DNA Shape Features Research Articles

MLSNet: a deep learning model for predicting transcription factor binding sites.

Accurate prediction of transcription factor binding sites (TFBSs) is essential for understanding gene regulation mechanisms and the etiology of diseases. Despite numerous advances in deep learning for predicting TFBSs, their performance can still be enhanced. In this study, we propose MLSNet, a novel deep learning architecture designed specifically to predict TFBSs. MLSNet innovatively integrates multisize convolutional fusion with long short-term memory (LSTM) networks to effectively capture DNA-sparse higher-order sequence features. Further, MLSNet incorporates super token attention and Bi-LSTM to systematically extract and integrate higher-order DNA shape features. Experimental results on 165 ChIP-seq (chromatin immunoprecipitation followed by sequencing) datasets indicate that MLSNet consistently outperforms several state-of-the-art algorithms in the prediction of TFBSs. Specifically, MLSNet reports average metrics: 0.8306 for ACC, 0.8992 for AUROC, and 0.9035 for AUPRC, surpassing the second-best methods by 1.82%, 1.68%, and 1.54%, respectively. This research delineates the effectiveness of combining multi-size convolutional layers with LSTM and DNA shape-based features in enhancing predictive accuracy. Moreover, this study comprehensively assesses the variability in model performance across different cell lines and transcription factors. The source code of MLSNet is available at https://github.com/minghaidea/MLSNet.

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.

DNA shape features improve prediction of CRISPR/Cas9 activity

The CRISPR/Cas9 genome editing technology has transformed basic and translational research in biology and medicine. However, the advances are hindered by off-target effects and a paucity in the knowledge of the mechanism of the Cas9 protein. Machine learning models have been proposed for the prediction of Cas9 activity at unintended sites, yet feature engineering plays a major role in the outcome of the predictors. This study evaluates the improvement in the performance of similar predictors upon inclusion of epigenetic and DNA shape feature groups in the conventionally used sequence-based Cas9 target and off-target datasets. The approach involved the utilization of neural networks trained on a diverse range of parameters, allowing us to systematically assess the performance increase for the meticulously designed datasets- (i) sequence only, (ii) sequence and epigenetic features, and (iii) sequence, epigenetic and DNA shape feature datasets.The addition of DNA shape information significantly improved predictive performance, evaluated by Akaike and Bayesian information criteria. The evaluation of individual feature importance by permutation and LIME-based methods also indicates that not only sequence features like mismatches and nucleotide composition, but also base pairing parameters like opening and stretch, that are indicative of distortion in the DNA-RNA hybrid in the presence of mismatches, influence model outcomes.

Discovering DNA shape motifs with multiple DNA shape features: generalization, methods, and validation.

DNA motifs are crucial patterns in gene regulation. DNA-binding proteins (DBPs), including transcription factors, can bind to specific DNA motifs to regulate gene expression and other cellular activities. Past studies suggest that DNA shape features could be subtly involved in DNA-DBP interactions. Therefore, the shape motif annotations based on intrinsic DNA topology can deepen theunderstanding of DNA-DBP binding. Nevertheless, high-throughput tools for DNA shape motif discovery that incorporate multiple features altogether remain insufficient. To address it, we propose a series of methods to discover non-redundant DNA shape motifs with the generalization to multiple motifs inmultiple shape features. Specifically, an existingGibbs sampling methodis generalized to multiple DNA motif discovery with multiple shape features. Meanwhile, an expectation-maximization (EM) method and a hybrid method coupling EM with Gibbs sampling are proposed anddeveloped with promisingperformance, convergence capability, and efficiency. The discovered DNA shape motif instances reveal insights intolow-signal ChIP-seq peak summits, complementing the existing sequence motif discovery works. Additionally, our modelling captures the potential interplays across multiple DNA shape features. We provide a valuable platform of tools for DNA shape motif discovery. An R package is built for open accessibility and long-lasting impact: https://zenodo.org/doi/10.5281/zenodo.10558980.

Structural and dynamical aspect of DNA motif sequence specific binding of AP-1 transcription factor.

Activator protein-1 (AP-1) comprises one of the largest and most evolutionary conserved families of ubiquitous eukaryotic transcription factors that act as a pioneer factor. Diversity in DNA binding interaction of AP-1 through a conserved basic-zipper (bZIP) domain directs in-depth understanding of how AP-1 achieves its DNA binding selectivity and consequently gene regulation specificity. Here, we address the structural and dynamical aspects of the DNA target recognition process of AP-1 using microsecond-long atomistic simulations based on the structure of the human AP-1 FosB/JunD bZIP-DNA complex. Our results show the unique role of DNA shape features in selective base specific interactions, characteristic ion population, and solvation properties of DNA grooves to form the motif sequence specific AP-1-DNA complex. The TpG step at the two terminals of the AP-1 site plays an important role in the structural adjustment of DNA by modifying the helical twist in the AP-1 bound state. We addressed the role of intrinsic motion of the bZIP domain in terms of opening and closing gripper motions of DNA binding helices, in target site recognition and binding of AP-1 factors. Our observations suggest that binding to the cognate motif in DNA is mainly accompanied with the precise adjustment of closing gripper motion of DNA binding helices of the bZIP domain.

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.

Protein coding regions prediction by fusing DNA shape features

Exons crucial for coding are often hidden within introns, and the two tend to vary greatly in length, which results in deep learning-based protein coding region prediction methods often performing poorly when applied to more structurally complex biological genomes. DNA shape information also plays a role in revealing the underlying logic of gene expression, yet current methods ignore the influence of DNA shape features when distinguishing coding and non-coding regions. We propose a method to predict protein-coding regions using the CNNS-BRNN model, which incorporates DNA shape features and improves the model's ability to distinguish between intronic and exonic features. We use a fusion coding technique that combines DNA shape features and traditional sequence features. Experiments show that this method outperforms the baseline method in metrics such as AUC and F1 by 2.3% and 5.3%, respectively, and the fusion coding method that introduces DNA shape features has a significant improvement in model performance.

Incorporating Sequence-Dependent DNA Shape and Dynamics into Transcriptome Data Analysis.

Differentially expressed genes in a cellular context may be co-regulated by the same transcription factor. However, in the absence of a concurrent transcription factor binding data, such interactions are difficult to detect, especially at the single cell expression level. Motif enrichments in such genes can be used to gain insight into differential expressions caused by the shared upstream TFs. However, it is now established that many genes are co-regulated by the same TF due to a shared DNA shape or sequence-dependent conformational dynamics instead of sequence motif. In this work, we demonstrate how, starting from a gene expression data, such DNA shape and dynamics signatures can be potentially detected using publicly available tools, including DynaSeq, developed in our group for predicting the sequence-dependent components of these DNA shapefeatures.

Deep flanking sequence engineering for efficient promoter design using DeepSEED

Designing promoters with desirable properties is essential in synthetic biology. Human experts are skilled at identifying strong explicit patterns in small samples, while deep learning models excel at detecting implicit weak patterns in large datasets. Biologists have described the sequence patterns of promoters via transcription factor binding sites (TFBSs). However, the flanking sequences of cis-regulatory elements, have long been overlooked and often arbitrarily decided in promoter design. To address this limitation, we introduce DeepSEED, an AI-aided framework that efficiently designs synthetic promoters by combining expert knowledge with deep learning techniques. DeepSEED has demonstrated success in improving the properties of Escherichia coli constitutive, IPTG-inducible, and mammalian cell doxycycline (Dox)-inducible promoters. Furthermore, our results show that DeepSEED captures the implicit features in flanking sequences, such as k-mer frequencies and DNA shape features, which are crucial for determining promoter properties.

Structural underpinnings of mutation rate variations in the human genome.

Single nucleotide mutation rates have critical implications for human evolution and genetic diseases. Importantly, the rates vary substantially across the genome and the principles underlying such variations remain poorly understood. A recent model explained much of this variation by considering higher-order nucleotide interactions in the 7-mer sequence context around mutated nucleotides. This model's success implicates a connection between DNA shape and mutation rates. DNA shape, i.e. structural properties like helical twist and tilt, is known to capture interactions between nucleotides within a local context. Thus, we hypothesized that changes in DNA shape features at and around mutated positions can explain mutation rate variations in the human genome. Indeed, DNA shape-based models of mutation rates showed similar or improved performance over current nucleotide sequence-based models. These models accurately characterized mutation hotspots in the human genome and revealed the shape features whose interactions underlie mutation rate variations. DNA shape also impacts mutation rates within putative functional regions like transcription factor binding sites where we find a strong association between DNA shape and position-specific mutation rates. This work demonstrates the structural underpinnings of nucleotide mutations in the human genome and lays the groundwork for future models of genetic variations to incorporate DNA shape.

DeepSTF: predicting transcription factor binding sites by interpretable deep neural networks combining sequence and shape.

Precise targeting of transcription factor binding sites (TFBSs) is essential to comprehending transcriptional regulatory processes and investigating cellular function. Although several deep learning algorithms have been created to predict TFBSs, the models' intrinsic mechanisms and prediction results are difficult to explain. There is still room for improvement in prediction performance. We present DeepSTF, a unique deep-learning architecture for predicting TFBSs by integrating DNA sequence and shape profiles. We use the improved transformer encoder structure for the first time in the TFBSs prediction approach. DeepSTF extracts DNA higher-order sequence features using stacked convolutional neural networks(CNNs), whereas rich DNA shape profiles are extracted by combining improved transformer encoder structure and bidirectional long short-term memory(Bi-LSTM), and, finally, the derived higher-order sequence features and representative shape profiles are integrated into the channel dimension to achieve accurate TFBSs prediction. Experiments on 165 ENCODE chromatin immunoprecipitation sequencing (ChIP-seq) datasets show that DeepSTF considerably outperforms several state-of-the-art algorithms in predicting TFBSs, and we explain the usefulness of the transformer encoder structure and the combined strategy using sequence features and shape profiles in capturing multiple dependencies and learning essential features. In addition, this paper examines the significance of DNA shape features predicting TFBSs. The source code of DeepSTF is available at https://github.com/YuBinLab-QUST/DeepSTF/.

Sequence-Specific Structural Features and Solvation Properties of Transcription Factor Binding DNA Motifs: Insights from Molecular Dynamics Simulation.

Sequence-specific recognition of transcription factor (TF) binding motifs in the target site of DNA over the vast amount of non-target DNA is of primary importance for the transcriptional regulation of gene expression by the TFs. Binding of TFs to the target site of DNA relies not only on the direct contact formation but also on the structural and conformational features of DNA. Recognition of DNA structural features or shape readout by proteins is an important factor in the context of TF-DNA interaction. Based on the atomistic molecular simulation, here we report the sequence-dependent unique structural features, solvation, and ion-binding properties of biologically relevant AT- and GC-rich human TF binding motifs in DNA. Counterion and water distribution around the motif is found to be sensitive to the motif sequence, which is accompanied with the DNA shape features. The motif sequence affects the electrostatic potential along the grooves, and cytosine methylation alters the DNA shape features. Characteristic solvation properties of TF binding motif DNA fragments infer that an ionic environment and hydration influences are essential to describe TF-DNA interactions.

A framework for mutational signature analysis based on DNA shape parameters.

The mutation risk of a DNA locus depends on its oligonucleotide context. In turn, mutability of oligonucleotides varies across individuals, due to exposure to mutagenic agents or due to variable efficiency and/or accuracy of DNA repair. Such variability is captured by mutational signatures, a mathematical construct obtained by a deconvolution of mutation frequency spectra across individuals. There is a need to enhance methods for inferring mutational signatures to make better use of sparse mutation data (e.g., resulting from exome sequencing of cancers), to facilitate insight into underlying biological mechanisms, and to provide more accurate mutation rate baselines for inferring positive and negative selection. We propose a conceptualization of mutational signatures that represents oligonucleotides via descriptors of DNA conformation: base pair, base pair step, and minor groove width parameters. We demonstrate how such DNA structural parameters can accurately predict mutation occurrence due to DNA repair failures or due to exposure to diverse mutagens such as radiation, chemical exposure, and the APOBEC cytosine deaminase enzymes. Furthermore, the mutation frequency of DNA oligomers classed by structural features can accurately capture systematic variability in mutagenesis of >1,000 tumors originating from diverse human tissues. A nonnegative matrix factorization was applied to mutation spectra stratified by DNA structural features, thereby extracting novel mutational signatures. Moreover, many of the known trinucleotide signatures were associated with an additional spectrum in the DNA structural descriptor space, which may aid interpretation and provide mechanistic insight. Overall, we suggest that the power of DNA sequence motif-based mutational signature analysis can be enhanced by drawing on DNA shape features.

Local DNA shape is a general principle of transcription factor binding specificity in Arabidopsis thaliana

Understanding gene expression will require understanding where regulatory factors bind genomic DNA. The frequently used sequence-based motifs of protein-DNA binding are not predictive, since a genome contains many more binding sites than are actually bound and transcription factors of the same family share similar DNA-binding motifs. Traditionally, these motifs only depict sequence but neglect DNA shape. Since shape may contribute non-linearly and combinational to binding, machine learning approaches ought to be able to better predict transcription factor binding. Here we show that a random forest machine learning approach, which incorporates the 3D-shape of DNA, enhances binding prediction for all 216 tested Arabidopsis thaliana transcription factors and improves the resolution of differential binding by transcription factor family members which share the same binding motif. We observed that DNA shape features were individually weighted for each transcription factor, even if they shared the same binding sequence.

Resolving diverse protein-DNA footprints from exonuclease-based ChIP experiments.

MotivationHigh-throughput chromatin immunoprecipitation (ChIP) sequencing-based assays capture genomic regions associated with the profiled transcription factor (TF). ChIP-exo is a modified protocol, which uses lambda exonuclease to digest DNA close to the TF-DNA complex, in order to improve on the positional resolution of the TF-DNA contact. Because the digestion occurs in the 5–3 orientation, the protocol produces directional footprints close to the complex, on both sides of the double stranded DNA. Like all ChIP-based methods, ChIP-exo reports a mixture of different regions associated with the TF: those bound directly to the TF as well as via intermediaries. However, the distribution of footprints are likely to be indicative of the complex forming at the DNA.ResultsWe present ExoDiversity, which uses a model-based framework to learn a joint distribution over footprints and motifs, thus resolving the mixture of ChIP-exo footprints into diverse binding modes. It uses no prior motif or TF information and automatically learns the number of different modes from the data. We show its application on a wide range of TFs and organisms/cell-types. Because its goal is to explain the complete set of reported regions, it is able to identify co-factor TF motifs that appear in a small fraction of the dataset. Further, ExoDiversity discovers small nucleotide variations within and outside canonical motifs, which co-occur with variations in footprints, suggesting that the TF-DNA structural configuration at those regions is likely to be different. Finally, we show that detected modes have specific DNA shape features and conservation signals, giving insights into the structure and function of the putative TF-DNA complexes.Availability and implementationThe code for ExoDiversity is available on https://github.com/NarlikarLab/exoDIVERSITY.Supplementary information Supplementary data are available at Bioinformatics online.

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

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.

Transcription Factor Binding Affinities and DNA Shape Readout.

SummaryAn essential event in gene regulation is the binding of a transcription factor (TF) to its target DNA. Models considering the interactions between the TF and the DNA geometry proved to be successful approaches to describe this binding event, while conserving data interpretability. However, a direct characterization of the DNA shape contribution to binding is still missing due to the lack of accurate and large-scale binding affinity data. Here, we use a binding assay we recently established to measure with high sensitivity the binding specificities of 13 Drosophila TFs, including dinucleotide dependencies to capture non-independent amino acid-base interactions. Correlating the binding affinities with all DNA shape features, we find that shape readout is widely used by these factors. A shape readout/TF-DNA complex structure analysis validates our approach while providing biological insights such as positively charged or highly polar amino acids often contact nucleotides that exhibit strong shape readout.

Alternative Activation of Macrophages Is Accompanied by Chromatin Remodeling Associated with Lineage-Dependent DNA Shape Features Flanking PU.1 Motifs.

IL-4 activates macrophages to adopt distinct phenotypes associated with clearance of helminth infections and tissue repair, but the phenotype depends on the cellular lineage of these macrophages. The molecular basis of chromatin remodeling in response to IL-4 stimulation in tissue-resident and monocyte-derived macrophages is not understood. In this study, we find that IL-4 activation of different lineages of peritoneal macrophages in mice is accompanied by lineage-specific chromatin remodeling in regions enriched with binding motifs of the pioneer transcription factor PU.1. PU.1 motif is similarly associated with both tissue-resident and monocyte-derived IL-4-induced accessible regions but has different lineage-specific DNA shape features and predicted cofactors. Mutation studies based on natural genetic variation between C57BL/6 and BALB/c mouse strains indicate that accessibility of these IL-4-induced regions can be regulated through differences in DNA shape without direct disruption of PU.1 motifs. We propose a model whereby DNA shape features of stimulation-dependent genomic elements contribute to differences in the accessible chromatin landscape of alternatively activated macrophages on different genetic backgrounds that may contribute to phenotypic variations in immune responses.

TFBSshape: an expanded motif database for DNA shape features of transcription factor binding sites.

TFBSshape (https://tfbsshape.usc.edu) is a motif database for analyzing structural profiles of transcription factor binding sites (TFBSs). The main rationale for this database is to be able to derive mechanistic insights in protein–DNA readout modes from sequencing data without available structures. We extended the quantity and dimensionality of TFBSshape, from mostly in vitro to in vivo binding and from unmethylated to methylated DNA. This new release of TFBSshape improves its functionality and launches a responsive and user-friendly web interface for easy access to the data. The current expansion includes new entries from the most recent collections of transcription factors (TFs) from the JASPAR and UniPROBE databases, methylated TFBSs derived from in vitro high-throughput EpiSELEX-seq binding assays and in vivo methylated TFBSs from the MeDReaders database. TFBSshape content has increased to 2428 structural profiles for 1900 TFs from 39 different species. The structural profiles for each TFBS entry now include 13 shape features and minor groove electrostatic potential for standard DNA and four shape features for methylated DNA. We improved the flexibility and accuracy for the shape-based alignment of TFBSs and designed new tools to compare methylated and unmethylated structural profiles of TFs and methods to derive DNA shape-preserving nucleotide mutations in TFBSs.

Prediction of regulatory motifs from human Chip-sequencing data using a deep learning framework.

The identification of transcription factor binding sites and cis-regulatory motifs is a frontier whereupon the rules governing protein–DNA binding are being revealed. Here, we developed a new method (DEep Sequence and Shape mOtif or DESSO) for cis-regulatory motif prediction using deep neural networks and the binomial distribution model. DESSO outperformed existing tools, including DeepBind, in predicting motifs in 690 human ENCODE ChIP-sequencing datasets. Furthermore, the deep-learning framework of DESSO expanded motif discovery beyond the state-of-the-art by allowing the identification of known and new protein–protein–DNA tethering interactions in human transcription factors (TFs). Specifically, 61 putative tethering interactions were identified among the 100 TFs expressed in the K562 cell line. In this work, the power of DESSO was further expanded by integrating the detection of DNA shape features. We found that shape information has strong predictive power for TF–DNA binding and provides new putative shape motif information for human TFs. Thus, DESSO improves in the identification and structural analysis of TF binding sites, by integrating the complexities of DNA binding into a deep-learning framework.