1
|
Tran TO, Vo TH, Le NQK. Omics-based deep learning approaches for lung cancer decision-making and therapeutics development. Brief Funct Genomics 2024; 23:181-192. [PMID: 37519050 DOI: 10.1093/bfgp/elad031] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2023] [Revised: 07/04/2023] [Accepted: 07/13/2023] [Indexed: 08/01/2023] Open
Abstract
Lung cancer has been the most common and the leading cause of cancer deaths globally. Besides clinicopathological observations and traditional molecular tests, the advent of robust and scalable techniques for nucleic acid analysis has revolutionized biological research and medicinal practice in lung cancer treatment. In response to the demands for minimally invasive procedures and technology development over the past decade, many types of multi-omics data at various genome levels have been generated. As omics data grow, artificial intelligence models, particularly deep learning, are prominent in developing more rapid and effective methods to potentially improve lung cancer patient diagnosis, prognosis and treatment strategy. This decade has seen genome-based deep learning models thriving in various lung cancer tasks, including cancer prediction, subtype classification, prognosis estimation, cancer molecular signatures identification, treatment response prediction and biomarker development. In this study, we summarized available data sources for deep-learning-based lung cancer mining and provided an update on recent deep learning models in lung cancer genomics. Subsequently, we reviewed the current issues and discussed future research directions of deep-learning-based lung cancer genomics research.
Collapse
Affiliation(s)
- Thi-Oanh Tran
- International Ph.D. Program in Cell Therapy and Regenerative Medicine, College of Medicine, Taipei Medical University, No 250 Wuxing Street, 110, Taipei, Taiwan
- AIBioMed Research Group, Taipei Medical University, No 250 Wuxing Street, 110, Taipei, Taiwan
- Hematology and Blood Transfusion Center, Bach Mai Hospital, No 78 Giai Phong Street, Hanoi, Viet Nam
| | - Thanh Hoa Vo
- Department of Science, School of Science and Computing, South East Technological University, Waterford X91 K0EK, Ireland
- Pharmaceutical and Molecular Biotechnology Research Center (PMBRC), South East Technological University, Waterford X91 K0EK, Ireland
| | - Nguyen Quoc Khanh Le
- Professional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, 250 Wuxing Street, 110, Taipei, Taiwan
- AIBioMed Research Group, Taipei Medical University, No 250 Wuxing Street, 110, Taipei, Taiwan
- Research Center for Artificial Intelligence in Medicine, Taipei Medical University, 250 Wuxing Street, 110, Taipei, Taiwan
- Translational Imaging Research Center, Taipei Medical University Hospital, 252 Wuxing Street, 110, Taipei, Taiwan
| |
Collapse
|
2
|
Arigoni M, Ratto ML, Riccardo F, Balmas E, Calogero L, Cordero F, Beccuti M, Calogero RA, Alessandri L. A single cell RNAseq benchmark experiment embedding "controlled" cancer heterogeneity. Sci Data 2024; 11:159. [PMID: 38307867 PMCID: PMC10837414 DOI: 10.1038/s41597-024-03002-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2023] [Accepted: 01/25/2024] [Indexed: 02/04/2024] Open
Abstract
Single-cell RNA sequencing (scRNA-seq) has emerged as a vital tool in tumour research, enabling the exploration of molecular complexities at the individual cell level. It offers new technical possibilities for advancing tumour research with the potential to yield significant breakthroughs. However, deciphering meaningful insights from scRNA-seq data poses challenges, particularly in cell annotation and tumour subpopulation identification. Efficient algorithms are therefore needed to unravel the intricate biological processes of cancer. To address these challenges, benchmarking datasets are essential to validate bioinformatics methodologies for analysing single-cell omics in oncology. Here, we present a 10XGenomics scRNA-seq experiment, providing a controlled heterogeneous environment using lung cancer cell lines characterised by the expression of seven different driver genes (EGFR, ALK, MET, ERBB2, KRAS, BRAF, ROS1), leading to partially overlapping functional pathways. Our dataset provides a comprehensive framework for the development and validation of methodologies for analysing cancer heterogeneity by means of scRNA-seq.
Collapse
Affiliation(s)
- Maddalena Arigoni
- Department of Molecular Biotechnology and Health Sciences, University of Torino, Torino, Italy
| | - Maria Luisa Ratto
- Department of Molecular Biotechnology and Health Sciences, University of Torino, Torino, Italy
| | - Federica Riccardo
- Department of Molecular Biotechnology and Health Sciences, University of Torino, Torino, Italy
| | - Elisa Balmas
- Department of Molecular Biotechnology and Health Sciences, University of Torino, Torino, Italy
| | - Lorenzo Calogero
- Department of Electronics and Telecommunications (DET), Politecnico di Torino, Torino, Italy
| | | | - Marco Beccuti
- Department of Computer Science, University of Torino, Torino, Italy
| | - Raffaele A Calogero
- Department of Molecular Biotechnology and Health Sciences, University of Torino, Torino, Italy.
| | - Luca Alessandri
- Department of Molecular Biotechnology and Health Sciences, University of Torino, Torino, Italy
| |
Collapse
|
3
|
Yin X, Liao H, Yun H, Lin N, Li S, Xiang Y, Ma X. Artificial intelligence-based prediction of clinical outcome in immunotherapy and targeted therapy of lung cancer. Semin Cancer Biol 2022; 86:146-159. [PMID: 35963564 DOI: 10.1016/j.semcancer.2022.08.002] [Citation(s) in RCA: 25] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Revised: 08/06/2022] [Accepted: 08/08/2022] [Indexed: 11/26/2022]
Abstract
Lung cancer accounts for the main proportion of malignancy-related deaths and most patients are diagnosed at an advanced stage. Immunotherapy and targeted therapy have great advances in application in clinics to treat lung cancer patients, yet the efficacy is unstable. The response rate of these therapies varies among patients. Some biomarkers have been proposed to predict the outcomes of immunotherapy and targeted therapy, including programmed cell death-ligand 1 (PD-L1) expression and oncogene mutations. Nevertheless, the detection tests are invasive, time-consuming, and have high demands on tumor tissue. The predictive performance of conventional biomarkers is also unsatisfactory. Therefore, novel biomarkers are needed to effectively predict the outcomes of immunotherapy and targeted therapy. The application of artificial intelligence (AI) can be a possible solution, as it has several advantages. AI can help identify features that are unable to be used by humans and perform repetitive tasks. By combining AI methods with radiomics, pathology, genomics, transcriptomics, proteomics, and clinical data, the integrated model has shown predictive value in immunotherapy and targeted therapy, which significantly improves the precision treatment of lung cancer patients. Herein, we reviewed the application of AI in predicting the outcomes of immunotherapy and targeted therapy in lung cancer patients, and discussed the challenges and future directions in this field.
Collapse
Affiliation(s)
- Xiaomeng Yin
- Division of Biotherapy, Cancer Center, West China Hospital and State Key Laboratory of Biotherapy, Sichuan University, No. 37 GuoXue Alley, Chengdu 610041, China
| | - Hu Liao
- Department of Thoracic Surgery, West China Hospital, Sichuan University, No. 37 GuoXue Alley, Chengdu 610041, China
| | - Hong Yun
- Division of Biotherapy, Cancer Center, West China Hospital and State Key Laboratory of Biotherapy, Sichuan University, No. 37 GuoXue Alley, Chengdu 610041, China
| | - Nan Lin
- Division of Biotherapy, Cancer Center, West China Hospital and State Key Laboratory of Biotherapy, Sichuan University, No. 37 GuoXue Alley, Chengdu 610041, China
| | - Shen Li
- West China School of Medicine, West China Hospital, Sichuan University, No. 37 GuoXue Alley, Chengdu 610041, China
| | - Yu Xiang
- Division of Biotherapy, Cancer Center, West China Hospital and State Key Laboratory of Biotherapy, Sichuan University, No. 37 GuoXue Alley, Chengdu 610041, China
| | - Xuelei Ma
- Division of Biotherapy, Cancer Center, West China Hospital and State Key Laboratory of Biotherapy, Sichuan University, No. 37 GuoXue Alley, Chengdu 610041, China.
| |
Collapse
|
4
|
Kang M, Oh JH. Editorial of Special Issue "Deep Learning and Machine Learning in Bioinformatics". Int J Mol Sci 2022; 23:ijms23126610. [PMID: 35743052 PMCID: PMC9224509 DOI: 10.3390/ijms23126610] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2022] [Accepted: 06/10/2022] [Indexed: 02/04/2023] Open
Abstract
In recent years, deep learning has emerged as a highly active research field, achieving great success in various machine learning areas, including image processing, speech recognition, and natural language processing, and now rapidly becoming a dominant tool in biomedicine [...].
Collapse
Affiliation(s)
- Mingon Kang
- Department of Computer Science, University of Nevada, Las Vegas, NV 89154, USA;
| | - Jung Hun Oh
- Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA
- Correspondence:
| |
Collapse
|
5
|
Cerqua M, Botti O, Arigoni M, Gioelli N, Serini G, Calogero R, Boccaccio C, Comoglio PM, Altintas DM. MET∆14 promotes a ligand-dependent, AKT-driven invasive growth. Life Sci Alliance 2022; 5:5/10/e202201409. [PMID: 35636967 PMCID: PMC9152130 DOI: 10.26508/lsa.202201409] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2022] [Revised: 05/13/2022] [Accepted: 05/17/2022] [Indexed: 11/24/2022] Open
Abstract
MET is an oncogene encoding the tyrosine kinase receptor for hepatocyte growth factor (HGF). Upon ligand binding, MET activates multiple signal transducers, including PI3K/AKT, STAT3, and MAPK. When mutated or amplified, MET becomes a "driver" for the onset and progression of cancer. The most frequent mutations in the MET gene affect the splicing sites of exon 14, leading to the deletion of the receptor's juxtamembrane domain (MET∆14). It is currently believed that, as in gene amplification, MET∆14 kinase is constitutively active. Our analysis of MET in carcinoma cell lines showed that MET∆14 strictly depends on HGF for kinase activation. Compared with wt MET, ∆14 is sensitive to lower HGF concentrations, with more sustained kinase response. Using three different models, we have demonstrated that MET∆14 activation leads to robust phosphorylation of AKT, leading to a distinctive transcriptomic signature. Functional studies revealed that ∆14 activation is predominantly responsible for enhanced protection from apoptosis and cellular migration. Thus, the unique HGF-dependent ∆14 oncogenic activity suggests consideration of HGF in the tumour microenvironment to select patients for clinical trials.
Collapse
Affiliation(s)
- Marina Cerqua
- Istituto Fondazione di Oncologia Molecolare - La Fondazione Italiana per la Ricerca sul Cancro (IFOM - FIRC) Institute of Molecular Oncology, Milano, Italy
| | - Orsola Botti
- Istituto Fondazione di Oncologia Molecolare - La Fondazione Italiana per la Ricerca sul Cancro (IFOM - FIRC) Institute of Molecular Oncology, Milano, Italy
| | - Maddalena Arigoni
- Department of Molecular Biotechnology and Health Sciences, University of Torino, Torino, Italy
| | - Noemi Gioelli
- Candiolo Cancer Institute-Fondazione del Piemonte per l'Oncologia, Istituto di Ricovero e Cura a Carattere Scientifico, Candiolo, Italy.,Department of Oncology, University of Torino School of Medicine, Turin, Italy
| | - Guido Serini
- Candiolo Cancer Institute-Fondazione del Piemonte per l'Oncologia, Istituto di Ricovero e Cura a Carattere Scientifico, Candiolo, Italy.,Department of Oncology, University of Torino School of Medicine, Turin, Italy
| | - Raffaele Calogero
- Department of Molecular Biotechnology and Health Sciences, University of Torino, Torino, Italy
| | - Carla Boccaccio
- Laboratory of Cancer Stem Cell Research, Candiolo Cancer Institute, Fondazione Piemontese per Oncologia - Istituti di Ricovero e Cura a Carattere Scientifico (FPO-IRCCS), Turin, Italy.,Department of Oncology, University of Turin Medical School, Turin, Italy
| | - Paolo M Comoglio
- Istituto Fondazione di Oncologia Molecolare - La Fondazione Italiana per la Ricerca sul Cancro (IFOM - FIRC) Institute of Molecular Oncology, Milano, Italy
| | - Dogus M Altintas
- Istituto Fondazione di Oncologia Molecolare - La Fondazione Italiana per la Ricerca sul Cancro (IFOM - FIRC) Institute of Molecular Oncology, Milano, Italy
| |
Collapse
|