CLNN-loop: a deep learning model to predict CTCF-mediated chromatin loops in the different cell lines and CTCF-binding sites (CBS) pair types

Abstract

Motivation Three-dimensional (3D) genome organization is of vital importance in gene regulation and disease mechanisms. Previous studies have shown that CTCF-mediated chromatin loops are crucial to studying the 3D structure of cells. Although various experimental techniques have been developed to detect chromatin loops, they have been found to be time-consuming and costly. Nowadays, various sequence-based computational methods can capture significant features of 3D genome organization and help predict chromatin loops. However, these methods have low performance and poor generalization ability in predicting chromatin loops. Results Here, we propose a novel deep learning model, called CLNN-loop, to predict chromatin loops in different cell lines and CTCF-binding sites (CBS) pair types by fusing multiple sequence-based features. The analysis of a series of examinations based on the datasets in the previous study shows that CLNN-loop has satisfactory performance and is superior to the existing methods in terms of predicting chromatin loops. In addition, we apply the SHAP framework to interpret the predictions of different models, and find that CTCF motif and sequence conservation are important signs of chromatin loops in different cell lines and CBS pair types. The source code of CLNN-loop is freely available at https://github.com/HaoWuLab-Bioinformatics/CLNN-loop and the webserver of CLNN-loop is freely available at http://hwclnn.sdu.edu.cn. Supplementary information Supplementary data are available at Bioinformatics online.

A multi-view latent variable model reveals cellular heterogeneity in complex tissues for paired multimodal single-cell data

“…It is expected to enable more accurate and robust cell type definition and downstream analysis than these sequenced from two modalities. For example, it has the potential to be used for discovering gene regulation mechanism from omics data ( Zhang et al , 2022a , b ).…”

scHiCyclePred: a deep learning framework for predicting cell cycle phases from single-cell Hi-C data using multi-scale interaction information

“…The batch norm layer prevents gradient explosion and disappearance, while the max pooling layer reduces feature dimension, preserves key features, scales back model calculations, avoids overfitting, and enhances generalizability. We use ReLU as the activation function to connect the batch norm layer and max pooling layer 54 , adding nonlinear components to enhance the model's expression capability. The dropout layer effectively prevents model overfitting by discarding some neurons during forward propagation with a predetermined probability.…”

Integrated analysis of ovarian cancer patients from prospective transcription factor activity reveals subtypes of prognostic significance

“…Transcription factors are DNA-binding proteins on specific nucleotide sequences upstream of genes [ [14] , [15] , [16] , [17] , [18] ]. They not only bind to non-coding DNA elements to activate or inhibit gene expression but also promote the transcription of mRNAs and functional non-coding RNAs [ 19 , 20 ].…”