Current Bioinformatics - Current Issue

The identification and functional prediction of Multifunctional Therapeutic Peptides (MFTP) play a pivotal role in drug discovery, particularly for conditions such as inflammation and hyperglycemia. Current computational methods exhibit limitations in their ability to accurately predict the multifunctionality of these peptides.

We propose a novel Wide and Deep Learning Framework that integrates both deep learning and machine learning approaches. The deep learning segment processes sequence vectors using a neural network model, while the wide segment utilizes the physicochemical properties of peptides in a random forest-based model. This hybrid approach aims to enhance the accuracy of MFTP function prediction.

Our framework outperformed the existing PrMFTP predictor in terms of precision, coverage, accuracy, and absolute true values. The evaluation was conducted on both training and independent testing datasets, demonstrating the robustness and generalizability of our model.

The proposed Wide & Deep Learning Framework offers a significant advancement in the computational prediction of MFTP functions. The availability of our model through a user-friendly web interface at MFTP-Tool.m6aminer.cn provides a valuable tool for researchers in the field of therapeutic peptide-based drug discovery, potentially accelerating the development of new treatments.

The potential of graph neural networks (GNNs) to revolutionize the analysis of non-Euclidean data has gained attention recently, making them attractive models for deep machine learning. However, insufficient compound or molecular graphs and feature representations might significantly impair and jeopardize their full potential. Despite the devastating impacts of ongoing COVID-19 across the globe, for which there is no drug with proven efficacy that has been shown to be effective. As various stages of drug discovery and repositioning require the accurate prediction of drug-target interactions (DTI), here, we propose a relational graph convolution network (RGCN) using multi-features based on the developed drug compound-coronavirus target graph data representation and combination of features. During the implementation of the model, we further introduced the use of not only the feature module to understand the topological structure of drugs but also the structure of the proven drug target (i.e., 3CL^pro) for SARS-CoV-2 that shares a genome sequence similar to that of other members of the betacoronavirus group such as SARS-CoV, MERS-CoV, bat coronavirus. Our feature comprises topological information in molecular SMILES and local chemical context in the SMILES sequence for the drug compound and drug target. Our proposed method prevailed with high and compelling performance accuracy of 97.30% which could be prioritized as the potential and promising prediction route for the development of novel oral antiviral medicine for COVID-19 drugs.

Forecasting DTI stands as a pivotal aspect of drug discovery. The focus on computational methods in DTI prediction has intensified due to the considerable expense and time investment associated with conducting extensive in vitro and in vivo experiments. Machine learning (ML) techniques, particularly deep learning, have found broad applications in DTI prediction. We are convinced that this study could be prioritized and utilized as the promising predictive route for the development of novel oral antiviral treatments for COVID-19 and other variants of coronaviruses.

This study addressed the problem of COVID-19 drugs using proposed RGCN with multi-features as an attractive and potential route. This study focused mainly on the prediction of novel antiviral drugs against coronaviruses using graph-based methodology, namely RGCN. This research further utilized the features of both drugs and common potential drug targets found in betacoronaviruses group to deepen understanding of their underlying relation.

Our suggested approach prevailed with a high and convincing performance accuracy of 97.30%, which may be utilized as a top priority to support and advance this field in the prediction and development of novel antiviral treatments against coronaviruses and their variants.

We recursively performed experiments using the proposed method on our constructed DCC-CvT graph dataset from our collected dataset with various single and multiple combinations of features and found that our model had achieved comparable best-averaged accuracy performance on T7 features followed by a combination of T7, R6, and L8. The proposed model implemented in this investigation turns out to outperform the previous related works.

The recent advancement in artificial intelligence has compelled medical research to adapt the technologies. The abundance of molecular data and AI technology has helped in explaining various diseases, even cancers. Schizophrenia is a complex neuropsychological disease whose etiology is unknown. Several gene-wide association studies attempted to narrow down the cause of the disease but did not successfully point out the mechanism behind the disease. There are studies regarding the epigenetic changes in the schizophrenia disease condition, and a classification machine-learning model has been trained using the blood methylation data.

In this study, we have demonstrated a novel approach to elucidating the molecular cause of the disease. We used a two-step machine-learning approach to determine the causal molecular markers. By doing so, we developed classification models using both gene expression microarray and methylation microarray data.

Our models, because of our novel approach, achieved good classification accuracy with the available data size. We analyzed the important features, and they add up as evidence for the glutamate hypothesis of schizophrenia.

In this way, we have demonstrated explaining a disease through machine learning models.

The application of deep generative models for molecular discovery has witnessed a significant surge in recent years. Currently, the field of molecular generation and molecular optimization is predominantly governed by autoregressive models regardless of how molecular data is represented. However, an emerging paradigm in the generation domain is diffusion models, which treat data non-autoregressively and have achieved significant breakthroughs in areas such as image generation.

The potential and capability of diffusion models in molecular generation and optimization tasks remain largely unexplored. In order to investigate the potential applicability of diffusion models in the domain of molecular exploration, we proposed DiffSeqMol, a molecular sequence generation model, underpinned by diffusion process.

DiffSeqMol distinguishes itself from traditional autoregressive methods by its capacity to draw samples from random noise and direct generating the entire molecule. Through experiment evaluations, we demonstrated that DiffSeqMol can achieve, even surpass, the performance of established state-of-the-art models on unconditional generation tasks and molecular optimization tasks.

Taken together, our results show that DiffSeqMol can be considered a promising molecular generation method. It opens new pathways to traverse the expansive chemical space and to discover novel molecules.

In cancer genomics research, identifying driver genes is a challenging task. Detecting cancer-driver genes can further our understanding of cancer risk factors and promote the development of personalized treatments. Gene mutations show mutual exclusivity and co-occur, and most of the existing methods focus on identifying driver pathways or driver gene sets through the study of mutual exclusivity, that is functionally redundant gene sets. Moreover, less research on cooperation genes with co-occurring mutations has been conducted.

We propose an effective method that combines the two characteristics of genes, co-occurring mutations and the coordinated regulation of proliferation genes, to explore cooperation driver genes.

This study is divided into three stages: (1) constructing a binary gene mutation matrix; (2) combining mutation co-occurrence characteristics to identify the candidate cooperation gene sets; and (3) constructing a gene regulation network to screen the cooperation gene sets that perform synergistically regulating proliferation.

The method performance is evaluated on three TCGA cancer datasets, and the experiments showed that it can detect effective cooperation driver gene sets. In further investigations, it was determined that the discovered set of co-driver genes could be used to generate prognostic classifications, which could be biologically significant and provide complementary information to the cancer genome.

Our approach is effective in identifying sets of cancer cooperation driver genes, and the results can be used as clinical markers to stratify patients.

Complex and diverse microbial communities play a pivotal role in human health and have become a new drug target. Exploring the connections between drugs and microbes not only provides profound insights into their mechanisms but also drives progress in drug discovery and repurposing. The use of wet lab experiments to identify associations is time-consuming and laborious. Hence, the advancement of precise and efficient computational methods can effectively improve the efficiency of association identification between microorganisms and drugs.

In this experiment, we propose a new deep learning model, a new multiview comparative hypergraph attention network (MCHAN) method for human microbe–drug association prediction.

First, we fuse multiple similarity matrices to obtain a fused microbial and drug similarity network. By combining graph convolutional networks with attention mechanisms, we extract key information from multiple perspectives. Then, we construct two network topologies based on the above fused data. One topology incorporates the concept of hypernodes to capture implicit relationships between microbes and drugs using virtual nodes to construct a hyperheterogeneous graph. Next, we propose a cross-contrastive learning task that facilitates the simultaneous guidance of graph embeddings from both perspectives, without the need for any labels. This approach allows us to bring nodes with similar features and network topologies closer while pushing away other nodes. Finally, we employ attention mechanisms to merge the outputs of the GCN and predict the associations between drugs and microbes.

To confirm the effectiveness of this method, we conduct experiments on three distinct datasets. The results demonstrate that the MCHAN model surpasses other methods in terms of performance. Furthermore, case studies provide additional evidence confirming the consistent predictive accuracy of the MCHAN model.

MCHAN is expected to become a valuable tool for predicting potential associations between microbiota and drugs in the future.

Human coronaviruses are a large group of viruses that exist widely in nature and multiply through self-replication. Due to its suddenness and variability, it poses a great threat to global human health and is a major problem currently faced by the medical and health fields.

COVID-19 is the seventh known coronavirus that can infect humans. The main purpose of this paper is to analyze the effective components and action targets of the Longyi Zhengqi formula and Lianhua Qingwen formula, study their mechanism of action in the treatment of new coronavirus pneumonia (new coronavirus pneumonia), compare the similarities and differences of their pharmacological effects, and obtain the pharmacodynamic mechanism of the two traditional Chinese medicine compounds.

Obtain the effective ingredients and targets of Longyi-Zhengqi Formula and Lianhua-Qingwen Formula from ETCM (Encyclopedia of Traditional Chinese Medicine) and other traditional Chinese medicine databases, use GeneCards database to obtain the relevant targets of COVID-19, and use Cytoscape software to build the component COVID-19 target network of Longyi-Zhengqi Formula and the component COVID-19 target network of Lianhua-Qingwen Formula. STRING was used to construct a protein interaction network and screen key targets. GO (Gene Ontology) was used for enrichment analysis and KEGG (Kyoto Encyclopedia of Genes and Genomes) was used for pathways to find out the targets and pathways related to the treatment of COVID-19.

In the GO enrichment analysis results, there are 106 biological processes, 31 cell localization and 28 molecular functions of the intersection PPI network targets of Longyi-Zhengqi Formula-COVID-19, 224 biological processes, 51 cell localization and 55 molecular functions of the intersection PPI network targets of Lianhua-Qingwen Formula-COVID-19. In the KEGG pathway analysis results, the number of targets of Longyi-Zhengqi Formula on the COVID-19 pathway is 7, and the number of targets of Lianhua-Qingwen Formula on the COVID-19 pathway is 19; In the regulation analysis results, Longyi-Zhengqi Formula achieves the effect of treating COVID-19 by regulating IL-6, and Lianhua-Qingwen Formula achieves the effect of treating pneumonia by regulating TLR4.

This paper explores the mechanism of action of Longyi-Zhengqi Formula and Lianhua-Qingwen Formula in treating COVID-19 based on the method of network pharmacology, and provides a theoretical basis for traditional Chinese medicine to treat sudden diseases caused by human coronavirus in terms of drug targets and disease interactions. It has certain practical significance.