Lian Liu

Dr. Lian Liu


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 September 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
MWMengdi Wang
Mengdi Wang
XLXiujuan Lei
Xiujuan Lei
LLLian Liu
Lian Liu
JCJianrui Chen
Jianrui Chen
FWFangXiang Wu
FangXiang Wu
Accurate prediction of drug-target interactions (DTIs) is essential for advancing drug discovery and repurposing. However, the sparsity of DTI data limits the effectiveness of existing computational methods, which primarily focus on sparse DTI networks and have poor performance in aggregating information from neighboring nodes and representing isolated nodes within the network. In this study, we propose a novel deep learning framework, named GIAE-DTI, which considers cross-modal similarity of drugs and targets and constructs a heterogeneous network for DTI prediction. Firstly, the model calculates the cross-modal similarity of drugs and proteins from the relationships among drugs, proteins, diseases, and side effects, and performs similarity integration by taking the average. Then, a drug-target heterogeneous network is constructed, including drug-drug interactions, protein-protein interactions, and drug-target interactions processed by weighted K nearest known neighbors. In the heterogeneous network, a graph autoencoder based on a graph isomorphism network is employed for feature extraction, while a dual decoder is utilized to achieve better self-supervised learning, resulting in latent feature representations for drugs and targets. Finally, a deep neural network is employed to predict DTIs. The experimental results indicate that on the benchmark dataset, GIAE-DTI achieves AUC and AUPR scores of 0.9533 and 0.9619, respectively, in DTI prediction, outperforming the current state-of-the-art methods. Additionally, case studies on four 5-hydroxytryptamine receptor-related targets and five drugs related to mental diseases show the great potential of the proposed method in practical applications.

28 April 2020 in IEEE Access
Verified
Journal Article
Open access
LLLian Liu
Lian Liu
XLXiujuan Lei
Xiujuan Lei
JMJia Meng
Jia Meng
ZWZhen Wei
Zhen Wei
As a new epitranscriptomic modification, N1-methyladenosine (m 1 A) plays an important role in the gene expression regulation. Although some computational methods were proposed to predict m 1 A modification sites, all of these methods apply machine learning predictions based on the nucleotide sequence features, and they missed the layer of information in transcript topology and RNA secondary structures. To enhance the prediction model of m 1 A RNA methylation, we proposed a computational framework, ISGm1A, which stands for integration sequence features and genomic features to improve the prediction of human m 1 A RNA methylation sites. Based on the random forest algorithm, ISGm1A takes advantage of both conventional sequence features and 75 genomic characteristics to improve the prediction performance of m 1 A sites in human. The results of five-fold cross validation and independent test show that ISGm1A outperforms other prediction algorithms (AUC = 0.903 and 0.909). In addition, through analyzing the importance of features, we found that the genomic features play a more important role in site prediction than the sequence features. Furthermore, with ISGm1A, we generated a high accuracy map of m 1 A by predicting all adenines sites in the transcriptome. The data and the results of the study are freely accessible at: https://github.com/lianliu09/m1a_prediction.git.

6 December 2023 in PLOS Computational Biology
Verified
Journal Article
Open access
PDF file
LLLian Liu
Lian Liu
YZYumeng Zhou
Yumeng Zhou
XLXiujuan Lei
Xiujuan Lei
RNA modification is a post transcriptional modification that occurs in all organisms and plays a crucial role in the stages of RNA life, closely related to many life processes. As one of the newly discovered modifications, N1-methyladenosine (m1A) plays an important role in gene expression regulation, closely related to the occurrence and development of diseases. However, due to the low abundance of m1A, verifying the associations between m1As and diseases through wet experiments requires a great quantity of manpower and resources. In this study, we proposed a computational method for predicting the associations ofRNAmethylation anddisease based ongraphconvolutionalnetwork (RMDGCN) with attention mechanism. We build an adjacency matrix through the collected m1As and diseases associations, and use positive-unlabeled learning to increase the number of positive samples. By extracting the features of m1As and diseases, a heterogeneous network is constructed, and a GCN with attention mechanism is adopted to predict the associations between m1As and diseases. The experimental results indicate that under a 5-fold cross validation, RMDGCN is superior to other methods (AUC = 0.9892 and AUPR = 0.8682). In addition, case studies indicate that RMDGCN can predict the relationships between unknown m1As and diseases. In summary, RMDGCN is an effective method for predicting the associations between m1As and diseases.

2 December 2024 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
LGLin Guo
Lin Guo
XLXiujuan Lei
Xiujuan Lei
LLLian Liu
Lian Liu
MCMing Chen
Ming Chen
YPYi Pan
Yi Pan
Drug-Drug Interaction is characterized by a modification in the action of one drug due to its concurrent use with another. It involves the safety and universality of drugs, and is one of the most meaningful issues in clinical drug combination therapy and drug development. We prefer to use computational methods to achieve DDI prediction in order to achieve large-scale prediction. This article designs a DDI prediction model DualC based on the layer attention mechanism of Graph Convolutional Network and 1 Dimensional-Convolutional Neural Network to extract topological and structural information of drugs. First, the DDI network is obtained from the drug relationship data in the database and the drug similarity network is calculated with the help of drug target features, then they are constructed into a heterogeneous network. Next, the layer attention mechanism and Graph Convolutional Network are used to learn the topological information. Subsequently, the structural information is acquired from the chemical substructure similarity matrix utilizing 1 Dimensional-Convolutional Neural Network. Finally, use the sigmoid function for DDI prediction. The experimental results show advantages of DualC which AUC reaches 0.965 and ACC reaches 0.973. The case study further proves DualC has certain practical significance.

2 June 2025 in Interdisciplinary Sciences: Computational Life Sciences
Verified
Journal Article
Closed access
PDF file
XTXin Tang
Xin Tang
XLXiujuan Lei
Xiujuan Lei
LLLian Liu
Lian Liu

27 May 2025 in Frontiers in Genetics
Verified
Journal Article
Open access
PDF file
LBLei Bai
Lei Bai
FLFei Liu
Fei Liu
YWYile Wang
Yile Wang
JSJunle Su
Junle Su
LLLian Liu
Lian Liu
As a crucial class of chemical modifications, 2′-O-methylation modification (abbreviated as Nm) is widely distributed in various organisms and plays a very important role in normal cellular physiological activities and the occurrence and development of diseases. Accurate prediction of Nm modification sites can provide important references for the diagnosis and treatment of diseases, as well as identifying for potential drug targets. Aiming at the current problems of unstable performance caused by the use of single features and the need to improve the prediction accuracy of Nm modification sites, this paper proposes MultiV_Nm, a prediction method for Nm sites based on multi-view features. MultiV_Nm extracts the features of Nm sites from multiple dimensions, including sequence features, chemical characteristics, and secondary structure features. By integrating the powerful local feature extraction ability of convolutional neural networks, the ability of graph attention networks to capture global structural information, and the efficient interaction advantage of cross-attention mechanisms for different features, it deeply explores and integrates multi-view features, and finally realizes the prediction of Nm modification sites. The results of cross-validation and independent tests show that this method exhibits significant advantages in key evaluation indicators such as precision, recall, and accuracy, and can effectively improve Nm sites prediction performance. The proposal of MultiV_Nm not only provides a powerful tool for the study of Nm modification but also offers new ideas for predicting other RNA modification sites.