Asymmetric predictive relationships across histone modifications

Knowledge of the wide array of epigenomic signals provides biological insight into the state of a give cell type, but it is infeasible to experimentally characterize all possible types of epigenomic signal in the multitude of cell types in the human body. The authors present Ocelot, a machine learning approach for imputing cell-type-specific epigenomic signals along the genome. Decoding the epigenomic landscapes in diverse tissues and cell types is fundamental to understanding molecular mechanisms underlying many essential cellular processes and human diseases. Recent advances in artificial intelligence provide new methods and strategies for imputing unknown epigenomes based on existing data, yet how to reveal the predictive relationships among epigenetic marks remains largely unexplored. Here we present a machine learning approach for epigenomic imputation and interpretation. Through dissection of the spatial contributions from six histone marks, we reveal the prevalent and asymmetric cross-prediction relationships among these marks. Meanwhile, our approach achieved high predictive performance on held-out prospective epigenomes and outperformed the state of the art. To facilitate future research, we further applied this approach to impute a total of 527 and 2,455 unavailable genome-wide histone modification signal tracks for the ENCODE3 and Roadmap datasets, respectively.

Automated summary

The authors introduce Ocelot, a machine learning approach for inferring cell-type-specific epigenomic signals, to uncover molecular mechanisms and potential mechanisms of diseases. By dissecting the spatial contributions of six histone marks, the prevalent and asymmetric cross-prediction relationships among these marks are revealed, with high predictive performance achieved on future epigenomic data.