$\textit{BlockFormer}$ : Transformer-based inference from interaction maps
For computational biology, this provides a data-driven solution to a previously manual or heuristic problem of centromere localization from Hi-C maps.
BlockFormer introduces a transformer-based method to infer parameters from interaction maps, such as centromere positions from Hi-C data, handling variability in entity count and size. It accurately recovers genomic positions across diverse species with varying genome sizes.
Inference from interaction maps, such as centromere identification from genome-wide chromosome conformation capture techniques -- notably Hi-C -- can be formulated as a generic inverse problem: infer a set of parameters given a map summarizing pairwise interactions between entities through blocks of variable numbers and sizes. In this work, we introduce a data-driven approach that leverages shared structure between these maps, such as global alignment between localized patterns, while handling the variability in number and size of entities arising in real-world data. Our approach relies on a transformer architecture capable of handling such variability and a custom simulator to generate abundant, yet computationally cheap synthetic data for training. Applied to the problem of centromere localization, the method accurately recovers their genomic positions across a wide range of species of various genome sizes.