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

Deep DNAshape webserver: prediction and real-time visualization of DNA shape considering extended k-mers

Sequence-dependent DNA shape plays an important role in understanding protein-DNA binding mechanisms. High-throughput prediction of DNA shape features has become a valuable tool in the field of protein-DNA recognition, transcription factor-DNA binding specificity, and gene regulation. However, our widely used webserver, DNAshape, relies on statistically summarized pentamer query tables to query DNA shape features. These query tables do not consider flanking regions longer than two base pairs, and acquiring a query table for hexamers or higher-order k-mers is currently still unrealistic due to limitations in achieving sufficient statistical coverage in molecular simulations or structural biology experiments. A recent deep-learning method, Deep DNAshape, can predict DNA shape features at the core of a DNA fragment considering flanking regions of up to seven base pairs, trained on limited simulation data. However, Deep DNAshape is rather complicated to install, and it must run locally compared to the pentamer-based DNAshape webserver, creating a barrier for users. Here, we present the Deep DNAshape webserver, which has the benefits of both methods while being accurate, fast, and accessible to all users. Additional improvements of the webserver include the detection of user input in real time, the ability of interactive visualization tools and different modes of analyses. URL: https://deepdnashape.usc.edu.

MulTFBS: A Spatial-Temporal Network with Multichannels for Predicting Transcription Factor Binding Sites

Revealing the mechanisms that influence transcription factor binding specificity is the key to understanding gene regulation. In previous studies, DNA double helix structure and one-hot embedding have been used successfully to design computational methods for predicting transcription factor binding sites (TFBSs). However, DNA sequence as a kind of biological language, the method of word embedding representation in natural language processing, has not been considered properly in TFBS prediction models. In our work, we integrate different types of features of DNA sequence to design a multichanneled deep learning framework, namely MulTFBS, in which independent one-hot encoding, word embedding encoding, which can incorporate contextual information and extract the global features of the sequences, and double helix three-dimensional structural features have been trained in different channels. To extract sequence high-level information effectively, in our deep learning framework, we select the spatial-temporal network by combining convolutional neural networks and bidirectional long short-term memory networks with attention mechanism. Compared with six state-of-the-art methods on 66 universal protein-binding microarray data sets of different transcription factors, MulTFBS performs best on all data sets in the regression tasks, with the average R2 of 0.698 and the average PCC of 0.833, which are 5.4% and 3.2% higher, respectively, than the suboptimal method CRPTS. In addition, we evaluate the classification performance of MulTFBS for distinguishing bound or unbound regions on TF ChIP-seq data. The results show that our framework also performs well in the TFBS classification tasks.

Predicting Transcription Factor Binding Sites with Deep Learning

Prediction of binding sites for transcription factors is important to understand how the latter regulate gene expression and how this regulation can be modulated for therapeutic purposes. A consistent number of references address this issue with different approaches, Machine Learning being one of the most successful. Nevertheless, we note that many such approaches fail to propose a robust and meaningful method to embed the genetic data under analysis. We try to overcome this problem by proposing a bidirectional transformer-based encoder, empowered by bidirectional long-short term memory layers and with a capsule layer responsible for the final prediction. To evaluate the efficiency of the proposed approach, we use benchmark ChIP-seq datasets of five cell lines available in the ENCODE repository (A549, GM12878, Hep-G2, H1-hESC, and Hela). The results show that the proposed method can predict TFBS within the five different cell lines very well; moreover, cross-cell predictions provide satisfactory results as well. Experiments conducted across cell lines are reinforced by the analysis of five additional lines used only to test the model trained using the others. The results confirm that prediction across cell lines remains very high, allowing an extensive cross-transcription factor analysis to be performed from which several indications of interest for molecular biology may be drawn.

BERT-TFBS: a novel BERT-based model for predicting transcription factor binding sites by transfer learning

Transcription factors (TFs) are proteins essential for regulating genetic transcriptions by binding to transcription factor binding sites (TFBSs) in DNA sequences. Accurate predictions of TFBSs can contribute to the design and construction of metabolic regulatory systems based on TFs. Although various deep-learning algorithms have been developed for predicting TFBSs, the prediction performance needs to be improved. This paper proposes a bidirectional encoder representations from transformers (BERT)-based model, called BERT-TFBS, to predict TFBSs solely based on DNA sequences. The model consists of a pre-trained BERT module (DNABERT-2), a convolutional neural network (CNN) module, a convolutional block attention module (CBAM) and an output module. The BERT-TFBS model utilizes the pre-trained DNABERT-2 module to acquire the complex long-term dependencies in DNA sequences through a transfer learning approach, and applies the CNN module and the CBAM to extract high-order local features. The proposed model is trained and tested based on 165 ENCODE ChIP-seq datasets. We conducted experiments with model variants, cross-cell-line validations and comparisons with other models. The experimental results demonstrate the effectiveness and generalization capability of BERT-TFBS in predicting TFBSs, and they show that the proposed model outperforms other deep-learning models. The source code for BERT-TFBS is available at https://github.com/ZX1998-12/BERT-TFBS.

Predicting DNA structure using a deep learning method

Understanding the mechanisms of protein-DNA binding is critical in comprehending gene regulation. Three-dimensional DNA structure, also described as DNA shape, plays a key role in these mechanisms. In this study, we present a deep learning-based method, Deep DNAshape, that fundamentally changes the current k-mer based high-throughput prediction of DNA shape features by accurately accounting for the influence of extended flanking regions, without the need for extensive molecular simulations or structural biology experiments. By using the Deep DNAshape method, DNA structural features can be predicted for any length and number of DNA sequences in a high-throughput manner, providing an understanding of the effects of flanking regions on DNA structure in a target region of a sequence. The Deep DNAshape method provides access to the influence of distant flanking regions on a region of interest. Our findings reveal that DNA shape readout mechanisms of a core target are quantitatively affected by flanking regions, including extended flanking regions, providing valuable insights into the detailed structural readout mechanisms of protein-DNA binding. Furthermore, when incorporated in machine learning models, the features generated by Deep DNAshape improve the model prediction accuracy. Collectively, Deep DNAshape can serve as versatile and powerful tool for diverse DNA structure-related studies.

Harnessing regulatory networks in Actinobacteria for natural product discovery

Microbes typically live in complex habitats where they need to rapidly adapt to continuously changing growth conditions. To do so, they produce an astonishing array of natural products with diverse structures and functions. Actinobacteria stand out for their prolific production of bioactive molecules, including antibiotics, anticancer agents, antifungals, and immunosuppressants. Attention has been directed especially towards the identification of the compounds they produce and the mining of the large diversity of biosynthetic gene clusters (BGCs) in their genomes. However, the current return on investment in random screening for bioactive compounds is low, while it is hard to predict which of the millions of BGCs should be prioritized. Moreover, many of the BGCs for yet undiscovered natural products are silent or cryptic under laboratory growth conditions. To identify ways to prioritize and activate these BGCs, knowledge regarding the way their expression is controlled is crucial. Intricate regulatory networks control global gene expression in Actinobacteria, governed by a staggering number of up to 1000 transcription factors per strain. This review highlights recent advances in experimental and computational methods for characterizing and predicting transcription factor binding sites and their applications to guide natural product discovery. We propose that regulation-guided genome mining approaches will open new avenues toward eliciting the expression of BGCs, as well as prioritizing subsets of BGCs for expression using synthetic biology approaches.

ONE-SENTENCE SUMMARY

This review provides insights into advances in experimental and computational methods aimed at predicting transcription factor binding sites and their applications to guide natural product discovery.

Deep DNAshape: Predicting DNA shape considering extended flanking regions using a deep learning method

Understanding the mechanisms of protein-DNA binding is critical in comprehending gene regulation. Three-dimensional DNA shape plays a key role in these mechanisms. In this study, we present a deep learning-based method, Deep DNAshape, that fundamentally changes the current k -mer based high-throughput prediction of DNA shape features by accurately accounting for the influence of extended flanking regions, without the need for extensive molecular simulations or structural biology experiments. By using the Deep DNAshape method, refined DNA shape features can be predicted for any length and number of DNA sequences in a high-throughput manner, providing a deeper understanding of the effects of flanking regions on DNA shape in a target region of a sequence. Deep DNAshape method provides access to the influence of distant flanking regions on a region of interest. Our findings reveal that DNA shape readout mechanisms of a core target are quantitatively affected by flanking regions, including extended flanking regions, providing valuable insights into the detailed structural readout mechanisms of protein-DNA binding. Furthermore, when incorporated in machine learning models, the features generated by Deep DNAshape improve the model prediction accuracy. Collectively, Deep DNAshape can serve as a versatile and powerful tool for diverse DNA structure-related studies.

A Bayesian approach to estimate MHC-peptide binding threshold

Major histocompatibility complex (MHC)-peptide binding is a critical step in enabling a peptide to serve as an antigen for T-cell recognition. Accurate prediction of this binding can facilitate various applications in immunotherapy. While many existing methods offer good predictive power for the binding affinity of a peptide to a specific MHC, few models attempt to infer the binding threshold that distinguishes binding sequences. These models often rely on experience-based ad hoc criteria, such as 500 or 1000nM. However, different MHCs may have different binding thresholds. As such, there is a need for an automatic, data-driven method to determine an accurate binding threshold. In this study, we proposed a Bayesian model that jointly infers core locations (binding sites), the binding affinity and the binding threshold. Our model provided the posterior distribution of the binding threshold, enabling accurate determination of an appropriate threshold for each MHC. To evaluate the performance of our method under different scenarios, we conducted simulation studies with varying dominant levels of motif distributions and proportions of random sequences. These simulation studies showed desirable estimation accuracy and robustness of our model. Additionally, when applied to real data, our results outperformed commonly used thresholds.

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

The Brain and Muscle ARNTL-Like 1 protein (BMAL1) forms a heterodimer with either Circadian Locomotor Output Cycles Kaput (CLOCK) or Neuronal PAS domain protein 2 (NPAS2) to act as a master regulator of the mammalian circadian clock gene network. The dimer binds to E-box gene regulatory elements on DNA, activating downstream transcription of clock genes. Identification of transcription factor binding sites and genomic features that correlate to DNA binding by BMAL1 is a challenging problem, given that CLOCK-BMAL1 or NPAS2-BMAL1 bind to several distinct binding motifs (CANNTG) on DNA. Using three different types of tissue-specific machine learning models with features based on (1) DNA sequence, (2) DNA sequence plus DNA shape, and (3) DNA sequence and shape plus histone modifications, we developed an interpretable predictive model of genome-wide BMAL1 binding to E-box motifs and dissected the mechanisms underlying BMAL1-DNA binding. Our results indicated that histone modifications, the local shape of the DNA, and the flanking sequence of the E-box motif are sufficient predictive features for BMAL1-DNA binding. Our models also provide mechanistic insights into tissue specificity of DNA binding by BMAL1.

Cooperation of local features and global representations by a dual-branch network for transcription factor binding sites prediction

Interactions between DNA and transcription factors (TFs) play an essential role in understanding transcriptional regulation mechanisms and gene expression. Due to the large accumulation of training data and low expense, deep learning methods have shown huge potential in determining the specificity of TFs-DNA interactions. Convolutional network-based and self-attention network-based methods have been proposed for transcription factor binding sites (TFBSs) prediction. Convolutional operations are efficient to extract local features but easy to ignore global information, while self-attention mechanisms are expert in capturing long-distance dependencies but difficult to pay attention to local feature details. To discover comprehensive features for a given sequence as far as possible, we propose a Dual-branch model combining Self-Attention and Convolution, dubbed as DSAC, which fuses local features and global representations in an interactive way. In terms of features, convolution and self-attention contribute to feature extraction collaboratively, enhancing the representation learning. In terms of structure, a lightweight but efficient architecture of network is designed for the prediction, in particular, the dual-branch structure makes the convolution and the self-attention mechanism can be fully utilized to improve the predictive ability of our model. The experiment results on 165 ChIP-seq datasets show that DSAC obviously outperforms other five deep learning based methods and demonstrate that our model can effectively predict TFBSs based on sequence feature alone. The source code of DSAC is available at https://github.com/YuBinLab-QUST/DSAC/.

Predicting TF Proteins by Incorporating Evolution Information Through PSSM

Transcription factors (TFs) are DNA binding proteins involved in the regulation of gene expression. They exist in all organisms and activate or repress transcription by binding to specific DNA sequences. Traditionally, TFs have been identified by experimental methods that are time-consuming and costly. In recent years, various computational methods have been developed to identify TF to overcome these limitations. However, there is a room for further improvement in the predictive performance of these tools in terms of accuracy. We report here a novel computational tool, TFnet, that provides accurate and comprehensive TF predictions from protein sequences. The accuracy of these predictions is substantially better than the results of the existing TF predictors and methods. Especially, it outperforms comparable methods significantly when sequence similarity to other known sequences in the database drops below 40%. Ablation tests reveal that the high predictive performance stems from innovative ways used in TFnet to derive sequence Position-Specific Scoring Matrix (PSSM) and encode inputs.

LangMoDHS: A deep learning language model for predicting DNase I hypersensitive sites in mouse genome

DNase I hypersensitive sites (DHSs) are a specific genomic region, which is critical to detect or understand cis-regulatory elements. Although there are many methods developed to detect DHSs, there is a big gap in practice. We presented a deep learning-based language model for predicting DHSs, named LangMoDHS. The LangMoDHS mainly comprised the convolutional neural network (CNN), the bi-directional long short-term memory (Bi-LSTM) and the feed-forward attention. The CNN and the Bi-LSTM were stacked in a parallel manner, which was helpful to accumulate multiple-view representations from primary DNA sequences. We conducted 5-fold cross-validations and independent tests over 14 tissues and 4 developmental stages. The empirical experiments showed that the LangMoDHS is competitive with or slightly better than the iDHS-Deep, which is the latest method for predicting DHSs. The empirical experiments also implied substantial contribution of the CNN, Bi-LSTM, and attention to DHSs prediction. We implemented the LangMoDHS as a user-friendly web server which is accessible at http:/www.biolscience.cn/LangMoDHS/. We used indices related to information entropy to explore the sequence motif of DHSs. The analysis provided a certain insight into the DHSs.

Convolution Neural Networks Using Deep Matrix Factorization for Predicting Circrna-Disease Association

CircRNAs have a stable structure, which gives them a higher tolerance to nucleases. Therefore, the properties of circular RNAs are beneficial in disease diagnosis. However, there are few known associations between circRNAs and disease. Biological experiments identify new associations is time-consuming and high-cost. As a result, there is a need of building efficient and achievable computation models to predict potential circRNA-disease associations. In this paper, we design a novel convolution neural networks framework(DMFCNNCD) to learn features from deep matrix factorization to predict circRNA-disease associations. Firstly, we decompose the circRNA-disease association matrix to obtain the original features of the disease and circRNA, and use the mapping module to extract potential nonlinear features. Then, we integrate it with the similarity information to form a training set. Finally, we apply convolution neural networks to predict the unknown association between circRNAs and diseases. The five-fold cross-validation on various experiments shows that our method can predict circRNA-disease association and outperforms state of the art methods.

PlantBind: an attention-based multi-label neural network for predicting plant transcription factor binding sites

Identification of transcription factor binding sites (TFBSs) is essential to understanding of gene regulation. Designing computational models for accurate prediction of TFBSs is crucial because it is not feasible to experimentally assay all transcription factors (TFs) in all sequenced eukaryotic genomes. Although many methods have been proposed for the identification of TFBSs in humans, methods designed for plants are comparatively underdeveloped. Here, we present PlantBind, a method for integrated prediction and interpretation of TFBSs based on DNA sequences and DNA shape profiles. Built on an attention-based multi-label deep learning framework, PlantBind not only simultaneously predicts the potential binding sites of 315 TFs, but also identifies the motifs bound by transcription factors. During the training process, this model revealed a strong similarity among TF family members with respect to target binding sequences. Trans-species prediction performance using four Zea mays TFs demonstrated the suitability of this model for transfer learning. Overall, this study provides an effective solution for identifying plant TFBSs, which will promote greater understanding of transcriptional regulatory mechanisms in plants.

Predicting In-Vitro DNA-Protein Binding With a Spatially Aligned Fusion of Sequence and Shape

Discovery of transcription factor binding sites (TFBSs) is of primary importance for understanding the underlying binding mechanic and gene regulation process. Growing evidence indicates that apart from the primary DNA sequences, DNA shape landscape has a significant influence on transcription factor binding preference. To effectively model the co-influence of sequence and shape features, we emphasize the importance of position information of sequence motif and shape pattern. In this paper, we propose a novel deep learning-based architecture, named hybridShape eDeepCNN, for TFBS prediction which integrates DNA sequence and shape information in a spatially aligned manner. Our model utilizes the power of the multi-layer convolutional neural network and constructs an independent subnetwork to adapt for the distinct data distribution of heterogeneous features. Besides, we explore the usage of continuous embedding vectors as the representation of DNA sequences. Based on the experiments on 20 in-vitro datasets derived from universal protein binding microarrays (uPBMs), we demonstrate the superiority of our proposed method and validate the underlying design logic.

DNAffinity: a machine-learning approach to predict DNA binding affinities of transcription factors

We present a physics-based machine learning approach to predict in vitro transcription factor binding affinities from structural and mechanical DNA properties directly derived from atomistic molecular dynamics simulations. The method is able to predict affinities obtained with techniques as different as uPBM, gcPBM and HT-SELEX with an excellent performance, much better than existing algorithms. Due to its nature, the method can be extended to epigenetic variants, mismatches, mutations, or any non-coding nucleobases. When complemented with chromatin structure information, our in vitro trained method provides also good estimates of in vivo binding sites in yeast.

Deep learning-based transcription factor activity for stratification of breast cancer patients

Transcription factors directly bind to DNA and regulate the expression of the gene, causing epigenetic modification of the DNA. They often mediate epigenetic parameters of transcriptional and posttranscriptional mechanisms, and their expression activities can be used to characterize genomic aberrations in cancer cell. In this study, the activity profile of transcription factors inferred by VIPER algorithm. The autoencoder model was applied for compressing the transcription factor activity profile for obtaining more useful transformed features for stratifying patients into two different breast cancer subtypes. The deep learning-based subtypes exhibited superior prognostic value and yielded better risk-stratification than the transcription factor activity-based method. Importantly, according to transformed features, a deep neural network was constructed to predict the subtypes, and achieved the accuracy of 94.98% and area under the ROC curve of 0.9663, respectively. The proposed subtypes were found to be significantly associated with immune infiltration, tumor immunogenicity and so on. Furthermore, the ceRNA network was constructed for the breast cancer subtypes. Besides, 11 master regulators were found to be associated with patients in cluster 1. Given the robustness performance of our deep learning model over multiple breast cancer cohorts, we expected this model may be useful in the area of prognosis prediction and lead some possibility for personalized medicine in breast cancer patients.

A novel convolution attention model for predicting transcription factor binding sites by combination of sequence and shape

The discovery of putative transcription factor binding sites (TFBSs) is important for understanding the underlying binding mechanism and cellular functions. Recently, many computational methods have been proposed to jointly account for DNA sequence and shape properties in TFBSs prediction. However, these methods fail to fully utilize the latent features derived from both sequence and shape profiles and have limitation in interpretability and knowledge discovery. To this end, we present a novel Deep Convolution Attention network combining Sequence and Shape, dubbed as D-SSCA, for precisely predicting putative TFBSs. Experiments conducted on 165 ENCODE ChIP-seq datasets reveal that D-SSCA significantly outperforms several state-of-the-art methods in predicting TFBSs, and justify the utility of channel attention module for feature refinements. Besides, the thorough analysis about the contribution of five shapes to TFBSs prediction demonstrates that shape features can improve the predictive power for transcription factors-DNA binding. Furthermore, D-SSCA can realize the cross-cell line prediction of TFBSs, indicating the occupancy of common interplay patterns concerning both sequence and shape across various cell lines. The source code of D-SSCA can be found at https://github.com/MoonLord0525/.

Regulatory SNPs: Altered Transcription Factor Binding Sites Implicated in Complex Traits and Diseases

The vast majority of the genetic variants (mainly SNPs) associated with various human traits and diseases map to a noncoding part of the genome and are enriched in its regulatory compartment, suggesting that many causal variants may affect gene expression. The leading mechanism of action of these SNPs consists in the alterations in the transcription factor binding via creation or disruption of transcription factor binding sites (TFBSs) or some change in the affinity of these regulatory proteins to their cognate sites. In this review, we first focus on the history of the discovery of regulatory SNPs (rSNPs) and systematized description of the existing methodical approaches to their study. Then, we brief the recent comprehensive examples of rSNPs studied from the discovery of the changes in the TFBS sequence as a result of a nucleotide substitution to identification of its effect on the target gene expression and, eventually, to phenotype. We also describe state-of-the-art genome-wide approaches to identification of regulatory variants, including both making molecular sense of genome-wide association studies (GWAS) and the alternative approaches the primary goal of which is to determine the functionality of genetic variants. Among these approaches, special attention is paid to expression quantitative trait loci (eQTLs) analysis and the search for allele-specific events in RNA-seq (ASE events) as well as in ChIP-seq, DNase-seq, and ATAC-seq (ASB events) data.