Next Article in Journal
Emerging Trends in the Management of Gastric Malignancy with Peritoneal Dissemination: Same Disease, Heterogeneous Prognosis
Next Article in Special Issue
Advancing Pancreatic Cancer Prediction with a Next Visit Token Prediction Head on Top of Med-BERT
Previous Article in Journal
Advancing Thoracic Surgical Oncology in the Era of Precision Medicine
Previous Article in Special Issue
Computational Mutagenesis of GPx7 and GPx8: Structural and Stability Insights into Rare Genetic and Somatic Missense Mutations and Their Implications for Cancer Development
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Editorial

Novel Computational and Artificial Intelligence Models in Cancer Research

by
Li Liu
1,2,*,
Fuhai Li
3,4,
Xiaoming Liu
5,
Kai Wang
6,7 and
Zhongming Zhao
8,*
1
College of Health Solutions, Arizona State University, Phoenix, AZ 85004, USA
2
Biodesign Institute, Arizona State University, Tempe, AZ 85281, USA
3
Institute for Informatics, Data Science and Biostatistics, Washington University in St. Louis, St. Louis, MO 63108, USA
4
Department of Pediatrics, Washington University in St. Louis, St. Louis, MO 63108, USA
5
University of South Florida Genomics & College of Public Health, University of South Florida, Tampa, FL 33612, USA
6
Raymond G. Perelman Center for Cellular and Molecular Therapeutics, Children’s Hospital of Philadelphia, Philadelphia, PA 19104, USA
7
Department of Pathology and Laboratory Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
8
Center for Precision Health, McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA
*
Authors to whom correspondence should be addressed.
Cancers 2025, 17(1), 116; https://doi.org/10.3390/cancers17010116
Submission received: 11 December 2024 / Accepted: 31 December 2024 / Published: 2 January 2025

1. Introduction

The ICIBM 2023 marked the 11th annual conference of its kind, with the ICIBM recently becoming the official conference of the International Association for Intelligent Biology and Medicine (IAIBM), showcasing cutting-edge advancements at the intersection of computation and biomedical research. A summary of the ICIBM 2023 program is provided by Li et al. [1]. As in previous years, cancer research remained a prominent focus, with numerous presentations highlighting innovative approaches to understanding and treating this complex disease. To summarize these contributions, selected works have been compiled in this Special Issue, “Novel Computational and Artificial Intelligence Models in Cancer Research”, reflecting the significant progress and interest in this critical area of study.

2. Summary of Studies

2.1. Cancer Imaging

AI advances in cancer imaging research leverage computer vision technologies, one of the earliest domains where machine learning and AI methods were successfully applied [2]. Medical imaging data, rich in detailed structural and functional information, naturally lend themselves to AI’s ability to extract patterns, enhance predictions, and support clinical decision-making [3,4]. Specifically in the context of cancer, AI demonstrates the ability to automate the initial interpretation of medical images, improve radiographic detection, and support clinical decision-making [5]. Two studies in this Special Issue demonstrate the transformative potential of AI when applied to imaging data.
The study by Hu et al. introduces a composite neural network within a federated learning environment that integrates multisource multimodal data to diagnose lymph node metastasis [6]. This approach jointly optimizes local models using data from individual hospitals and leverages a global model to aggregate and enhance the performance of local predictions. Applied to patients who have gynecologic malignancies and undergo preoperative imaging assessments, the model achieves remarkable diagnostic performance by integrating magnetic resonance imaging (MRI) data and clinical text data. The federated learning framework also addresses privacy concerns by ensuring local data protection and confidentiality to facilitate multi-institutional collaboration.
The study by Das et al. presents a Bayesian framework designed to quantify glioblastoma growth based on multimodal MRI data [7]. This approach extracts the current tumor volume and various radiomic parameters from an MRI scan, and integrates these features with spatial information and glioma diffusion properties within a structural equation model to predict the ultimate tumor volume, i.e., the number of cells that could proliferate from this tumor during its survival time. When tested on preoperative baseline multimodal MRI scans of glioblastomas, this approach demonstrates reliable predictions of the growth of fourth-grade tumors using a time-independent approach.

2.2. Molecular Pathways and Drivers of Cancer

Cancer has molecular underpinnings at various levels, including genetic mutations, epigenetic changes, transcriptional dysregulation, altered protein–protein interactions, and impaired microenvironment dynamics [8,9]. These interconnected processes form complex pathways that are challenging to decipher. Omics studies of bulk tissues and single cells have become powerful tools to investigate these intricate mechanisms [10,11]. However, the high-dimensional and multifaceted nature of omics data makes their interpretation a significant analytical challenge. AI techniques have demonstrated remarkable success in overcoming these challenges, revealing hidden patterns, and identifying actionable targets [12,13,14]. In this Special Issue, five studies present novel AI-driven methods to identify the molecular pathways and drivers of cancer.
Young et al. introduce a redundant-input neural network (RINN) to evaluate the impact of somatic genomic alterations on cancer cell signaling [15]. Designed as a causal graphical model, RINN traces the flow of information from genomic alterations to signaling proteins and pathways, ultimately linking these changes to differential gene expression. By training the model on TCGA pan-cancer data, the authors identify instances where multiple somatic genomic alterations converge on and perturb the same signaling pathways, highlighting the shared functional impacts of diverse genomic changes in cancer.
Yang et al. introduce MultiFDRnet, an algorithm designed to detect perturbed subnetworks by aggregating somatically mutated genes across multiple protein–protein interaction networks [16]. MultiFDRnet integrates networks from different databases and tissue types, leveraging the complementary strengths of diverse network annotations while maintaining control over the overall false discovery rate. The method is extensively validated using both simulated and real cancer data. The application of MultiFDRnet to bladder cancer and head and neck cancer samples reveal hotspots in generic pathways shared across cancers as well as cancer-type-specific pathways.
Wei et al. present an immune-related risk score model for endometrial cancer, integrating clinical and molecular data to stratify patient outcomes [17]. The workflow begins with constructing a gene co-expression network, from which immune-related modules are mined to identify genes associated with overall survival. These genes are then linearly combined to generate a risk score. Beyond serving as a prognostic marker, further analysis of the predictor genes’ expression levels reveals their associations with the molecular basis of the disease, tumor immune microenvironment, and responses to treatments.
Zhang et al. introduce scGEM, a nested tree-structured nonparametric Bayesian model designed to construct gene co-expression modules (GEMs) from single-cell transcriptomic data [18]. This algorithm models the hierarchical relationships among cells, capturing the gradual changes in both the topology of GEMs and the transcription abundance of their member genes during cellular differentiation and specialization. The resulting GEMs enhance the deconvolution of functional signals in bulk transcriptomic data. Applying scGEM to triple-negative breast cancer data reveals significant correlations between cell-type-specific GEMs and key processes such as lymphocyte infiltration and the cell cycle, both of which are critical in tumorigenesis.
Chen et al. focus on identifying cancer drivers in non-human model organisms [19]. They employ transfer learning techniques to adapt the GUST model [20], originally developed to distinguish oncogenes and tumor suppressor genes in human tumors, to mouse models. By comparing genetic drivers in humans to those in mice across different cancer types, the study identifies both conserved and unique tumorigenesis mechanisms across species and cancer types. This approach bridges the translational gap between human and murine cancer research, providing a robust framework for better aligning non-human tumor models with human cancer studies.

2.3. Benchmarking Computational Tools

With the rapid evolution of precision oncology, multiple competing methods and models often emerge for the same task, reflecting the dynamic nature of innovation and discovery [21,22]. While this diversity fuels progress, it also underscores the need for rigorous evaluation to ensure reliability, reproducibility, and meaningful comparisons across tools. Benchmarking provides a standardized framework for assessing the strengths and limitations of various methods, facilitating their refinement and ensuring their applicability in diverse clinical and research settings [23]. Two studies in this issue exemplify the importance of benchmarking.
The first study focuses on evaluating transcriptomic biomarkers for immune checkpoint blockades (ICBs) [24]. Kang et al. manually curate and uniformly process transcriptomic data from over 1400 cancer patients, integrating these data with clinical data. Using this extensive dataset, they systematically assess the performance of 39 biomarker sets in predicting ICB responses and survival outcomes across various contexts. Their analysis reveals that while most biomarkers exhibit low stability and robustness across datasets, two biomarker sets demonstrate strong correlations with ICB responses, and another two are significantly associated with clinical outcomes. An online resource, ICB-Portal, hosts the datasets and evaluation results from this study, enabling other researchers to test and refine their custom biomarkers.
The second study assesses data quality in small RNA profiling studies of human extracellular vesicles (EVs) [25]. Wang et al. reanalyze 83 small RNA expression datasets, encompassing samples from diverse sources, representing varying phenotypes, and prepared using different techniques. When evaluated on a comprehensive set of quality metrics, these datasets exhibit significant biases associated with technical platforms, RNA composition, and RNA biotype enrichment. These biases contribute to substantial variability that can obscure true biological signals and compromise reproducibility. While the findings offer valuable guidance for quality control, EV isolation methods, and data interpretation, they also highlight the urgent need for standardized protocols in EV research to improve data consistency and ensure the reliability of biological conclusions in future studies.

3. Conclusions

The nine studies featured in this Special Issue exemplify the transformative potential of computational and AI-driven methods in cancer research. From developing novel models to benchmarking existing tools, these contributions address key challenges in oncology and medical imaging and pave the way for innovations in diagnosis, treatment, and prevention. By fostering collaboration between computational scientists, biologists, and clinicians, this Special Issue reflects the interdisciplinary nature of modern cancer research. We hope it inspires further exploration and application of AI technologies, driving progress toward a future of precision oncology.

Author Contributions

Writing—original draft preparation, L.L.; writing—review and editing, F.L., X.L., K.W. and Z.Z.; funding acquisition, K.W. and Z.Z. All authors have read and agreed to the published version of the manuscript.

Funding

We thank the financial support of ICIBM conferences from the National Science Foundation (grant numbers 2312126 and 2427012).

Acknowledgments

We extend our gratitude to the reviewers for their invaluable efforts in evaluating the manuscripts submitted to the ICIBM 2023 and its associated Special Issues. We also appreciate the contributions of the program committee members, chairs of other ICIBM committees, session chairs, and volunteers, whose dedication and hard work are instrumental in ensuring the success of the conference.

Conflicts of Interest

The authors declare no conflicts of interest.

References

  1. Li, F.; Liu, L.; Wang, K.; Liu, X.; Zhao, Z. Intelligent Biology and Medicine: Accelerating Innovative Computational Approaches. Comput. Struct. Biotechnol. J. 2024, 27, 32–34. [Google Scholar] [CrossRef]
  2. Koh, D.M.; Papanikolaou, N.; Bick, U.; Illing, R.; Kahn, C.E., Jr.; Kalpathi-Cramer, J.; Matos, C.; Marti-Bonmati, L.; Miles, A.; Mun, S.K.; et al. Artificial intelligence and machine learning in cancer imaging. Commun. Med. 2022, 2, 133. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  3. Esteva, A.; Chou, K.; Yeung, S.; Naik, N.; Madani, A.; Mottaghi, A.; Liu, Y.; Topol, E.; Dean, J.; Socher, R. Deep learning-enabled medical computer vision. npj Digit. Med. 2021, 4, 5. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  4. Galić, I.; Habijan, M.; Leventić, H.; Romić, K. Machine learning empowering personalized medicine: A comprehensive review of medical image analysis methods. Electronics 2023, 12, 4411. [Google Scholar] [CrossRef]
  5. Bi, W.L.; Hosny, A.; Schabath, M.B.; Giger, M.L.; Birkbak, N.J.; Mehrtash, A.; Allison, T.; Arnaout, O.; Abbosh, C.; Dunn, I.F.; et al. Artificial intelligence in cancer imaging: Clinical challenges and applications. CA Cancer J. Clin. 2019, 69, 127–157. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  6. Hu, Z.; Ma, L.; Ding, Y.; Zhao, X.; Shi, X.; Lu, H.; Liu, K. Enhancing the Accuracy of Lymph-Node-Metastasis Prediction in Gynecologic Malignancies Using Multimodal Federated Learning: Integrating CT, MRI, and PET/CT. Cancers 2023, 15, 5281. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  7. Das, A.; Ding, S.; Liu, R.; Huang, C. Quantifying the Growth of Glioblastoma Tumors Using Multimodal MRI Brain Images. Cancers 2023, 15, 3614. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  8. Pecorino, L. Molecular Biology of Cancer: Mechanisms, Targets, and Therapeutics; Oxford University Press: Oxford, UK, 2021. [Google Scholar]
  9. Fares, J.; Fares, M.Y.; Khachfe, H.H.; Salhab, H.A.; Fares, Y. Molecular principles of metastasis: A hallmark of cancer revisited. Signal Transduct. Target. Ther. 2020, 5, 28. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  10. Hasin, Y.; Seldin, M.; Lusis, A. Multi-omics approaches to disease. Genome Biol. 2017, 18, 83. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  11. Baysoy, A.; Bai, Z.; Satija, R.; Fan, R. The technological landscape and applications of single-cell multi-omics. Nat. Rev. Mol. Cell Biol. 2023, 24, 695–713. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  12. Prelaj, A.; Miskovic, V.; Zanitti, M.; Trovo, F.; Genova, C.; Viscardi, G.; Rebuzzi, S.E.; Mazzeo, L.; Provenzano, L.; Kosta, S.; et al. Artificial intelligence for predictive biomarker discovery in immuno-oncology: A systematic review. Ann. Oncol. 2024, 35, 29–65. [Google Scholar] [CrossRef] [PubMed]
  13. Cai, Z.; Poulos, R.C.; Liu, J.; Zhong, Q. Machine learning for multi-omics data integration in cancer. iScience 2022, 25, 103798. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  14. Chi, J.; Shu, J.; Li, M.; Mudappathi, R.; Jin, Y.; Lewis, F.; Boon, A.; Qin, X.; Liu, L.; Gu, H. Artificial Intelligence in Metabolomics: A Current Review. Trends Analyt. Chem. 2024, 178, 117852. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  15. Young, J.D.; Ren, S.; Chen, L.; Lu, X. Revealing the Impact of Genomic Alterations on Cancer Cell Signaling with an Interpretable Deep Learning Model. Cancers 2023, 15, 3857. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  16. Yang, L.; Chen, R.; Melendy, T.; Goodison, S.; Sun, Y. Identifying Significantly Perturbed Subnetworks in Cancer Using Multiple Protein-Protein Interaction Networks. Cancers 2023, 15, 4090. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  17. Wei, W.; Ye, B.; Huang, Z.; Mu, X.; Qiao, J.; Zhao, P.; Jiang, Y.; Wu, J.; Zhan, X. Prediction of Prognosis, Immunotherapy and Chemotherapy with an Immune-Related Risk Score Model for Endometrial Cancer. Cancers 2023, 15, 3673. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  18. Zhang, H.; Lu, X.; Lu, B.; Chen, L. scGEM: Unveiling the Nested Tree-Structured Gene Co-Expressing Modules in Single Cell Transcriptome Data. Cancers 2023, 15, 4277. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  19. Chen, H.; Shu, J.; Maley, C.C.; Liu, L. A Mouse-Specific Model to Detect Genes under Selection in Tumors. Cancers 2023, 15, 5156. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  20. Chandrashekar, P.; Ahmadinejad, N.; Wang, J.; Sekulic, A.; Egan, J.B.; Asmann, Y.W.; Kumar, S.; Maley, C.; Liu, L. Somatic selection distinguishes oncogenes and tumor suppressor genes. Bioinformatics 2020, 36, 1712–1717. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  21. Zheng, H.; Zhang, G.; Zhang, L.; Wang, Q.; Li, H.; Han, Y.; Xie, L.; Yan, Z.; Li, Y.; An, Y.; et al. Comprehensive Review of Web Servers and Bioinformatics Tools for Cancer Prognosis Analysis. Front. Oncol. 2020, 10, 68. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  22. Nourbakhsh, M.; Degn, K.; Saksager, A.; Tiberti, M.; Papaleo, E. Prediction of cancer driver genes and mutations: The potential of integrative computational frameworks. Brief. Bioinform. 2024, 25, bbad519. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  23. Weber, L.M.; Saelens, W.; Cannoodt, R.; Soneson, C.; Hapfelmeier, A.; Gardner, P.P.; Boulesteix, A.L.; Saeys, Y.; Robinson, M.D. Essential guidelines for computational method benchmarking. Genome Biol. 2019, 20, 125. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  24. Kang, H.; Zhu, X.; Cui, Y.; Xiong, Z.; Zong, W.; Bao, Y.; Jia, P. A Comprehensive Benchmark of Transcriptomic Biomarkers for Immune Checkpoint Blockades. Cancers 2023, 15, 4094. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
  25. Wang, J.; Chen, H.C.; Sheng, Q.; Dawson, T.R.; Coffey, R.J.; Patton, J.G.; Weaver, A.M.; Shyr, Y.; Liu, Q. Systematic Assessment of Small RNA Profiling in Human Extracellular Vesicles. Cancers 2023, 15, 3446. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Liu, L.; Li, F.; Liu, X.; Wang, K.; Zhao, Z. Novel Computational and Artificial Intelligence Models in Cancer Research. Cancers 2025, 17, 116. https://doi.org/10.3390/cancers17010116

AMA Style

Liu L, Li F, Liu X, Wang K, Zhao Z. Novel Computational and Artificial Intelligence Models in Cancer Research. Cancers. 2025; 17(1):116. https://doi.org/10.3390/cancers17010116

Chicago/Turabian Style

Liu, Li, Fuhai Li, Xiaoming Liu, Kai Wang, and Zhongming Zhao. 2025. "Novel Computational and Artificial Intelligence Models in Cancer Research" Cancers 17, no. 1: 116. https://doi.org/10.3390/cancers17010116

APA Style

Liu, L., Li, F., Liu, X., Wang, K., & Zhao, Z. (2025). Novel Computational and Artificial Intelligence Models in Cancer Research. Cancers, 17(1), 116. https://doi.org/10.3390/cancers17010116

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop