Yen-Wei Chu1,2,3,4,5,6*
Chi-Chang Chang7,8- 1Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung, Taiwan
- 2Institute of Molecular Biology, National Chung Hsing University, Taichung, Taiwan
- 3Agricultural Biotechnology Center, National Chung Hsing University, Taichung, Taiwan
- 4Ph. D. Program in Translational Medicine, National Chung Hsing University, Taichung, Taiwan
- 5Rong Hsing Research Center for Translational Medicine, Taichung, Taiwan
- 6Ph. D Program in Medical Biotechnology, National Chung Hsing University, Taichung, Taiwan
- 7School of Medical Informatics, Chung Shan Medical University & IT Office, Chung Shan Medical University Hospital, Taichung City, Taiwan
- 8Department of Information Management, Ming Chuan University, Taoyuan City, Taiwan
Editorial on the Research Topic
Using physical & genomics markers for smart therapy via expert systems with computer learning
Cancer diagnosis, prognosis, and treatment stand as pivotal factors in enhancing patient outcomes. Recent advances in AI, deep learning, and genomics are reshaping cancer research (Bhinder et al., 2021; Luchini et al., 2022). The integration of physical and genomics markers is essential for smart therapy. This is achieved through expert systems with computer learning (Chen et al., 2022; Deng et al., 2022; Ma et al., 2022; Chen et al., 2023; Sidorenkov et al., 2023).
Research in this domain has spotlighted predictive modeling and cancer biomarkers, demonstrating the application of machine learning in predicting malignancy and metastasis across various cancers, including lung and colorectal cancers (Ma et al., 2022; Wang et al., 2022; Mu et al., 2023). Furthermore, the emergence of novel combined models, integrating deep learning-pathomics and radiomics, holds promise in predicting postoperative outcomes in cancer patients (Wang et al., 2022).
Machine learning and whole-evidence analysis have facilitated comprehensive evaluation in cancer research. Studies focusing on lung cancer screening and hepatocellular carcinoma prognosis have enhanced screening and prognostic accuracy (Deng et al., 2022; Sidorenkov et al., 2023). Additionally, deep learning-based systems have demonstrated expert-level accuracy in delineating head and neck lymph node levels, contributing to advancements in radiotherapy research (Weissmann et al., 2023).
The investigation of cancer stem cells and their involvement in tumorigenesis has gained significant attention. Studies in this field have delved into the exploration of prognostic long non-coding RNAs (lncRNAs) and the development of deep learning models for early cancer diagnosis. These efforts underscore the critical importance of integrating both physical and genomic markers in treatment planning (Al Mamun et al., 2021).
In a stride toward addressing technical challenges in single-cell RNA-Seq data analysis, Huang et al. pioneered a novel approach integrating low-rank matrix completion for missing value imputation. Their work not only enhanced the accuracy of intratumor heterogeneity analysis but also laid a foundation for precise interpretations within the intricate landscape of cancer biology.
A pivotal study by Zhou et al. illuminated the significance of an immune-related prognostic signature in predicting the clinical outcomes and tumor immunity of stomach adenocarcinomas (STAD). Their findings underscored the pivotal role of immune cell infiltration, unveiling distinctive clusters of “hot” and “cold” tumors with divergent clinical trajectories, while identifying key genes, such as PEG10, DKK1, and RGS1, as critical prognostic markers.
Genes exert a significant impact not only on cancer but also on the development of various other diseases. Chuang et al. delved into the genetic nuances of diabetic retinopathy, shedding light on the influence of genetic variants of the lncRNA LINC00673 on disease susceptibility. Their exploration unveiled associations between specific LINC00673 single nucleotide polymorphisms (SNPs) and the development of non-proliferative diabetic retinopathy (NPDR), providing crucial insights into the genetic underpinnings of this complex ocular condition.
In parallel, Hsieh and Li harnessed the potential of image recognition techniques to rectify data imbalances in genetic disease research, spotlighting the transformative role of Synthetic Minority Oversampling Technique (SMOTE) in restoring data integrity within human biobanks. Their study streamlined data processing and facilitated more robust analysis and interpretation of genetic datasets.
In summary, these groundbreaking studies demonstrate the transformative potential of integrating physical and genomic markers into intelligent therapy systems, fortified by cutting-edge computational technologies. By fostering a collaborative and interdisciplinary approach that promotes scientific excellence, societal inclusivity, and ethical healthcare practices, we pave the way for a future where personalized medicine is not just a vision but a tangible reality accessible to all.
Author contributions
Y-WC: Writing–original draft, Writing–review and editing. C-CC: Writing–original draft.
Funding
The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This research was supported by (1) the National Science and Technology Council, Taiwan, under grant number 110-2221-E-005-062-MY3, 111-2221-E-005-073-MY3, 111-2423-H-006 -002 -MY3, and 112-2321-B-006 -013 (2) Smart Sustainable New Agriculture Research Center (SMARTer) 111-2634-F-005-001.
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher’s note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
Al Mamun, A., Tanvir, R. B., Sobhan, M., Mathee, K., Narasimhan, G., Holt, G. E., et al. (2021). Multi-run concrete autoencoder to identify prognostic lncRNAs for 12 cancers. Int. J. Mol. Sci. 22 (21), 11919. doi:10.3390/ijms222111919
Bhinder, B., Gilvary, C., Madhukar, N. S., and Elemento, O. (2021). Artificial intelligence in cancer research and precision medicine. Cancer Discov. 11 (4), 900–915. doi:10.1158/2159-8290.CD-21-0090
Chen, T., Hu, L., Lu, Q., Xiao, F., Xu, H., Li, H., et al. (2023). A computer-aided diagnosis system for brain tumors based on artificial intelligence algorithms. Front. Neurosci. 17, 1120781. doi:10.3389/fnins.2023.1120781
Chen, W., Gong, M., Zhou, D., Zhang, L., Kong, J., Jiang, F., et al. (2022). CT-based deep learning radiomics signature for the preoperative prediction of the muscle-invasive status of bladder cancer. Front. Oncol. 12, 1019749. doi:10.3389/fonc.2022.1019749
Deng, P. Z., Zhao, B. G., Huang, X. H., Xu, T. F., Chen, Z. J., Wei, Q. F., et al. (2022). Preoperative contrast-enhanced computed tomography-based radiomics model for overall survival prediction in hepatocellular carcinoma. World J. Gastroenterol. 28 (31), 4376–4389. doi:10.3748/wjg.v28.i31.4376
Luchini, C., Pea, A., and Scarpa, A. (2022). Artificial intelligence in oncology: current applications and future perspectives. Br. J. Cancer 126 (1), 4–9. doi:10.1038/s41416-021-01633-1
Ma, M., Gan, L., Liu, Y., Jiang, Y., Xin, L., Liu, Y., et al. (2022). Radiomics features based on automatic segmented MRI images: prognostic biomarkers for triple-negative breast cancer treated with neoadjuvant chemotherapy. Eur. J. Radiol. 146, 110095. doi:10.1016/j.ejrad.2021.110095
Mu, J., Kuang, K., Ao, M., Li, W., Dai, H., Ouyang, Z., et al. (2023). Deep learning predicts malignancy and metastasis of solid pulmonary nodules from CT scans. Front. Med. (Lausanne) 10, 1145846. doi:10.3389/fmed.2023.1145846
Sidorenkov, G., Stadhouders, R., Jacobs, C., Mohamed Hoesein, F. A. A., Gietema, H. A., Nackaerts, K., et al. (2023). Multi-source data approach for personalized outcome prediction in lung cancer screening: update from the NELSON trial. Eur. J. Epidemiol. 38 (4), 445–454. doi:10.1007/s10654-023-00975-9
Wang, R., Dai, W., Gong, J., Huang, M., Hu, T., Li, H., et al. (2022). Development of a novel combined nomogram model integrating deep learning-pathomics, radiomics and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients. J. Hematol. Oncol. 15 (1), 11. doi:10.1186/s13045-022-01225-3
Keywords: predictive modeling, cancer biomarkers, machine learning, whole-evidence, cancer stem cells
Citation: Chu Y-W and Chang C-C (2023) Editorial: Using physical & genomics markers for smart therapy via expert systems with computer learning. Front. Genet. 14:1336399. doi: 10.3389/fgene.2023.1336399
Received: 10 November 2023; Accepted: 21 November 2023;
Published: 28 November 2023.
Edited and reviewed by:
Richard D. Emes, Nottingham Trent University, United KingdomCopyright © 2023 Chu and Chang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Yen-Wei Chu, eXdjaHVAbmNodS5lZHUudHc=