A Deep Learning Framework for Chromatin Loop De Novo Prediction with Enhanced Feature Extraction

Chromatin encompasses a variety of three-dimensional structures with distinct forms and ranges, among which chromatin loops play a crucial role in gene regulatory mechanisms and the maintenance of cellular homeostasis. Despite the recognition of the critical role of chromatin loops, existing prediction models often overlook the heterogeneity among different feature data, and there is a scarcity of corresponding prediction tools. To fill this gap, we introduce CHASOS2 (CHromatin loop prediction with Anchor Score and OCR Score), a user-friendly toolkit for de novo prediction and evaluation of chromatin loop. CHASOS2 uses convolutional modules with multi-receptive fields to generate features capable of mitigating the heterogeneities among diverse feature data and employs a gradient boosting tree model to predict chromatin loops. Experimental evaluations indicate that CHASOS2 outperforms existing methods, particularly in scenarios involving heterogeneous feature data. A case study applying CHASOS2 de novo prediction toolkit on the K562 cell line demonstrates high consistency with ChIA-PET identified chromatin loops, validating the effectiveness of our method and toolkit.