GMFGRN: a matrix factorization and graph neural network approach for gene regulatory network inference.

The recent advances of single-cell RNA sequencing (scRNA-seq) have enabled reliable profiling of gene expression at the single-cell level, providing opportunities for accurate inference of gene regulatory networks (GRNs) on scRNA-seq data. Most methods for inferring GRNs suffer from the inability to eliminate transitive interactions or necessitate expensive computational resources. To address these, we present a novel method, termed GMFGRN, for accurate graph neural network (GNN)-based GRN inference from scRNA-seq data. GMFGRN employs GNN for matrix factorization and learns representative embeddings for genes. For transcription factor-gene pairs, it utilizes the learned embeddings to determine whether they interact with each other. The extensive suite of benchmarking experiments encompassing eight static scRNA-seq datasets alongside several state-of-the-art methods demonstrated mean improvements of 1.9 and 2.5% over the runner-up in area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). In addition, across four time-series datasets, maximum enhancements of 2.4 and 1.3% in AUROC and AUPRC were observed in comparison to the runner-up. Moreover, GMFGRN requires significantly less training time and memory consumption, with time and memory consumed <10% compared to the second-best method. These findings underscore the substantial potential of GMFGRN in the inference of GRNs. It is publicly available at https://github.com/Lishuoyy/GMFGRN.

TripletCell: a deep metric learning framework for accurate annotation of cell types at the single-cell level.

Single-cell RNA sequencing (scRNA-seq) has significantly accelerated the experimental characterization of distinct cell lineages and types in complex tissues and organisms. Cell-type annotation is of great importance in most of the scRNA-seq analysis pipelines. However, manual cell-type annotation heavily relies on the quality of scRNA-seq data and marker genes, and therefore can be laborious and time-consuming. Furthermore, the heterogeneity of scRNA-seq datasets poses another challenge for accurate cell-type annotation, such as the batch effect induced by different scRNA-seq protocols and samples. To overcome these limitations, here we propose a novel pipeline, termed TripletCell, for cross-species, cross-protocol and cross-sample cell-type annotation. We developed a cell embedding and dimension-reduction module for the feature extraction (FE) in TripletCell, namely TripletCell-FE, to leverage the deep metric learning-based algorithm for the relationships between the reference gene expression matrix and the query cells. Our experimental studies on 21 datasets (covering nine scRNA-seq protocols, two species and three tissues) demonstrate that TripletCell outperformed state-of-the-art approaches for cell-type annotation. More importantly, regardless of protocols or species, TripletCell can deliver outstanding and robust performance in annotating different types of cells. TripletCell is freely available at https://github.com/liuyan3056/TripletCell. We believe that TripletCell is a reliable computational tool for accurately annotating various cell types using scRNA-seq data and will be instrumental in assisting the generation of novel biological hypotheses in cell biology.

MAResNet: predicting transcription factor binding sites by combining multi-scale bottom-up and top-down attention and residual network.

Accurate identification of transcription factor binding sites is of great significance in understanding gene expression, biological development and drug design. Although a variety of methods based on deep-learning models and large-scale data have been developed to predict transcription factor binding sites in DNA sequences, there is room for further improvement in prediction performance. In addition, effective interpretation of deep-learning models is greatly desirable. Here we present MAResNet, a new deep-learning method, for predicting transcription factor binding sites on 690 ChIP-seq datasets. More specifically, MAResNet combines the bottom-up and top-down attention mechanisms and a state-of-the-art feed-forward network (ResNet), which is constructed by stacking attention modules that generate attention-aware features. In particular, the multi-scale attention mechanism is utilized at the first stage to extract rich and representative sequence features. We further discuss the attention-aware features learned from different attention modules in accordance with the changes as the layers go deeper. The features learned by MAResNet are also visualized through the TMAP tool to illustrate that the method can extract the unique characteristics of transcription factor binding sites. The performance of MAResNet is extensively tested on 690 test subsets with an average AUC of 0.927, which is higher than that of the current state-of-the-art methods. Overall, this study provides a new and useful framework for the prediction of transcription factor binding sites by combining the funnel attention modules with the residual network.

SAResNet: self-attention residual network for predicting DNA-protein binding.

Knowledge of the specificity of DNA-protein binding is crucial for understanding the mechanisms of gene expression, regulation and gene therapy. In recent years, deep-learning-based methods for predicting DNA-protein binding from sequence data have achieved significant success. Nevertheless, the current state-of-the-art computational methods have some drawbacks associated with the use of limited datasets with insufficient experimental data. To address this, we propose a novel transfer learning-based method, termed SAResNet, which combines the self-attention mechanism and residual network structure. More specifically, the attention-driven module captures the position information of the sequence, while the residual network structure guarantees that the high-level features of the binding site can be extracted. Meanwhile, the pre-training strategy used by SAResNet improves the learning ability of the network and accelerates the convergence speed of the network during transfer learning. The performance of SAResNet is extensively tested on 690 datasets from the ChIP-seq experiments with an average AUC of 92.0%, which is 4.4% higher than that of the best state-of-the-art method currently available. When tested on smaller datasets, the predictive performance is more clearly improved. Overall, we demonstrate that the superior performance of DNA-protein binding prediction on DNA sequences can be achieved by combining the attention mechanism and residual structure, and a novel pipeline is accordingly developed. The proposed methodology is generally applicable and can be used to address any other sequence classification problems.

Improving protein fold recognition using triplet network and ensemble deep learning.

Protein fold recognition is a critical step toward protein structure and function prediction, aiming at providing the most likely fold type of the query protein. In recent years, the development of deep learning (DL) technique has led to massive advances in this important field, and accordingly, the sensitivity of protein fold recognition has been dramatically improved. Most DL-based methods take an intermediate bottleneck layer as the feature representation of proteins with new fold types. However, this strategy is indirect, inefficient and conditional on the hypothesis that the bottleneck layer's representation is assumed as a good representation of proteins with new fold types. To address the above problem, in this work, we develop a new computational framework by combining triplet network and ensemble DL. We first train a DL-based model, termed FoldNet, which employs triplet loss to train the deep convolutional network. FoldNet directly optimizes the protein fold embedding itself, making the proteins with the same fold types be closer to each other than those with different fold types in the new protein embedding space. Subsequently, using the trained FoldNet, we implement a new residue-residue contact-assisted predictor, termed FoldTR, which improves protein fold recognition. Furthermore, we propose a new ensemble DL method, termed FSD_XGBoost, which combines protein fold embedding with the other two discriminative fold-specific features extracted by two DL-based methods SSAfold and DeepFR. The Top 1 sensitivity of FSD_XGBoost increases to 74.8% at the fold level, which is ~9% higher than that of the state-of-the-art method. Together, the results suggest that fold-specific features extracted by different DL methods complement with each other, and their combination can further improve fold recognition at the fold level. The implemented web server of FoldTR and benchmark datasets are publicly available at http://csbio.njust.edu.cn/bioinf/foldtr/.

Learning Cell Annotation under Multiple Reference Datasets by Multisource Domain Adaptation.

Accurate and efficient cell type annotation is essential for single-cell sequence analysis. Currently, cell type annotation using well-annotated reference datasets with powerful models has become increasingly popular. However, with the increasing amount of single-cell data, there is an urgent need to develop a novel annotation method that can integrate multiple reference datasets to improve cell type annotation performance. Since the unwanted batch effects between individual reference datasets, integrating multiple reference datasets is still an open challenge. To address this, we proposed scMDR and scMultiR, respectively, using multisource domain adaptation to learn cell type-specific information from multiple reference datasets and query cells. Based on the learned cell type-specific information, scMDR and scMultiR provide the most likely cell types for the query cells. Benchmark experiments demonstrated their state-of-the-art effectiveness for integrative single-cell assignment with multiple reference datasets.

Improving the prediction of DNA-protein binding by integrating multi-scale dense convolutional network with fault-tolerant coding.

Accurate prediction of DNA-protein binding (DPB) is of great biological significance for studying the regulatory mechanism of gene expression. In recent years, with the rapid development of deep learning techniques, advanced deep neural networks have been introduced into the field and shown to significantly improve the prediction performance of DPB. However, these methods are primarily based on the DNA sequences measured by the ChIP-seq technology, failing to consider the possible partial variations of the motif sequences and errors of the sequencing technology itself. To address this, we propose a novel computational method, termed MSDenseNet, which combines a new fault-tolerant coding (FTC) scheme with the dense connectional deep neural networks. Three important factors can be attributed to the success of MSDenseNet: First, MSDenseNet utilizes a powerful feature representation approach, which transforms the raw DNA sequence into fusion coding using the fault-tolerant feature sequence; Second, in terms of network structure, MSDenseNet uses a multi-scale convolution within the dense layer and the multi-scale convolution preceding the dense block. This is shown to be able to significantly improve the network performance and accelerate the network convergence speed, and third, building upon the advanced deep neural network, MSDenseNet is capable of effectively mining the hidden complex relationship between the internal attributes of fusion sequence features to enhance the prediction of DPB. Benchmarking experiments on 690 ChIP-seq datasets show that MSDenseNet achieves an average AUC of 0.933 and outperforms the state-of-the-art method. The source code of MSDenseNet is available at https://github.com/csbio-njust-edu/msdensenet. The results show that MSDenseNet can effectively predict DPB. We anticipate that MSDenseNet will be exploited as a powerful tool to facilitate a more exhaustive understanding of DNA-binding proteins and help toward their functional characterization.

Integrating unsupervised language model with multi-view multiple sequence alignments for high-accuracy inter-chain contact prediction.

Accurate identification of inter-chain contacts in the protein complex is critical to determine the corresponding 3D structures and understand the biological functions. We proposed a new deep learning method, ICCPred, to deduce the inter-chain contacts from the amino acid sequences of the protein complex. This pipeline was built on the designed deep residual network architecture, integrating the pre-trained language model with three multiple sequence alignments (MSAs) from different biological views. Experimental results on 709 non-redundant benchmarking protein complexes showed that the proposed ICCPred significantly increased inter-chain contact prediction accuracy compared to the state-of-the-art approaches. Detailed data analyses showed that the significant advantage of ICCPred lies in the utilization of pre-trained transformer language models which can effectively extract the complementary co-evolution diversity from three MSAs. Meanwhile, the designed deep residual network enhances the correlation between the co-evolution diversity and the patterns of inter-chain contacts. These results demonstrated a new avenue for high-accuracy deep-learning inter-chain contact prediction that is applicable to large-scale protein-protein interaction annotations from sequence alone.