Article
Biochemistry & Molecular Biology
Fang Ge, Yi-Heng Zhu, Jian Xu, Arif Muhammad, Jiangning Song, Dong-Jun Yu
Summary: A new transmembrane protein mutation predictor, MutTMPredictor, was developed in this study and demonstrated to be effective through experiments on multiple datasets. The performance of MutTMPredictor surpassed existing predictors, showcasing its potential as a valuable tool for predicting and prioritizing missense mutations in transmembrane proteins. The MutTMPredictor webserver is freely accessible for academic use.
COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL
(2021)
Article
Biochemical Research Methods
Yang Li, Xue-Gang Hu, Zhu-Hong You, Li-Ping Li, Pei-Pei Li, Yan-Bin Wang, Yu-An Huang
Summary: In this paper, a novel framework, GLCM-WSRC, is proposed for the automatic prediction of SIPs based on protein evolutionary information from protein primary sequences. Experimental results show high prediction performance, indicating the potential usefulness of the proposed model for large-scale self-interacting protein prediction and other bioinformatics tasks detection in the future.
BMC BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Zhenling Peng, Zixia Li, Qiaozhen Meng, Bi Zhao, Lukasz Kurgan
Summary: One of the key features of IDRs is to facilitate interactions between proteins and nucleic acids. There are different types of disordered binding regions, including MoRFs, SLiMs, and longer binding domains. Recent research has introduced a new class of disordered binding regions called LIPs, which undergo disorderto-order transition upon binding. However, there are currently no dedicated sequence-based predictors for LIPs.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Zhenling Peng, Zixia Li, Qiaozhen Meng, Bi Zhao, Lukasz Kurgan
Summary: This paper introduces a new method for predicting intrinsically disordered regions (IDRs) called CLIP. CLIP uses inputs such as co-evolutionary information, physicochemical profiles, and disorder predictions to predict linear interacting peptides (LIPs) in protein sequences. Experimental results show that CLIP achieves good performance in predicting LIPs and outperforms current tools for predicting MoRFs and disordered protein-binding regions.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Suyeon Lee, Heewon Jung, Jiwoo Park, Jaegyoon Ahn
Summary: This study demonstrated the accurate prediction of cancer prognoses by using patient-specific cancer driver genes. By generating patient-specific gene networks and using modified PageRank algorithm to generate feature vectors representing the impact of genes on the network, a deep feedforward network was trained for prediction. The proposed method showed significantly better prediction performance for some cancer types and indicated the association of heterogeneous cancer driver information with cancer prognosis.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Chemistry, Medicinal
Adnan Khan, Jamal Uddin, Farman Ali, Harish Kumar, Wajdi Alghamdi, Aftab Ahmad
Summary: The development of intracellular ice in cold-blooded organisms can be fatal, but they produce antifreeze proteins (AFPs) to survive in subzero temperatures. AFPs also have applications in various fields. This study introduces a new approach called AFP-SPTS for accurate AFP prediction. By exploring different features and using ensemble learning with machine learning algorithms, the proposed predictor achieved improved accuracies compared to existing models.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Genetics & Heredity
Li-Ping Li, Bo Zhang, Li Cheng
Summary: Identification and characterization of plant protein-protein interactions (PPIs) are crucial in understanding protein functions and molecular mechanisms in plant cells. This article proposes a computational framework, CPIELA, for predicting plant PPIs, which combines PSSM, LOOP, and ROF model. Experimental results demonstrate that CPIELA achieved high prediction accuracies and outperforms other state-of-the-art methods. CPIELA has the potential to be a useful tool in identifying possible plant PPIs.
FRONTIERS IN GENETICS
(2022)
Article
Computer Science, Artificial Intelligence
Bin Yu, Cheng Chen, Xiaolin Wang, Zhaomin Yu, Anjun Ma, Bingqiang Liu
Summary: Using machine-learning-based frameworks can automatically identify protein-protein interactions (PPIs) and provide new ideas for drug research and development. The deep forest model GcForest-PPI outperforms other methods in predicting PPIs and can improve drug discovery.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Biochemical Research Methods
Yiming Li, Min Zeng, Yifan Wu, Yaohang Li, Min Li
Summary: This paper proposes EP-EDL, an ensemble deep learning model that uses only protein sequence information to predict human essential proteins. EP-EDL outperforms state-of-the-art sequence-based methods and provides a practical and flexible way for accurate prediction of essential proteins.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Article
Chemistry, Medicinal
Ji Lv, Guixia Liu, Yuan Ju, Houhou Huang, Dalin Li, Ying Sun
Summary: Previous studies have shown that antibiotics can be divided into groups based on drug-drug interactions (DDI). However, these studies focused on a specific bacteria strain and existing datasets often contain noise. To address this problem, we developed a multi-source information fusion method that integrates DDI information from multiple bacterial strains. Our method effectively identifies antibiotic subgroups and provides insights into the mechanism of action of antibiotics and multi-species group-group interactions.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Biochemical Research Methods
Lesong Wei, Xiucai Ye, Yuyang Xue, Tetsuya Sakurai, Leyi Wei
Summary: ATSE is a peptide toxicity predictor based on graph neural networks and attention mechanism, which accurately predicts the potential toxicity of peptides. By combining structural and evolutionary information, ATSE outperforms other methods and provides interpretable and visualizable features for further analysis.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Antoine Passemiers, Yves Moreau, Daniele Raimondi
Summary: This article presents a novel method called PORTIA for inferring gene regulatory networks (GRNs). The method is based on robust precision matrix estimation and is shown to outperform state-of-the-art methods in terms of speed while still maintaining good accuracy. The authors extensively validated PORTIA using benchmark datasets and propose a new scoring metric based on graph-theoretical concepts.
Article
Computer Science, Artificial Intelligence
Wei Yin, Yifan Liu, Chunhua Shen
Summary: This work emphasizes the importance of high-order 3D geometric constraints in monocular depth prediction. By introducing a loss term based on virtual normal directions, the accuracy and robustness of depth estimation can be significantly improved. Moreover, this approach disentangles scale information and enriches the model with better shape information. Experimental results demonstrate state-of-the-art performance on various datasets with diverse scenes.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Biochemical Research Methods
Travis J. Lawrence, Dana L. Carper, Margaret K. Spangler, Alyssa A. Carrell, Tomas A. Rush, Stephen J. Minter, David J. Weston, Jessy L. Labbe
Summary: Antimicrobial peptides (AMPs) are promising alternative antimicrobial agents, but efficient methods for predicting AMP sequences are currently lacking. amPEPpy is an open-source, multi-threaded command-line application designed to predict AMP sequences using a random forest classifier.
Article
Biology
Hongli Gao, Cheng Chen, Shuangyi Li, Congjing Wang, Weifeng Zhou, Bin Yu
Summary: In this paper, the EResCNN model is developed to predict protein-protein interactions using deep learning techniques. The model combines multiple feature representation methods and utilizes a residual convolutional neural network to capture high-level information. Experimental results show that EResCNN achieves good predictive performance on different datasets and can be applied to cross-species prediction.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Biotechnology & Applied Microbiology
Zhengwei Li, Tangbo Zhong, Deshuang Huang, Zhu-Hong You, Ru Nie
Summary: In this study, a novel deep learning model called HGANMDA was proposed to predict miRNA-disease associations. The model constructed a heterogeneous graph and utilized hierarchical graph attention network to achieve accurate prediction of miRNA-disease associations.
Article
Biochemical Research Methods
Zhi-Hua Du, Yang-Han Wu, Yu-An Huang, Jie Chen, Gui-Qing Pan, Lun Hu, Zhu-Hong You, Jian-Qiang Li
Summary: This study introduces a graph attention-based autoencoder model to predict TF-target gene interactions, which shows excellent prediction performance on a real dataset.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Han-Yuan Zhang, Lei Wang, Zhu-Hong You, Lun Hu, Bo-Wei Zhao, Zheng-Wei Li, Yang-Ming Li
Summary: Researchers have discovered a novel topology of RNA transcript called circular RNA (circRNA) that competes with messenger RNA (mRNA) and long noncoding RNA in gene regulation. This finding suggests that circRNA could be associated with complex diseases, thus identifying the relationship between them would contribute to medical research. However, in vitro experiments to determine the circRNA-disease association are time-consuming and lack direction. To address this, a computational method called iGRLCDA was proposed, which utilizes graph convolution network (GCN) and graph factorization (GF) to predict circRNA-disease associations. The performance of iGRLCDA was compared to other prediction models using five-fold cross-validation, showing strong competitiveness and high accuracy.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Xiaorui Su, Lun Hu, Zhuhong You, Pengwei Hu, Bowei Zhao
Summary: This paper proposes a KG-based drug-drug interaction (DDI) prediction framework called DDKG, which utilizes KG information and attention mechanism. Experimental results show that DDKG outperforms existing algorithms on different evaluation metrics.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biotechnology & Applied Microbiology
Zhong-Hao Ren, Chang-Qing Yu, Li-Ping Li, Zhu-Hong You, Yong-Jian Guan, Xin-Fei Wang, Jie Pan
Summary: Co-administration of drugs is an effective strategy for treating complex diseases, but predicting drug-drug interactions (DDIs) accurately is challenging. In this paper, a novel method called BioDKG-DDI is proposed to predict potential DDIs by integrating multiple features and biochemical information using an attention mechanism and deep neural network. Experimental results demonstrate that this method is robust and simple, and can serve as a beneficial supplement to the experimental process.
BRIEFINGS IN FUNCTIONAL GENOMICS
(2022)
Article
Genetics & Heredity
Zhong-Hao Ren, Chang-Qing Yu, Li-Ping Li, Zhu-Hong You, Yong-Jian Guan, Yue-Chao Li, Jie Pan
Summary: Non-coding RNAs (ncRNAs) play important roles in biological processes through interactions with RNA binding proteins (RBPs). Computational methods have been developed to predict ncRNA-protein interactions, but some of them have limited applicability. In this study, a computational method called SAWRPI is proposed to predict ncRNA-protein interactions using sequence information. The method achieved high performance in experiments, showing its potential as a reliable tool for predicting ncRNA-protein interactions.
FRONTIERS IN GENETICS
(2022)
Article
Biology
Zhong-Hao Ren, Chang-Qing Yu, Li-Ping Li, Zhu-Hong You, Jie Pan, Yong-Jian Guan, Lu-Xiang Guo
Summary: Combining drugs to fight against diseases has a long history, but potential drug interactions can lead to unknown toxicity. Our study introduces a computational framework and an online tool for researchers to identify potential interactions in the fields of biomedicine and pharmacology. This approach provides new insights for rapidly identifying drug-drug interactions.
Article
Biochemistry & Molecular Biology
Ying Wang, Lin-Lin Wang, Leon Wong, Yang Li, Lei Wang, Zhu-Hong You
Summary: Protein is the fundamental organic substance in cells that plays a crucial role in biological activities. Self-interacting protein (SIP) is an important protein interaction. This study presents a SIP prediction method, SIPGCN, using a deep learning graph convolutional network (GCN). The results demonstrate excellent performance of SIPGCN.
Article
Biology
Xinke Zhan, Mang Xiao, Zhuhong You, Chenggang Yan, Jianxin Guo, Liping Wang, Yaoqi Sun, Bingwan Shang
Summary: This paper proposes a computational method for predicting protein-protein interactions from protein sequences. The method utilizes PSSM, LPP, and RF for feature extraction and classification. Experimental results demonstrate that the method is stable, accurate, and promising as a useful tool for proteomics research.
Article
Biochemical Research Methods
Kai Zheng, Xin-Lu Zhang, Lei Wang, Zhu-Hong You, Zhao-Hui Zhan, Hao-Yuan Li
Summary: PIWI proteins and piRNAs are commonly found in human cancers and are associated with poorer clinical outcomes. A new graph neural network framework called line graph attention networks (LGAT) is developed for predicting the association between PiRNAs and diseases. Experimental results show that LGAT performs excellently in identifying potential associations.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Xiangyu Pan, Lun Hu, Pengwei Hu, Zhu-Hong You
Summary: Protein complexes play a crucial role in understanding protein biological processes. In this study, we propose a novel fuzzy-based clustering framework called FCAN-PCI, which considers both network topology and protein attribute information to improve identification accuracy and identify overlapping complexes.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Review
Computer Science, Information Systems
Zhanheng Chen, Zhuhong You, Qinhu Zhang, Zhenhao Guo, Siguo Wang, Yanbin Wang
Summary: This review provides a comprehensive overview of recent literature on computational prediction of self-interacting proteins (SIPs), serving as a valuable reference for future work. The review first describes the data required for predicting drug-target interactions (DTIs), followed by the presentation of interesting feature extraction methods and computational models. An empirical comparison is then conducted to demonstrate the prediction performance of various classifiers under different feature extraction and encoding schemes. Overall, potential methods for further enhancing SIPs prediction performance and related research directions are summarized and highlighted.
FRONTIERS OF COMPUTER SCIENCE
(2023)
Article
Automation & Control Systems
Lei Wang, Zhu-Hong You, De-Shuang Huang, Jian-Qiang Li
Summary: This study presents a new computational model, MGRCDA, which utilizes metagraph recommendation theory to predict potential circRNA-disease associations. By integrating heterogeneous biological networks and utilizing an iterative search algorithm, MGRCDA achieved high prediction accuracy and reliability. The experimental results demonstrate its feasibility and efficiency in reducing the scope of wet-lab experiments.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Biology
Yong-Jian Guan, Chang-Qing Yu, Yan Qiao, Li-Ping Li, Zhu-Hong You, Zhong-Hao Ren, Yue-Chao Li, Jie Pan
Summary: This study presents a computational method called MFIDMA for predicting drug-miRNA associations. The proposed model demonstrates excellent performance in experiments and can be used for the development and research of miRNA-targeted drugs, providing new perspectives on miRNA therapeutics research and drug discovery.
Article
Biochemical Research Methods
Jie Pan, Zhuhong You, Wencai You, Tian Zhao, Chenlu Feng, Xuexia Zhang, Fengzhi Ren, Sanxing Ma, Fan Wu, Shiwei Wang, Yanmei Sun
Summary: This study developed a model called PTBGRP based on microbial heterogeneous interaction network to predict new phages for bacterial hosts. By integrating different biological attributes and topological features, a deep neural network classifier was used to predict unknown PBI pairs. Experimental results demonstrated that PTBGRP achieved the best performance on pathogen and PBI datasets.
BRIEFINGS IN BIOINFORMATICS
(2023)
