1
|
Zhao Y, Jin J, Gao W, Qiao J, Wei L. Moss-m7G: A Motif-Based Interpretable Deep Learning Method for RNA N7-Methlguanosine Site Prediction. J Chem Inf Model 2024; 64:6230-6240. [PMID: 39011571 DOI: 10.1021/acs.jcim.4c00802] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/17/2024]
Abstract
N-7methylguanosine (m7G) modification plays a crucial role in various biological processes and is closely associated with the development and progression of many cancers. Accurate identification of m7G modification sites is essential for understanding their regulatory mechanisms and advancing cancer therapy. Previous studies often suffered from insufficient research data, underutilization of motif information, and lack of interpretability. In this work, we designed a novel motif-based interpretable method for m7G modification site prediction, called Moss-m7G. This approach enables the analysis of RNA sequences from a motif-centric perspective. Our proposed word-detection module and motif-embedding module within Moss-m7G extract motif information from sequences, transforming the raw sequences from base-level into motif-level and generating embeddings for these motif sequences. Compared with base sequences, motif sequences contain richer contextual information, which is further analyzed and integrated through the Transformer model. We constructed a comprehensive m7G data set to implement the training and testing process to address the data insufficiency noted in prior research. Our experimental results affirm the effectiveness and superiority of Moss-m7G in predicting m7G modification sites. Moreover, the introduction of the word-detection module enhances the interpretability of the model, providing insights into the predictive mechanisms.
Collapse
Affiliation(s)
- Yanxi Zhao
- School of Software, Shandong University, Jinan 250101, China
- Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan 250101, China
| | - Junru Jin
- School of Software, Shandong University, Jinan 250101, China
- Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan 250101, China
| | - Wenjia Gao
- School of Software, Shandong University, Jinan 250101, China
- Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan 250101, China
| | - Jianbo Qiao
- School of Software, Shandong University, Jinan 250101, China
- Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan 250101, China
| | - Leyi Wei
- School of Software, Shandong University, Jinan 250101, China
- Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan 250101, China
- School of Informatics, Xiamen University, Xiamen 361104, China
| |
Collapse
|
2
|
Zuo Y, Zhang B, Dong Y, He W, Bi Y, Liu X, Zeng X, Deng Z. Glypred: Lysine Glycation Site Prediction via CCU-LightGBM-BiLSTM Framework with Multi-Head Attention Mechanism. J Chem Inf Model 2024. [PMID: 39121059 DOI: 10.1021/acs.jcim.4c01034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/11/2024]
Abstract
Glycation, a type of posttranslational modification, preferentially occurs on lysine and arginine residues, impairing protein functionality and altering characteristics. This process is linked to diseases such as Alzheimer's, diabetes, and atherosclerosis. Traditional wet lab experiments are time-consuming, whereas machine learning has significantly streamlined the prediction of protein glycation sites. Despite promising results, challenges remain, including data imbalance, feature redundancy, and suboptimal classifier performance. This research introduces Glypred, a lysine glycation site prediction model combining ClusterCentroids Undersampling (CCU), LightGBM, and bidirectional long short-term memory network (BiLSTM) methodologies, with an additional multihead attention mechanism integrated into the BiLSTM. To achieve this, the study undertakes several key steps: selecting diverse feature types to capture comprehensive protein information, employing a cluster-based undersampling strategy to balance the data set, using LightGBM for feature selection to enhance model performance, and implementing a bidirectional LSTM network for accurate classification. Together, these approaches ensure that Glypred effectively identifies glycation sites with high accuracy and robustness. For feature encoding, five distinct feature types─AAC, KMER, DR, PWAA, and EBGW─were selected to capture a broad spectrum of protein sequence and biological information. These encoded features were integrated and validated to ensure comprehensive protein information acquisition. To address the issue of highly imbalanced positive and negative samples, various undersampling algorithms, including random undersampling, NearMiss, edited nearest neighbor rule, and CCU, were evaluated. CCU was ultimately chosen to remove redundant nonglycated training data, establishing a balanced data set that enhances the model's accuracy and robustness. For feature selection, the LightGBM ensemble learning algorithm was employed to reduce feature dimensionality by identifying the most significant features. This approach accelerates model training, enhances generalization capabilities, and ensures good transferability of the model. Finally, a bidirectional long short-term memory network was used as the classifier, with a network structure designed to capture glycation modification site features from both forward and backward directions. To prevent overfitting, appropriate regularization parameters and dropout rates were introduced, achieving efficient classification. Experimental results show that Glypred achieved optimal performance. This model provides new insights for bioinformatics and encourages the application of similar strategies in other fields. A lysine glycation site prediction software tool was also developed using the PyQt5 library, offering researchers an auxiliary screening tool to reduce workload and improve efficiency. The software and data sets are available on GitHub: https://github.com/ZBYnb/Glypred.
Collapse
Affiliation(s)
- Yun Zuo
- School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214000, China
| | - Bangyi Zhang
- School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214000, China
| | - Yinkang Dong
- School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214000, China
| | - Wenying He
- School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, China
| | - Yue Bi
- Department of Biochemistry and Molecular Biology and Biomedicine Discovery Institute, Monash University, Clayton 3800, Australia
| | - Xiangrong Liu
- Department of Computer Science and Technology, National Institute for Data Science in Health and Medicine, Xiamen Key Laboratory of Intelligent Storage and Computing, Xiamen University, Xiamen 361005, China
| | - Xiangxiang Zeng
- School of Information Science and Engineering, Hunan University, Changsha 410012, China
| | - Zhaohong Deng
- School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214000, China
| |
Collapse
|
3
|
Xu Y, Zhang S, Zhu F, Liang Y. A deep learning model for anti-inflammatory peptides identification based on deep variational autoencoder and contrastive learning. Sci Rep 2024; 14:18451. [PMID: 39117712 PMCID: PMC11310449 DOI: 10.1038/s41598-024-69419-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2024] [Accepted: 08/05/2024] [Indexed: 08/10/2024] Open
Abstract
As a class of biologically active molecules with significant immunomodulatory and anti-inflammatory effects, anti-inflammatory peptides have important application value in the medical and biotechnology fields due to their unique biological functions. Research on the identification of anti-inflammatory peptides provides important theoretical foundations and practical value for a deeper understanding of the biological mechanisms of inflammation and immune regulation, as well as for the development of new drugs and biotechnological applications. Therefore, it is necessary to develop more advanced computational models for identifying anti-inflammatory peptides. In this study, we propose a deep learning model named DAC-AIPs based on variational autoencoder and contrastive learning for accurate identification of anti-inflammatory peptides. In the sequence encoding part, the incorporation of multi-hot encoding helps capture richer sequence information. The autoencoder, composed of convolutional layers and linear layers, can learn latent features and reconstruct features, with variational inference enhancing the representation capability of latent features. Additionally, the introduction of contrastive learning aims to improve the model's classification ability. Through cross-validation and independent dataset testing experiments, DAC-AIPs achieves superior performance compared to existing state-of-the-art models. In cross-validation, the classification accuracy of DAC-AIPs reached around 88%, which is 7% higher than previous models. Furthermore, various ablation experiments and interpretability experiments validate the effectiveness of DAC-AIPs. Finally, a user-friendly online predictor is designed to enhance the practicality of the model, and the server is freely accessible at http://dac-aips.online .
Collapse
Affiliation(s)
- Yujie Xu
- School of Mathematics and Statistics, Xidian University, Xi'an, 710071, People's Republic of China
| | - Shengli Zhang
- School of Mathematics and Statistics, Xidian University, Xi'an, 710071, People's Republic of China.
| | - Feng Zhu
- Center for Translational Medicine, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, 710061, People's Republic of China
| | - Yunyun Liang
- School of Science, Xi'an Polytechnic University, Xi'an, 710048, People's Republic of China
| |
Collapse
|
4
|
Li Y, Lin Y, Hu P, Peng D, Luo H, Peng X. Single-Cell RNA-Seq Debiased Clustering via Batch Effect Disentanglement. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:11371-11381. [PMID: 37030864 DOI: 10.1109/tnnls.2023.3260003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
A variety of single-cell RNA-seq (scRNA-seq) clustering methods has achieved great success in discovering cellular phenotypes. However, it remains challenging when the data confounds with batch effects brought by different experimental conditions or technologies. Namely, the data partitions would be biased toward these nonbiological factors. Meanwhile, the batch differences are not always much smaller than true biological variations, hindering the cooperation of batch integration and clustering methods. To overcome this challenge, we propose single-cell RNA-seq debiased clustering (SCDC), an end-to-end clustering method that is debiased toward batch effects by disentangling the biological and nonbiological information from scRNA-seq data during data partitioning. In six analyses, SCDC qualitatively and quantitatively outperforms both the state-of-the-art clustering and batch integration methods in handling scRNA-seq data with batch effects. Furthermore, SCDC clusters data with a linearly increasing running time with respect to cell numbers and a fixed graphics processing unit (GPU) memory consumption, making it scalable to large datasets. The code will be released on Github.
Collapse
|
5
|
Luo G, Zhang H, Yuan Q, Li J, Wang W, Wang FY. One Size Fits All: A Unified Traffic Predictor for Capturing the Essential Spatial-Temporal Dependency. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024; 35:11317-11331. [PMID: 37030861 DOI: 10.1109/tnnls.2023.3259045] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/19/2023]
Abstract
Traffic prediction is a keystone for building smart cities in the new era and has found wide applications in traffic scheduling and management, environment policy making, public safety, and so on. Instead of creating a traffic predictor for each city, this article focuses on designing a unified network model that could be directly applied for traffic prediction in any city, by learning the essential spatial-temporal dependencies, i.e., the mutual relationship between traffic and the corresponding fine-grained road network. To achieve this goal, this article proposes a joint knowledge- and data-driven mechanism that novelly divides dependencies into three kinds of correlations, i.e., road segment, intra-intersection, and inter-intersection correlation, which capture the microcosmic, middle, and macroscopic dependencies between traffic and the road network, respectively. Specifically, we first construct traffic datasets that could cover all road segments from real-world trajectory datasets, which makes it possible to model the whole road network as a graph, with the help of fine-grained road topology. Then, we propose meta road segment learner, connection-aware spatial-temporal graph convolutional network (GCN), and multiscale residual networks for capturing the microcosmic, middle, and macroscopic dependencies, respectively. Our experiments on three real-world datasets demonstrate that our proposed method could: 1) achieve better prediction accuracy compared with several approaches and 2) capture the mutual relationship between traffic and the fine-grained road network since our model trained only using data from the source city achieves good performance when it is directly applied for traffic prediction in the target city, without any fine-tuning. The codes will be made publicly available.
Collapse
|
6
|
Yao L, Xie P, Guan J, Chung CR, Huang Y, Pang Y, Wu H, Chiang YC, Lee TY. CapsEnhancer: An Effective Computational Framework for Identifying Enhancers Based on Chaos Game Representation and Capsule Network. J Chem Inf Model 2024; 64:5725-5736. [PMID: 38946113 PMCID: PMC11267569 DOI: 10.1021/acs.jcim.4c00546] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2024] [Revised: 06/21/2024] [Accepted: 06/21/2024] [Indexed: 07/02/2024]
Abstract
Enhancers are a class of noncoding DNA, serving as crucial regulatory elements in governing gene expression by binding to transcription factors. The identification of enhancers holds paramount importance in the field of biology. However, traditional experimental methods for enhancer identification demand substantial human and material resources. Consequently, there is a growing interest in employing computational methods for enhancer prediction. In this study, we propose a two-stage framework based on deep learning, termed CapsEnhancer, for the identification of enhancers and their strengths. CapsEnhancer utilizes chaos game representation to encode DNA sequences into unique images and employs a capsule network to extract local and global features from sequence "images". Experimental results demonstrate that CapsEnhancer achieves state-of-the-art performance in both stages. In the first and second stages, the accuracy surpasses the previous best methods by 8 and 3.5%, reaching accuracies of 94.5 and 95%, respectively. Notably, this study represents the pioneering application of computer vision methods to enhancer identification tasks. Our work not only contributes novel insights to enhancer identification but also provides a fresh perspective for other biological sequence analysis tasks.
Collapse
Affiliation(s)
- Lantian Yao
- Kobilka
Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
- School
of Science and Engineering, The Chinese
University of Hong Kong, Shenzhen 518172, China
| | - Peilin Xie
- Kobilka
Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Jiahui Guan
- School
of Medicine, The Chinese University of Hong
Kong, Shenzhen 518172, China
| | - Chia-Ru Chung
- Department
of Computer Science and Information Engineering, National Central University, Taoyuan 320317, Taiwan
| | - Yixian Huang
- School
of Medicine, The Chinese University of Hong
Kong, Shenzhen 518172, China
| | - Yuxuan Pang
- Division
of Health Medical Intelligence, Human Genome Center, The Institute
of Medical Science, The University of Tokyo, Tokyo 108-8639, Japan
| | - Huacong Wu
- School
of Medicine, The Chinese University of Hong
Kong, Shenzhen 518172, China
| | - Ying-Chih Chiang
- Kobilka
Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
- School
of Medicine, The Chinese University of Hong
Kong, Shenzhen 518172, China
| | - Tzong-Yi Lee
- Institute
of Bioinformatics and Systems Biology, National
Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan
- Center
for Intelligent Drug Systems and Smart Bio-devices (IDS2B), National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan
| |
Collapse
|
7
|
Zhuang J, Huang X, Liu S, Gao W, Su R, Feng K. MulTFBS: A Spatial-Temporal Network with Multichannels for Predicting Transcription Factor Binding Sites. J Chem Inf Model 2024; 64:4322-4333. [PMID: 38733561 DOI: 10.1021/acs.jcim.3c02088] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/13/2024]
Abstract
Revealing the mechanisms that influence transcription factor binding specificity is the key to understanding gene regulation. In previous studies, DNA double helix structure and one-hot embedding have been used successfully to design computational methods for predicting transcription factor binding sites (TFBSs). However, DNA sequence as a kind of biological language, the method of word embedding representation in natural language processing, has not been considered properly in TFBS prediction models. In our work, we integrate different types of features of DNA sequence to design a multichanneled deep learning framework, namely MulTFBS, in which independent one-hot encoding, word embedding encoding, which can incorporate contextual information and extract the global features of the sequences, and double helix three-dimensional structural features have been trained in different channels. To extract sequence high-level information effectively, in our deep learning framework, we select the spatial-temporal network by combining convolutional neural networks and bidirectional long short-term memory networks with attention mechanism. Compared with six state-of-the-art methods on 66 universal protein-binding microarray data sets of different transcription factors, MulTFBS performs best on all data sets in the regression tasks, with the average R2 of 0.698 and the average PCC of 0.833, which are 5.4% and 3.2% higher, respectively, than the suboptimal method CRPTS. In addition, we evaluate the classification performance of MulTFBS for distinguishing bound or unbound regions on TF ChIP-seq data. The results show that our framework also performs well in the TFBS classification tasks.
Collapse
Affiliation(s)
- Jujuan Zhuang
- The School of Science, Dalian Maritime University, Dalian 116026, China
| | - Xinru Huang
- The School of Science, Dalian Maritime University, Dalian 116026, China
| | - Shuhan Liu
- The School of Science, Dalian Maritime University, Dalian 116026, China
| | - Wanquan Gao
- The School of Science, Dalian Maritime University, Dalian 116026, China
| | - Rui Su
- The School of Science, Dalian Maritime University, Dalian 116026, China
| | - Kexin Feng
- The School of Science, Dalian Maritime University, Dalian 116026, China
| |
Collapse
|
8
|
Alsini R, Almuhaimeed A, Ali F, Khalid M, Farrash M, Masmoudi A. Deep-VEGF: deep stacked ensemble model for prediction of vascular endothelial growth factor by concatenating gated recurrent unit with two-dimensional convolutional neural network. J Biomol Struct Dyn 2024:1-11. [PMID: 38450715 DOI: 10.1080/07391102.2024.2323144] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2023] [Accepted: 02/16/2024] [Indexed: 03/08/2024]
Abstract
Vascular endothelial growth factor (VEGF) is involved in the development and progression of various diseases, including cancer, diabetic retinopathy, macular degeneration and arthritis. Understanding the role of VEGF in various disorders has led to the development of effective treatments, including anti-VEGF drugs, which have significantly improved therapeutic methods. Accurate VEGF identification is critical, yet experimental identification is expensive and time-consuming. This study presents Deep-VEGF, a novel computational model for VEGF prediction based on deep-stacked ensemble learning. We formulated two datasets using primary sequences. A novel feature descriptor named K-Space Tri Slicing-Bigram position-specific scoring metrix (KSTS-BPSSM) is constructed to extract numerical features from primary sequences. The model training is performed by deep learning techniques, including gated recurrent unit (GRU), generative adversarial network (GAN) and convolutional neural network (CNN). The GRU and CNN are ensembled using stacking learning approach. KSTS-BPSSM-based ensemble model secured the most accurate predictive outcomes, surpassing other competitive predictors across both training and testing datasets. This demonstrates the potential of leveraging deep learning for accurate VEGF prediction as a powerful tool to accelerate research, streamline drug discovery and uncover novel therapeutic targets. This insightful approach holds promise for expanding our knowledge of VEGF's role in health and disease.Communicated by Ramaswamy H. Sarma.
Collapse
Affiliation(s)
- Raed Alsini
- Department of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia
| | - Abdullah Almuhaimeed
- Digital Health Institute, King Abdulaziz City for Science and Technology, Riyadh, Saudi Arabia
| | - Farman Ali
- Sarhad University of Science and Information Technology Peshawar, Mardan Campus, Pakistan
| | - Majdi Khalid
- Department of Computer Science and Artificial Intelligence, College of Computing, Umm Al-Qura University, Makkah, Saudi Arabia
| | - Majed Farrash
- Department of Computer Science and Artificial Intelligence, College of Computing, Umm Al-Qura University, Makkah, Saudi Arabia
| | - Atef Masmoudi
- College of Computer Science, King Khalid University, Abha, Saudi Arabia
| |
Collapse
|
9
|
Zuo Y, Zhang J, He W, Liu X, Deng Z. CarSitePred: an integrated algorithm for identifying carbonylated sites based on KNDUA-LNDOT resampling technique. J Biomol Struct Dyn 2024:1-13. [PMID: 38334134 DOI: 10.1080/07391102.2024.2313712] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2023] [Accepted: 01/27/2024] [Indexed: 02/10/2024]
Abstract
Carbonylated sites are the determining factors for functional changes or deletions in carbonylated proteins, so identifying carbonylated sites is essential for understanding the process of protein carbonylated and exploring the pathogenesis of related diseases. The current wet experimental methods for predicting carbonylated modification sites ae not only expensive and time-consuming, but also have limited protein processing capabilities and cannot meet the needs of researchers. The identification of carbonylated sites using computational methods not only improves the functional characterization of proteins, but also provides researchers with free tools for predicting carbonylated sites. Therefore, it is essential to establish a model using computational methods that can accurately predict protein carbonylated sites. In this study, a prediction model, CarSitePred, is proposed to identify carbonylation sites. In CarSitePred, specific location amino acid hydrophobic hydrophilic, one-to-one numerical conversion of amino acids, and AlexNet convolutional neural networks convert preprocessed carbonylated sequences into valid numerical features. The K-means Normal Distribution-based Undersampling Algorithm (KNDUA) and Localized Normal Distribution Oversampling Technology (LNDOT) were firstly proposed and employed to balance the K, P, R and T carbonylation training dataset. And for the first time, carbonylation modification sites were transformed into the form of images and directly inputted into AlexNet convolutional neural network to extract features for fitting SVM classifiers. The 10-fold cross-validation and independent testing results show that CarSitePred achieves better prediction performance than the best currently available prediction models. Availability: https://github.com/zuoyun123/CarSitePred.Communicated by Ramaswamy H. Sarma.
Collapse
Affiliation(s)
- Yun Zuo
- School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China
| | - Jingrun Zhang
- School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China
| | - Wenying He
- School of Artificial Intelligence, Hebei University of Technology, Tianjin, China
| | - Xiangrong Liu
- Department of Computer Science, Xiamen University, Xiamen, China
| | - Zhaohong Deng
- School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China
| |
Collapse
|