scMeFormer: a transformer-based deep learning model for imputing DNA methylation states in single cells enhances the detection of epigenetic alterations in schizophrenia.

DNA methylation (DNAm), a crucial epigenetic mark, plays a key role in gene regulation, mammalian development, and various human diseases. Single-cell technologies enable the profiling of DNAm states at cytosines within the DNA sequence of individual cells, but they often suffer from limited coverage of CpG sites. In this study, we introduce scMeFormer, a transformer-based deep learning model designed to impute DNAm states for each CpG site in single cells. Through comprehensive evaluations, we demonstrate the superior performance of scMeFormer compared to alternative models across four single-nucleus DNAm datasets generated by distinct technologies. Remarkably, scMeFormer exhibits high-fidelity imputation, even when dealing with significantly reduced coverage, as low as 10% of the original CpG sites. Furthermore, we applied scMeFormer to a single-nucleus DNAm dataset generated from the prefrontal cortex of four schizophrenia patients and four neurotypical controls. This enabled the identification of thousands of differentially methylated regions associated with schizophrenia that would have remained undetectable without imputation and added granularity to our understanding of epigenetic alterations in schizophrenia within specific cell types. Our study highlights the power of deep learning in imputing DNAm states in single cells, and we expect scMeFormer to be a valuable tool for single-cell DNAm studies.

Deep learning predicts DNA methylation regulatory variants in specific brain cell types and enhances fine mapping for brain disorders.

DNA methylation (DNAm) is essential for brain development and function and potentially mediates the effects of genetic risk variants underlying brain disorders. We present INTERACT, a transformer-based deep learning model to predict regulatory variants impacting DNAm levels in specific brain cell types, leveraging existing single-nucleus DNAm data from the human brain. We show that INTERACT accurately predicts cell type-specific DNAm profiles, achieving an average area under the Receiver Operating Characteristic curve of 0.98 across cell types. Furthermore, INTERACT predicts cell type-specific DNAm regulatory variants, which reflect cellular context and enrich the heritability of brain-related traits in relevant cell types. Importantly, we demonstrate that incorporating predicted variant effects and DNAm levels of CpG sites enhances the fine mapping for three brain disorders-schizophrenia, depression, and Alzheimer's disease-and facilitates mapping causal genes to particular cell types. Our study highlights the power of deep learning in identifying cell type-specific regulatory variants, which will enhance our understanding of the genetics of complex traits.

Deep learning predicts DNA methylation regulatory variants in the human brain and elucidates the genetics of psychiatric disorders.

There is growing evidence for the role of DNA methylation (DNAm) quantitative trait loci (mQTLs) in the genetics of complex traits, including psychiatric disorders. However, due to extensive linkage disequilibrium (LD) of the genome, it is challenging to identify causal genetic variations that drive DNAm levels by population-based genetic association studies. This limits the utility of mQTLs for fine-mapping risk loci underlying psychiatric disorders identified by genome-wide association studies (GWAS). Here we present INTERACT, a deep learning model that integrates convolutional neural networks with transformer, to predict effects of genetic variations on DNAm levels at CpG sites in the human brain. We show that INTERACT-derived DNAm regulatory variants are not confounded by LD, are concentrated in regulatory genomic regions in the human brain, and are convergent with mQTL evidence from genetic association analysis. We further demonstrate that predicted DNAm regulatory variants are enriched for heritability of brain-related traits and improve polygenic risk prediction for schizophrenia across diverse ancestry samples. Finally, we applied predicted DNAm regulatory variants for fine-mapping schizophrenia GWAS risk loci to identify potential novel risk genes. Our study shows the power of a deep learning approach to identify functional regulatory variants that may elucidate the genetic basis of complex traits.

Prediction of TF-Binding Site by Inclusion of Higher Order Position Dependencies.

Most proposed methods for TF-binding site (TFBS) predictions only use low order dependencies for predictions due to the lack of efficient methods to extract higher order dependencies. In this work, we first propose a novel method to extract higher order dependencies by applying CNN on histone modification features. We then propose a novel TFBS prediction method, referred to as CNN_TF, by incorporating low order and higher order dependencies. CNN_TF is first evaluated on 13 TFs in the mES cell. Results show that using higher order dependencies outperforms low order dependencies significantly on 11 TFs. This indicates that higher order dependencies are indeed more effective for TFBS predictions than low order dependencies. Further experiments show that using both low order dependencies and higher order dependencies improves performance significantly on 12 TFs, indicating the two dependency types are complementary. To evaluate the influence of cell-types on prediction performances, CNN_TF was applied to five TFs in five cell-types of humans. Even though low order dependencies and higher order dependencies show different contributions in different cell-types, they are always complementary in predictions. When comparing to several state-of-the-art methods, CNN_TF outperforms them by at least 5.3 percent in AUPR.

EL_LSTM: Prediction of DNA-Binding Residue from Protein Sequence by Combining Long Short-Term Memory and Ensemble Learning.

Most past works for DNA-binding residue prediction did not consider the relationships between residues. In this paper, we propose a novel approach for DNA-binding residue prediction, referred to as EL_LSTM, which includes two main components. The first component is the Long Short-Term Memory (LSTM), which learns pairwise relationships between residues through a bi-gram model and then learns feature vectors for all residues. The second component is an ensemble learning based classifier introduced to tackle the data imbalance problem in binding residue predictions. We use a variant of the bagging strategy in ensemble learning to achieve balanced samples. Evaluations on PDNA-224 and DBP-123 show that adding feature relationships performs better than classifiers without feature relationships by at least 0.028 on MCC, 1.18 percent on ST and 0.012 on AUC. This indicates the usefulness of feature relationships for DNA-binding residue predictions. Evaluation on using ensemble learning indicates that the improvement can reach at least 0.021 on MCC, 1.32 percent on ST, and 0.018 on AUC compared to the use of a single LSTM classifier. Comparisons with the state-of-the-art predictors show that our proposed EL_LSTM outperforms them significantly. Further feature analysis validates the effectiveness of LSTM for the prediction of DNA-binding residues.

Cross-Cell-Type Prediction of TF-Binding Site by Integrating Convolutional Neural Network and Adversarial Network.

Transcription factor binding sites (TFBSs) play an important role in gene expression regulation. Many computational methods for TFBS prediction need sufficient labeled data. However, many transcription factors (TFs) lack labeled data in cell types. We propose a novel method, referred to as DANN_TF, for TFBS prediction. DANN_TF consists of a feature extractor, a label predictor, and a domain classifier. The feature extractor and the domain classifier constitute an Adversarial Network, which ensures that learned features are common features across different cell types. DANN_TF is evaluated on five TFs in five cell types with a total of 25 cell-type TF pairs and compared to a baseline method which does not use Adversarial Network. For both data augmentation and cross-cell-type prediction, DANN_TF performs better than the baseline method on most cell-type TF pairs. DANN_TF is further evaluated by an additional 13 TFs in the five cell types with a total of 65 cell-type TF pairs. Results show that DANN_TF achieves significantly higher AUC than the baseline method on 96.9% pairs of the 65 cell-type TF pairs. This is a strong indication that DANN_TF can indeed learn common features for cross-cell-type TFBS prediction.

MTTFsite: cross-cell type TF binding site prediction by using multi-task learning.

MOTIVATION: The prediction of transcription factor binding sites (TFBSs) is crucial for gene expression analysis. Supervised learning approaches for TFBS predictions require large amounts of labeled data. However, many TFs of certain cell types either do not have sufficient labeled data or do not have any labeled data. RESULTS: In this paper, a multi-task learning framework (called MTTFsite) is proposed to address the lack of labeled data problem by leveraging on labeled data available in cross-cell types. The proposed MTTFsite contains a shared CNN to learn common features for all cell types and a private CNN for each cell type to learn private features. The common features are aimed to help predicting TFBSs for all cell types especially those cell types that lack labeled data. MTTFsite is evaluated on 241 cell type TF pairs and compared with a baseline method without using any multi-task learning model and a fully shared multi-task model that uses only a shared CNN and do not use private CNNs. For cell types with insufficient labeled data, results show that MTTFsite performs better than the baseline method and the fully shared model on more than 89% pairs. For cell types without any labeled data, MTTFsite outperforms the baseline method and the fully shared model by more than 80 and 93% pairs, respectively. A novel gene expression prediction method (called TFChrome) using both MTTFsite and histone modification features is also presented. Results show that TFBSs predicted by MTTFsite alone can achieve good performance. When MTTFsite is combined with histone modification features, a significant 5.7% performance improvement is obtained. AVAILABILITY AND IMPLEMENTATION: The resource and executable code are freely available at http://hlt.hitsz.edu.cn/MTTFsite/ and http://www.hitsz-hlt.com:8080/MTTFsite/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

CNNH_PSS: protein 8-class secondary structure prediction by convolutional neural network with highway.

BACKGROUND: Protein secondary structure is the three dimensional form of local segments of proteins and its prediction is an important problem in protein tertiary structure prediction. Developing computational approaches for protein secondary structure prediction is becoming increasingly urgent. RESULTS: We present a novel deep learning based model, referred to as CNNH_PSS, by using multi-scale CNN with highway. In CNNH_PSS, any two neighbor convolutional layers have a highway to deliver information from current layer to the output of the next one to keep local contexts. As lower layers extract local context while higher layers extract long-range interdependencies, the highways between neighbor layers allow CNNH_PSS to have ability to extract both local contexts and long-range interdependencies. We evaluate CNNH_PSS on two commonly used datasets: CB6133 and CB513. CNNH_PSS outperforms the multi-scale CNN without highway by at least 0.010 Q8 accuracy and also performs better than CNF, DeepCNF and SSpro8, which cannot extract long-range interdependencies, by at least 0.020 Q8 accuracy, demonstrating that both local contexts and long-range interdependencies are indeed useful for prediction. Furthermore, CNNH_PSS also performs better than GSM and DCRNN which need extra complex model to extract long-range interdependencies. It demonstrates that CNNH_PSS not only cost less computer resource, but also achieves better predicting performance. CONCLUSION: CNNH_PSS have ability to extracts both local contexts and long-range interdependencies by combing multi-scale CNN and highway network. The evaluations on common datasets and comparisons with state-of-the-art methods indicate that CNNH_PSS is an useful and efficient tool for protein secondary structure prediction.

EL_PSSM-RT: DNA-binding residue prediction by integrating ensemble learning with PSSM Relation Transformation.

BACKGROUND: Prediction of DNA-binding residue is important for understanding the protein-DNA recognition mechanism. Many computational methods have been proposed for the prediction, but most of them do not consider the relationships of evolutionary information between residues. RESULTS: In this paper, we first propose a novel residue encoding method, referred to as the Position Specific Score Matrix (PSSM) Relation Transformation (PSSM-RT), to encode residues by utilizing the relationships of evolutionary information between residues. PDNA-62 and PDNA-224 are used to evaluate PSSM-RT and two existing PSSM encoding methods by five-fold cross-validation. Performance evaluations indicate that PSSM-RT is more effective than previous methods. This validates the point that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction. An ensemble learning classifier (EL_PSSM-RT) is also proposed by combining ensemble learning model and PSSM-RT to better handle the imbalance between binding and non-binding residues in datasets. EL_PSSM-RT is evaluated by five-fold cross-validation using PDNA-62 and PDNA-224 as well as two independent datasets TS-72 and TS-61. Performance comparisons with existing predictors on the four datasets demonstrate that EL_PSSM-RT is the best-performing method among all the predicting methods with improvement between 0.02-0.07 for MCC, 4.18-21.47% for ST and 0.013-0.131 for AUC. Furthermore, we analyze the importance of the pair-relationships extracted by PSSM-RT and the results validates the usefulness of PSSM-RT for encoding DNA-binding residues. CONCLUSIONS: We propose a novel prediction method for the prediction of DNA-binding residue with the inclusion of relationship of evolutionary information and ensemble learning. Performance evaluation shows that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction and ensemble learning can be used to address the data imbalance issue between binding and non-binding residues. A web service of EL_PSSM-RT ( http://hlt.hitsz.edu.cn:8080/PSSM-RT_SVM/ ) is provided for free access to the biological research community.

PDNAsite: Identification of DNA-binding Site from Protein Sequence by Incorporating Spatial and Sequence Context.

Protein-DNA interactions are involved in many fundamental biological processes essential for cellular function. Most of the existing computational approaches employed only the sequence context of the target residue for its prediction. In the present study, for each target residue, we applied both the spatial context and the sequence context to construct the feature space. Subsequently, Latent Semantic Analysis (LSA) was applied to remove the redundancies in the feature space. Finally, a predictor (PDNAsite) was developed through the integration of the support vector machines (SVM) classifier and ensemble learning. Results on the PDNA-62 and the PDNA-224 datasets demonstrate that features extracted from spatial context provide more information than those from sequence context and the combination of them gives more performance gain. An analysis of the number of binding sites in the spatial context of the target site indicates that the interactions between binding sites next to each other are important for protein-DNA recognition and their binding ability. The comparison between our proposed PDNAsite method and the existing methods indicate that PDNAsite outperforms most of the existing methods and is a useful tool for DNA-binding site identification. A web-server of our predictor (http://hlt.hitsz.edu.cn:8080/PDNAsite/) is made available for free public accessible to the biological research community.

Identifying DNA-binding proteins by combining support vector machine and PSSM distance transformation.

BACKGROUND: DNA-binding proteins play a pivotal role in various intra- and extra-cellular activities ranging from DNA replication to gene expression control. Identification of DNA-binding proteins is one of the major challenges in the field of genome annotation. There have been several computational methods proposed in the literature to deal with the DNA-binding protein identification. However, most of them can't provide an invaluable knowledge base for our understanding of DNA-protein interactions. RESULTS: We firstly presented a new protein sequence encoding method called PSSM Distance Transformation, and then constructed a DNA-binding protein identification method (SVM-PSSM-DT) by combining PSSM Distance Transformation with support vector machine (SVM). First, the PSSM profiles are generated by using the PSI-BLAST program to search the non-redundant (NR) database. Next, the PSSM profiles are transformed into uniform numeric representations appropriately by distance transformation scheme. Lastly, the resulting uniform numeric representations are inputted into a SVM classifier for prediction. Thus whether a sequence can bind to DNA or not can be determined. In benchmark test on 525 DNA-binding and 550 non DNA-binding proteins using jackknife validation, the present model achieved an ACC of 79.96%, MCC of 0.622 and AUC of 86.50%. This performance is considerably better than most of the existing state-of-the-art predictive methods. When tested on a recently constructed independent dataset PDB186, SVM-PSSM-DT also achieved the best performance with ACC of 80.00%, MCC of 0.647 and AUC of 87.40%, and outperformed some existing state-of-the-art methods. CONCLUSIONS: The experiment results demonstrate that PSSM Distance Transformation is an available protein sequence encoding method and SVM-PSSM-DT is a useful tool for identifying the DNA-binding proteins. A user-friendly web-server of SVM-PSSM-DT was constructed, which is freely accessible to the public at the web-site on http://bioinformatics.hitsz.edu.cn/PSSM-DT/.

PseDNA-Pro: DNA-Binding Protein Identification by Combining Chou's PseAAC and Physicochemical Distance Transformation.

Identification of DNA-binding proteins is an important problem in biomedical research as DNA-binding proteins are crucial for various cellular processes. Currently, the machine learning methods achieve the-state-of-the-art performance with different features. A key step to improve the performance of these methods is to find a suitable representation of proteins. In this study, we proposed a feature vector composed of three kinds of sequence-based features, including overall amino acid composition, pseudo amino acid composition (PseAAC) proposed by Chou and physicochemical distance transformation. These features not only consider the sequence composition of proteins, but also incorporate the sequence-order information of amino acids in proteins. The feature vectors were fed into Support Vector Machine (SVM) for DNA-binding protein identification. The proposed method is called PseDNA-Pro. Experiments on stringent benchmark datasets and independent test datasets by using the Jackknife test showed that PseDNA-Pro can achieve an accuracy of higher than 80 %, outperforming several state-of-the-art methods, including DNAbinder, DNA-Prot, and iDNA-Prot. These results indicate that the combination of various features for DNA-binding protein prediction is a suitable approach, and the sequence-order information among residues in proteins is relative for discrimination. For practical applications, a web-server of PseDNA-Pro was established, which is available from http://bioinformatics.hitsz.edu.cn/PseDNA-Pro/.

Identification of DNA-binding proteins by incorporating evolutionary information into pseudo amino acid composition via the top-n-gram approach.

DNA-binding proteins are crucial for various cellular processes and hence have become an important target for both basic research and drug development. With the avalanche of protein sequences generated in the postgenomic age, it is highly desired to establish an automated method for rapidly and accurately identifying DNA-binding proteins based on their sequence information alone. Owing to the fact that all biological species have developed beginning from a very limited number of ancestral species, it is important to take into account the evolutionary information in developing such a high-throughput tool. In view of this, a new predictor was proposed by incorporating the evolutionary information into the general form of pseudo amino acid composition via the top-n-gram approach. It was observed by comparing the new predictor with the existing methods via both jackknife test and independent data-set test that the new predictor outperformed its counterparts. It is anticipated that the new predictor may become a useful vehicle for identifying DNA-binding proteins. It has not escaped our notice that the novel approach to extract evolutionary information into the formulation of statistical samples can be used to identify many other protein attributes as well.

iDNA-Prot|dis: identifying DNA-binding proteins by incorporating amino acid distance-pairs and reduced alphabet profile into the general pseudo amino acid composition.

Playing crucial roles in various cellular processes, such as recognition of specific nucleotide sequences, regulation of transcription, and regulation of gene expression, DNA-binding proteins are essential ingredients for both eukaryotic and prokaryotic proteomes. With the avalanche of protein sequences generated in the postgenomic age, it is a critical challenge to develop automated methods for accurate and rapidly identifying DNA-binding proteins based on their sequence information alone. Here, a novel predictor, called "iDNA-Prot|dis", was established by incorporating the amino acid distance-pair coupling information and the amino acid reduced alphabet profile into the general pseudo amino acid composition (PseAAC) vector. The former can capture the characteristics of DNA-binding proteins so as to enhance its prediction quality, while the latter can reduce the dimension of PseAAC vector so as to speed up its prediction process. It was observed by the rigorous jackknife and independent dataset tests that the new predictor outperformed the existing predictors for the same purpose. As a user-friendly web-server, iDNA-Prot|dis is accessible to the public at http://bioinformatics.hitsz.edu.cn/iDNA-Prot_dis/. Moreover, for the convenience of the vast majority of experimental scientists, a step-by-step protocol guide is provided on how to use the web-server to get their desired results without the need to follow the complicated mathematic equations that are presented in this paper just for the integrity of its developing process. It is anticipated that the iDNA-Prot|dis predictor may become a useful high throughput tool for large-scale analysis of DNA-binding proteins, or at the very least, play a complementary role to the existing predictors in this regard.

enDNA-Prot: identification of DNA-binding proteins by applying ensemble learning.

DNA-binding proteins are crucial for various cellular processes, such as recognition of specific nucleotide, regulation of transcription, and regulation of gene expression. Developing an effective model for identifying DNA-binding proteins is an urgent research problem. Up to now, many methods have been proposed, but most of them focus on only one classifier and cannot make full use of the large number of negative samples to improve predicting performance. This study proposed a predictor called enDNA-Prot for DNA-binding protein identification by employing the ensemble learning technique. Experiential results showed that enDNA-Prot was comparable with DNA-Prot and outperformed DNAbinder and iDNA-Prot with performance improvement in the range of 3.97-9.52% in ACC and 0.08-0.19 in MCC. Furthermore, when the benchmark dataset was expanded with negative samples, the performance of enDNA-Prot outperformed the three existing methods by 2.83-16.63% in terms of ACC and 0.02-0.16 in terms of MCC. It indicated that enDNA-Prot is an effective method for DNA-binding protein identification and expanding training dataset with negative samples can improve its performance. For the convenience of the vast majority of experimental scientists, we developed a user-friendly web-server for enDNA-Prot which is freely accessible to the public.