hypothesis we implemented Vision Transformer ViT architectures to predict replication timing proxies from whole slide histopathology images. Patch level embeddings were extracted using a pretrained ViT and aggregated through attention based multiple instance learning to predict sample level replication timing. In parallel CellViT models were employed to perform cell level prediction enabling comparison between patch based and cellular representations. Across both modeling strategies statistically significant correlations were observed between image derived features and methylation based replication timing proxies. Patch level models achieved correlations of approximately 46 percent while cell level models exceeded 50 percent on the validation cohort with mean absolute error and mean squared error values ranging between 0.4 and 0.6. These results demonstrate that replication timing associated epigenomic states are reflected in tissue morphology and can be inferred from routine histopathology establishing a feasible framework for noninvasive replicosomic inference and future spatially resolved analyses.
Leyva et al. (Fri,) studied this question.