Predicting transcription factor binding sites using DNA shape features based on shared hybrid deep learning architecture

Abstract

The study of transcriptional regulation is still difficult yet fundamental in molecular biology research. Recent research has shown that the double helix structure of nucleotides plays an important role in improving the accuracy and interpretability of transcription factor binding sites (TFBSs). Although several computational methods have been designed to take both DNA sequence and DNA shape features into consideration simultaneously, how to design an efficient model is still an intractable topic. In this paper, we proposed a hybrid convolutional recurrent neural network (CNN/RNN) architecture, CRPTS, to predict TFBSs by combining DNA sequence and DNA shape features. The novelty of our proposed method relies on three critical aspects: (1) the application of a shared hybrid CNN and RNN has the ability to efficiently extract features from large-scale genomic sequences obtained by high-throughput technology; (2) the common patterns were found from DNA sequences and their corresponding DNA shape features; (3) our proposed CRPTS can capture local structural information of DNA sequences without completely relying on DNA shape data. A series of comprehensive experiments on 66 in vitro datasets derived from universal protein binding microarrays (uPBMs) shows that our proposed method CRPTS obviously outperforms the state-of-the-art methods.

DNAffinity: A Machine-Learning Approach to Predict DNA Binding Affinities of Transcription Factors

“…Methods) and comparing it to the other algorithms that had the best (newest) and the worst performance compared to ours: CRPT (27) and DNAShapeR (33) for uPBM data and both DNAShapeR (33) and DeepSELEX (38) for HT-SELEX data (see Supplementary Table 4); confirming that also using this metric the results obtained by our algorithm are consistent.…”

Prediction of mammalian tissue-specific CLOCK-BMAL1 binding to E-box motifs

“…Validating the predictive classifier model on only the DNA shape features did not give a convincing performance metric as compared to the DNA sequence-only model or the sequence + DNA shape model, suggesting that local shape or topology of the DNA near the E-box by itself is not sufficient to predict BMAL1 binding (results not shown). Recent studies have shown that DNA shape computed using core TF binding motifs and flanking sequences improves transcription factor binding prediction in many human TFs (Mathelier et al, 2016; S. Wang et al, 2021; T. Zhou et al, 2015). In another study, DNA topology was highly correlated with the structure and stability of the nucleosome, with topological changes influencing the binding of transcription factors to DNA (Gupta et al, 2009).…”

Computational prediction and characterization of cell-type-specific and shared binding sites

“…As for CNN-plus, (i) we just simply encoded DNA sequences and chromatin accessibility signals, but more appropriate methods for dealing with the inputs need to be further explored, e.g, k -mer embedding representing high-order dependencies of nucleotides (48,49), a bimodal neural network for separately handling DNA sequences and chromatin accessibility signals (50); (ii) we just considered a simple CNN architecture composed of three convolutional layers, but advanced DL-based models also need to be further explored, e.g, hybrid neural networks (51,52), transformer architectures (53,54), since they have been proved to be equipped with stronger feature learning ability. Given the massive data being generated by the ENCODE Consortium and other large-scale efforts, there is an excellent opportunity to learn richer representations to more fully understand cell-type-specific and shared binding activities.…”