Tiansheng Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tiansheng Tang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Changliang Shan
State Key Laboratory of Medicinal Chemical Biology, College of Pharmacy and Tianjin Key Laboratory of Molecular Drug Research, Nankai University, Tianjin 300350, China
1 shared publication Evelyn Mellisa
Department of Cardiothoracic Surgery, The First Affiliated Hospital of Wannan Medical College, Wuhu, China
1 shared publicationFen Gong
Department of Cardiothoracic Surgery, The First Affiliated Hospital of Wannan Medical College, Wuhu, China
1 shared publication- Hongkai Chang
State Key Laboratory of Medicinal Chemical Biology, College of Pharmacy and Tianjin Key Laboratory of Molecular Drug Research, Nankai University, Tianjin 300350, China
1 shared publication - Jianshi Liu
Department of Cardiovascular Surgery, Tianjin Chest Hospital, Tianjin 300222, China
1 shared publication - Jiyan Wang
State Key Laboratory of Medicinal Chemical Biology, College of Pharmacy and Tianjin Key Laboratory of Molecular Drug Research, Nankai University, Tianjin, China
1 shared publication
Latest Publications
- Open Access
- 12 September 2022
- Published by Frontiers Media SA in Frontiers in Oncology
- Vol. 12, 964605
Invasive ductal breast cancer molecular subtype prediction by MRI radiomic and clinical features based on machine learning
Background: Most studies of molecular subtype prediction in breast cancer were mainly based on two-dimensional MRI images, the predictive value of three-dimensional volumetric features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for predicting breast cancer molecular subtypes has not been thoroughly investigated. This study aimed to look into the role of features derived from DCE-MRI and how they could be combined with clinical data to predict invasive ductal breast cancer molecular subtypes.Methods: From January 2019 to December 2021, 190 Chinese women with invasive ductal breast cancer were studied (32 triple-negative, 59 HER2-enriched, and 99 luminal lesions) in this institutional review board-approved retrospective cohort study. The image processing software extracted 1130 quantitative radiomic features from the segmented lesion area, including shape-based, first-order statistical, texture, and wavelet features. Three binary classifications of the subtypes were performed: triple-negative vs. non-triple-negative, HER2-overexpressed vs. non-HER2-overexpressed, and luminal (A + B) vs. non-luminal. For the classification, five machine learning methods (random forest, logistic regression, support vector machine, naïve Bayes, and eXtreme Gradient Boosting) were employed. The classifiers were chosen using the least absolute shrinkage and selection operator method. The area evaluated classification performance under the receiver operating characteristic curve, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean.Results: EXtreme Gradient Boosting model showed the best performance in luminal and non-luminal groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.8282, 0.7524, 0.6542, 0.6964, 0.6086, 0.3458, 0.8524 and 0.7016, respectively. Meanwhile, the random forest model showed the best performance in HER2-overexpressed and non-HER2-overexpressed groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.8054, 0.2941, 0.9744, 0.7679, 0.4348, 0.0256, 0.8333 and 0.5353, respectively. Furthermore, eXtreme Gradient Boosting model showed the best performance in the triple-negative and non-triple-negative groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.9031, 0.9362, 0.4444, 0.8571, 0.9167, 0.5556, 0.8980 and 0.6450.Conclusion: Clinical data and three-dimension imaging features from DCE-MRI were identified as potential biomarkers for distinguishing between three molecular subtypes of invasive ductal carcinomas breast cancer. In the future, more extensive studies will be required to evaluate the findings.
- 12 September 2022
- Published by Frontiers Media SA in Frontiers in Oncology
- Vol. 12, 964605
Open AccessInvasive ductal breast cancer molecular subtype prediction by MRI radiomic and clinical features based on machine learning
Background: Most studies of molecular subtype prediction in breast cancer were mainly based on two-dimensional MRI images, the predictive value of three-dimensional volumetric features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for predicting breast cancer molecular subtypes has not been thoroughly investigated. This study aimed to look into the role of features derived from DCE-MRI and how they could be combined with clinical data to predict invasive ductal breast cancer molecular subtypes.Methods: From January 2019 to December 2021, 190 Chinese women with invasive ductal breast cancer were studied (32 triple-negative, 59 HER2-enriched, and 99 luminal lesions) in this institutional review board-approved retrospective cohort study. The image processing software extracted 1130 quantitative radiomic features from the segmented lesion area, including shape-based, first-order statistical, texture, and wavelet features. Three binary classifications of the subtypes were performed: triple-negative vs. non-triple-negative, HER2-overexpressed vs. non-HER2-overexpressed, and luminal (A + B) vs. non-luminal. For the classification, five machine learning methods (random forest, logistic regression, support vector machine, naïve Bayes, and eXtreme Gradient Boosting) were employed. The classifiers were chosen using the least absolute shrinkage and selection operator method. The area evaluated classification performance under the receiver operating characteristic curve, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean.Results: EXtreme Gradient Boosting model showed the best performance in luminal and non-luminal groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.8282, 0.7524, 0.6542, 0.6964, 0.6086, 0.3458, 0.8524 and 0.7016, respectively. Meanwhile, the random forest model showed the best performance in HER2-overexpressed and non-HER2-overexpressed groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.8054, 0.2941, 0.9744, 0.7679, 0.4348, 0.0256, 0.8333 and 0.5353, respectively. Furthermore, eXtreme Gradient Boosting model showed the best performance in the triple-negative and non-triple-negative groups, with AUC, sensitivity, specificity, accuracy, F1-Score, false positive rate, precision, and geometric mean of 0.9031, 0.9362, 0.4444, 0.8571, 0.9167, 0.5556, 0.8980 and 0.6450.Conclusion: Clinical data and three-dimension imaging features from DCE-MRI were identified as potential biomarkers for distinguishing between three molecular subtypes of invasive ductal carcinomas breast cancer. In the future, more extensive studies will be required to evaluate the findings.
- Open Access
PRIM2 Promotes Cell Cycle and Tumor Progression in p53-Mutant Lung Cancer
P53 is a common tumor suppressor, and its mutation drives tumorigenesis. What is more, p53 mutations have also been reported to be indicative of poor prognosis in lung cancer, but the detailed mechanism has not been elucidated. In this study, we found that DNA primase subunit 2 (PRIM2) had a high expression level and associated with poor prognosis in lung cancer. Furthermore, we found that PRIM2 expression was abnormally increased in lung cancer cells with p53 mutation or altered the p53/RB pathway based on database. We also verified that PRIM2 expression was elevated by mutation or deletion of p53 in lung cancer cell lines. Lastly, silence p53 increased the expression of RPIM2. Thus, these data suggest that PRIM2 is a cancer-promoting factor which is regulated by the p53/RB pathway. The p53 tumor-suppressor gene integrates numerous signals that control cell proliferation, cell cycle, and cell death; and the p53/RB pathway determines the cellular localization of transcription factor E2F, which regulates the expression of downstream targets. Next, we explored the role of PRIM2 in lung cancer and found that knockdown of PRIM2 induced cell cycle arrest, increased DNA damage, and increased cell senescence, leading to decreased lung cancer cell proliferation. Lastly, the positive correlation between PRIM2 and E2F/CDK also indicated that PRIM2 was involved in promoting cell cycle mediated by p53/RB pathway. These results confirmed that the expression of PRIM2 is regulated by the p53/RB pathway in lung cancer cells, promotes DNA replication and mismatch repair, and activates the cell cycle. Overall, we found that frequent p53 mutations increased PRIM2 expression, activated the cell cycle, and promoted lung cancer progression.
Open AccessPRIM2 Promotes Cell Cycle and Tumor Progression in p53-Mutant Lung Cancer
P53 is a common tumor suppressor, and its mutation drives tumorigenesis. What is more, p53 mutations have also been reported to be indicative of poor prognosis in lung cancer, but the detailed mechanism has not been elucidated. In this study, we found that DNA primase subunit 2 (PRIM2) had a high expression level and associated with poor prognosis in lung cancer. Furthermore, we found that PRIM2 expression was abnormally increased in lung cancer cells with p53 mutation or altered the p53/RB pathway based on database. We also verified that PRIM2 expression was elevated by mutation or deletion of p53 in lung cancer cell lines. Lastly, silence p53 increased the expression of RPIM2. Thus, these data suggest that PRIM2 is a cancer-promoting factor which is regulated by the p53/RB pathway. The p53 tumor-suppressor gene integrates numerous signals that control cell proliferation, cell cycle, and cell death; and the p53/RB pathway determines the cellular localization of transcription factor E2F, which regulates the expression of downstream targets. Next, we explored the role of PRIM2 in lung cancer and found that knockdown of PRIM2 induced cell cycle arrest, increased DNA damage, and increased cell senescence, leading to decreased lung cancer cell proliferation. Lastly, the positive correlation between PRIM2 and E2F/CDK also indicated that PRIM2 was involved in promoting cell cycle mediated by p53/RB pathway. These results confirmed that the expression of PRIM2 is regulated by the p53/RB pathway in lung cancer cells, promotes DNA replication and mismatch repair, and activates the cell cycle. Overall, we found that frequent p53 mutations increased PRIM2 expression, activated the cell cycle, and promoted lung cancer progression.