Tianjun Li

Tianjun Li

Auto-generated profile, based on publicly available information

Tianjun Li

Department of Computer and Information Science, University of Macau, Taipa, Macau, China

Research Focus & Metrics

Academic Career Length

26Years (2001-Present)

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

Representative Publications

View All Publications
22 April 2023 in Information Sciences
Verified
Journal Article
Closed access
YWYingxu Wang
Yingxu Wang
LCLong Chen
Long Chen
JZJin Zhou
Jin Zhou
TLTianjun Li
Tianjun Li
YYYufeng Yu
Yufeng Yu

16 July 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YWYingxu Wang
Yingxu Wang
TLTianjun Li
Tianjun Li
LCLong Chen
Long Chen
YYYufeng Yu
Yufeng Yu
YZYinping Zhao
Yinping Zhao
JZJin Zhou
Jin Zhou
Tensor-based robust principal component analysis (PCA) methods are efficient to discover the low-rank part of a hyperspectral image for reducing redundant information and guarantee good classification results. However, current methods cannot remove noise adequately, and the residual noise remaining in the low-rank image limits the further improvement of classification performance. Thus, enhancing the robustness to noise is important and helpful for tensor-based robust PCA (RPCA) methods to process hyperspectral images. To this end, we propose a tensor-based RPCA method with a locality preserving graph and frontal slice sparsity (LPGTRPCA) for hyperspectral image classification. Specifically, a tensor $l_{2,2,1}$ norm that requires the frontal slice sparsity of a tensor is defined to extract the noise in the hyperspectral image from the frontal direction. What is more, a position-based Laplacian graph that preserves the local structures of a tensor according to the spatial position is designed for relieving the impact of the residual noise remaining in the low-rank image. Based on the tensor nuclear norm, the tensor $l_{2,2,1}$ norm, and the position-based Laplacian graph, LPGTRPCA efficiently separates the low-rank part with little noise from a raw hyperspectral image and achieves more robust classification results than current methods. LPGTRPCA is optimized by the alternative direction multiplier method (ADMM), and the convergence of solutions is experimentally demonstrated. In the experiments conducted on Indian Pines, Pavia University, and Salinas datasets, LPGTRPCA outperformed various state-of-the-art and classical tensor-based RPCA methods in terms of average class classification accuracy (AA), overall classification accuracy (OA), and kappa coefficient (KC).

1 August 2019 in Translational Lung Cancer Research
Verified
Journal Article
Open access
PDF file
MJMan Jiang
Man Jiang
CZChuantao Zhang
Chuantao Zhang
DLDong Liu
Dong Liu
YWYongjie Wang
Yongjie Wang
HWHongmei Wang
Hongmei Wang
XZXiao chun Zhang
Xiao chun Zhang
Background: Antiangiogenic agent-treated patients usually develop cavitation in their lung lesions. The clinical significance of lung cavitation development during antiangiogenic therapy has not been determined yet. Herein, we evaluated the clinical outcomes of patients who developed tumor cavitation following apatinib treatment and explored the mechanisms. Methods: In this study (Clinical Trial No. NCT03629691), 187 patients (77 lung cancer and 110 gastric adenocarcinoma patients) who had progressed or relapsed after undergoing at least two lines of systemic therapy in accordance with the NCCN guidelines for primary or metastatic lung tumors were treated with apatinib at a dosage of 250 mg per day between February 1, 2015 and May 19, 2017. The effect of lung cavitation development on locoregional control (LRC), progression-free survival (PFS), and overall survival (OS) was analyzed with Kaplan-Meier estimates and compared with the log-rank test. Zebrafish experiments were used to study the anticancer mechanism of apatinib in different tumors. Western-blotting was used to analyze the expression of Cyclin D1, p53, HIF-α, and VEGFR before and after apatinib treatment in both normoxia and hypoxia. Results: Cavitation development was beneficial in patients receiving apatinib therapy regardless of whether they had primary or metastatic lung cancer. Zebrafish experiments showed that apatinib inhibited tumor growth by both suppressing vascular growth and inhibiting cell proliferation. Vascular proliferation induced by the H1299 cell lines showed higher sensitivity to apatinib than that induced by the SCG-7901 cell line. However, apatinib showed weak tumor type selectivity on cell proliferation inhibition in vivo. Under hypoxic conditions, apatinib could not inhibit the protein expression of VEGFR and HIF-α in both cell lines; however, apatinib decreased the expression of cyclin D1 and P53 significantly. Conclusions: Lung cavitation development is common with apatinib therapy and is a potential prognostic marker. Apatinib inhibits tumor growth by both vessel growth inhibition and proliferation inhibition.

1 November 2021 in Applied Soft Computing
Verified
Journal Article
Closed access
YWYingxu Wang
Yingxu Wang
TLTianjun Li
Tianjun Li
LCLong Chen
Long Chen
GXGuangmei Xu
Guangmei Xu
JZJin Zhou
Jin Zhou
CCC. L. Philip Chen
C. L. Philip Chen

6 November 2019 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
TLTianjun Li
Tianjun Li
LCLong Chen
Long Chen
MGMin Gan
Min Gan
Background: Mass spectra are usually acquired from the Liquid Chromatography-Mass Spectrometry (LC-MS) analysis for isotope labeled proteomics experiments. In such experiments, the mass profiles of labeled (heavy) and unlabeled (light) peptide pairs are represented by isotope clusters (2D or 3D) that provide valuable information about the studied biological samples in different conditions. The core task of quality control in quantitative LC-MS experiment is to filter out low-quality peptides with questionable profiles. The commonly used methods for this problem are the classification approaches. However, the data imbalance problems in previous control methods are often ignored or mishandled. In this study, we introduced a quality control framework based on the extreme gradient boosting machine (XGBoost), and carefully addressed the imbalanced data problem in this framework. Results: In the XGBoost based framework, we suggest the application of the Synthetic minority over-sampling technique (SMOTE) to re-balance data and use the balanced data to train the boosted trees as the classifier. Then the classifier is applied to other data for the peptide quality assessment. Experimental results show that our proposed framework increases the reliability of peptide heavy-light ratio estimation significantly. Conclusions: Our results indicate that this framework is a powerful method for the peptide quality assessment. For the feature extraction part, the extracted ion chromatogram (XIC) based features contribute to the peptide quality assessment. To solve the imbalanced data problem, SMOTE brings a much better classification performance. Finally, the XGBoost is capable for the peptide quality control. Overall, our proposed framework provides reliable results for the further proteomics studies.

1 December 2017
Verified
Conference Paper
Closed access
LCLong Chen
Long Chen
TZTong Zhang
Tong Zhang
TLTianjun Li
Tianjun Li
A method for controlling the quality of isotope labeled mass spectra is described here. In such mass spectra, the profiles of labeled (heavy) and unlabeled (light) peptide pairs provide us valuable information about the studied biological samples in different conditions. The core task of quality control in quantitative LC-MS experiment is to filter out low quality spectra or the peptides with error profiles. The most common used method for this problem is training a classifier for the spectra data to separate it into positive (high quality) and negative (low quality) ones. However, the small number of error profiles always makes the training data dominated by the positive samples, i.e., class imbalance problem. So the Syntheic minority over-sampling technique (SMOTE) is employed to handle the unbalanced data and then applied extreme gradient boosting (Xgboost) model as the classifier. We assessed the different heavy-light peptide ratio samples by the trained Xgboost classifier, and found that the SMOTE Xgboost classifier increases the reliability of peptide ratio estimations significantly.