ACPred-BMF: bidirectional LSTM with multiple feature representations for explainable anticancer peptide prediction.

Cancer has become a major factor threatening human life and health. Under the circumstance that traditional treatment methods such as chemotherapy and radiotherapy are not highly specific and often cause severe side effects and toxicity, new treatment methods are urgently needed. Anticancer peptide drugs have low toxicity, stronger efficacy and specificity, and have emerged as a new type of cancer treatment drugs. However, experimental identification of anticancer peptides is time-consuming and expensive, and difficult to perform in a high-throughput manner. Computational identification of anticancer peptides can make up for the shortcomings of experimental identification. In this study, a deep learning-based predictor named ACPred-BMF is proposed for the prediction of anticancer peptides. This method uses the quantitative and qualitative properties of amino acids, binary profile feature to numerical representation for the peptide sequences. The Bidirectional LSTM network architecture is used in the model, and the attention mechanism is also considered. To alleviate the black-box problem of deep learning model prediction, we visualized the automatically extracted features and used the Shapley additive explanations algorithm to determine the importance of features to further understand the anticancer peptide mechanism. The results show that our method is one of the state-of-the-art anticancer peptide predictors. A web server as the implementation of ACPred-BMF that can be accessed via: http://mialab.ruc.edu.cn/ACPredBMFServer/ .

ToxIBTL: prediction of peptide toxicity based on information bottleneck and transfer learning.

MOTIVATION: Recently, peptides have emerged as a promising class of pharmaceuticals for various diseases treatment poised between traditional small molecule drugs and therapeutic proteins. However, one of the key bottlenecks preventing them from therapeutic peptides is their toxicity toward human cells, and few available algorithms for predicting toxicity are specially designed for short-length peptides. RESULTS: We present ToxIBTL, a novel deep learning framework by utilizing the information bottleneck principle and transfer learning to predict the toxicity of peptides as well as proteins. Specifically, we use evolutionary information and physicochemical properties of peptide sequences and integrate the information bottleneck principle into a feature representation learning scheme, by which relevant information is retained and the redundant information is minimized in the obtained features. Moreover, transfer learning is introduced to transfer the common knowledge contained in proteins to peptides, which aims to improve the feature representation capability. Extensive experimental results demonstrate that ToxIBTL not only achieves a higher prediction performance than state-of-the-art methods on the peptide dataset, but also has a competitive performance on the protein dataset. Furthermore, a user-friendly online web server is established as the implementation of the proposed ToxIBTL. AVAILABILITY AND IMPLEMENTATION: The proposed ToxIBTL and data can be freely accessible at http://server.wei-group.net/ToxIBTL. Our source code is available at https://github.com/WLYLab/ToxIBTL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Consensus-based clustering of single cells by reconstructing cell-to-cell dissimilarity.

The development of single-cell ribonucleic acid (RNA) sequencing (scRNA-seq) technology has led to great opportunities for the identification of heterogeneous cell types in complex tissues. Clustering algorithms are of great importance to effectively identify different cell types. In addition, the definition of the distance between each two cells is a critical step for most clustering algorithms. In this study, we found that different distance measures have considerably different effects on clustering algorithms. Moreover, there is no specific distance measure that is applicable to all datasets. In this study, we introduce a new single-cell clustering method called SD-h, which generates an applicable distance measure for different kinds of datasets by optimally synthesizing commonly used distance measures. Then, hierarchical clustering is performed based on the new distance measure for more accurate cell-type clustering. SD-h was tested on nine frequently used scRNA-seq datasets and it showed great superiority over almost all the compared leading single-cell clustering algorithms.

Identification of HCC-Related Genes Based on Differential Partial Correlation Network.

Hepatocellular carcinoma (HCC) is one of the most common causes of cancer-related death, but its pathogenesis is still unclear. As the disease is involved in multiple biological processes, systematic identification of disease genes and module biomarkers can provide a better understanding of disease mechanisms. In this study, we provided a network-based approach to integrate multi-omics data and discover disease-related genes. We applied our method to HCC data from The Cancer Genome Atlas (TCGA) database and obtained a functional module with 15 disease-related genes as network biomarkers. The results of classification and hierarchical clustering demonstrate that the identified functional module can effectively distinguish between the disease and the control group in both supervised and unsupervised methods. In brief, this computational method to identify potential functional disease modules could be useful to disease diagnosis and further mechanism study of complex diseases.

TransRef enables accurate transcriptome assembly by redefining accurate neo-splicing graphs.

RNA-seq technology is widely employed in various research areas related to transcriptome analyses, and the identification of all the expressed transcripts from short sequencing reads presents a considerable computational challenge. In this study, we introduce TransRef, a new computational algorithm for accurate transcriptome assembly by redefining a novel graph model, the neo-splicing graph, and then iteratively applying a constrained dynamic programming to reconstruct all the expressed transcripts for each graph. When TransRef is utilized to analyze both real and simulated datasets, its performance is notably better than those of several state-of-the-art assemblers, including StringTie2, Cufflinks and Scallop. In particular, the performance of TransRef is notably strong in identifying novel transcripts and transcripts with low-expression levels, while the other assemblers are less effective.

FEGS: a novel feature extraction model for protein sequences and its applications.

BACKGROUND: Feature extraction of protein sequences is widely used in various research areas related to protein analysis, such as protein similarity analysis and prediction of protein functions or interactions. RESULTS: In this study, we introduce FEGS (Feature Extraction based on Graphical and Statistical features), a novel feature extraction model of protein sequences, by developing a new technique for graphical representation of protein sequences based on the physicochemical properties of amino acids and effectively employing the statistical features of protein sequences. By fusing the graphical and statistical features, FEGS transforms a protein sequence into a 578-dimensional numerical vector. When FEGS is applied to phylogenetic analysis on five protein sequence data sets, its performance is notably better than all of the other compared methods. CONCLUSION: The FEGS method is carefully designed, which is practically powerful for extracting features of protein sequences. The current version of FEGS is developed to be user-friendly and is expected to play a crucial role in the related studies of protein sequence analyses.

TransBorrow: genome-guided transcriptome assembly by borrowing assemblies from different assemblers.

RNA-seq technology is widely used in various transcriptomic studies and provides great opportunities to reveal the complex structures of transcriptomes. To effectively analyze RNA-seq data, we introduce a novel transcriptome assembler, TransBorrow, which borrows the assemblies from different assemblers to search for reliable subsequences by building a colored graph from those borrowed assemblies. Then, by seeding reliable subsequences, a newly designed path extension strategy accurately searches for a transcript-representing path cover over each splicing graph. TransBorrow was tested on both simulated and real data sets and showed great superiority over all the compared leading assemblers.

DCGR: feature extractions from protein sequences based on CGR via remodeling multiple information.

BACKGROUND: Protein feature extraction plays an important role in the areas of similarity analysis of protein sequences and prediction of protein structures, functions and interactions. The feature extraction based on graphical representation is one of the most effective and efficient ways. However, most existing methods suffer limitations from their method design. RESULTS: We introduce DCGR, a novel method for extracting features from protein sequences based on the chaos game representation, which is developed by constructing CGR curves of protein sequences according to physicochemical properties of amino acids, followed by converting the CGR curves into multi-dimensional feature vectors by using the distributions of points in CGR images. Tested on five data sets, DCGR was significantly superior to the state-of-the-art feature extraction methods. CONCLUSION: The DCGR is practically powerful for extracting effective features from protein sequences, and therefore important in similarity analysis of protein sequences, study of protein-protein interactions and prediction of protein functions. It is freely available at https://sourceforge.net/projects/transcriptomeassembly/files/Feature%20Extraction .

TransLiG: a de novo transcriptome assembler that uses line graph iteration.

We present TransLiG, a new de novo transcriptome assembler, which is able to integrate the sequence depth and pair-end information into the assembling procedure by phasing paths and iteratively constructing line graphs starting from splicing graphs. TransLiG is shown to be significantly superior to all the salient de novo assemblers in both accuracy and computing resources when tested on artificial and real RNA-seq data. TransLiG is freely available at https://sourceforge.net/projects/transcriptomeassembly/files/ .

Predicting nucleosome positioning based on geometrically transformed Tsallis entropy.

As the fundamental unit of eukaryotic chromatin structure, nucleosome plays critical roles in gene expression and regulation by controlling physical access to transcription factors. In this paper, based on the geometrically transformed Tsallis entropy and two index-vectors, a valid nucleosome positioning information model is developed to describe the distribution of A/T-riched and G/C-riched dimeric and trimeric motifs along the DNA duplex. When applied to train the support vector machine, the model achieves high AUCs across five organisms, which have significantly outperformed the previous studies. Besides, we adopt the concept of relative distance to describe the probability of arbitrary DNA sequence covered by nucleosome. Thus, the average nucleosome occupancy profile over the S.cerevisiae genome is calculated. With our peak detection model, the isolated nucleosomes along genome sequence are located. When compared with some published results, it shows that our model is effective for nucleosome positioning. The index-vector component [Formula in text] is identified to be an important influencing factor of nucleosome organizations.