Cancers

Research

20 pages, 4650 KiB

Open AccessArticle

Enhancing the Accuracy of Lymph-Node-Metastasis Prediction in Gynecologic Malignancies Using Multimodal Federated Learning: Integrating CT, MRI, and PET/CT

by Zhijun Hu, Ling Ma, Yue Ding, Xuanxuan Zhao, Xiaohua Shi, Hongtao Lu and Kaijiang Liu

Cancers 2023, 15(21), 5281; https://doi.org/10.3390/cancers15215281 - 03 Nov 2023

Cited by 1 | Viewed by 779

Abstract

Gynecological malignancies, particularly lymph node metastasis, have presented a diagnostic challenge, even with traditional imaging techniques such as CT, MRI, and PET/CT. This study was conceived to explore and, subsequently, to bridge this diagnostic gap through a more holistic and innovative approach. By [...] Read more.

Gynecological malignancies, particularly lymph node metastasis, have presented a diagnostic challenge, even with traditional imaging techniques such as CT, MRI, and PET/CT. This study was conceived to explore and, subsequently, to bridge this diagnostic gap through a more holistic and innovative approach. By developing a comprehensive framework that integrates both non-image data and detailed MRI image analyses, this study harnessed the capabilities of a multimodal federated-learning model. Employing a composite neural network within a federated-learning environment, this study adeptly merged diverse data sources to enhance prediction accuracy. This was further complemented by a sophisticated deep convolutional neural network with an enhanced U-NET architecture for meticulous MRI image processing. Traditional imaging yielded sensitivities ranging from 32.63% to 57.69%. In contrast, the federated-learning model, without incorporating image data, achieved an impressive sensitivity of approximately 0.9231, which soared to 0.9412 with the integration of MRI data. Such advancements underscore the significant potential of this approach, suggesting that federated learning, especially when combined with MRI assessment data, can revolutionize lymph-node-metastasis detection in gynecological malignancies. This paves the way for more precise patient care, potentially transforming the current diagnostic paradigm and resulting in improved patient outcomes. Full article

(This article belongs to the Special Issue Novel Computational and Artificial Intelligence (AI) Models in Cancer Research)

► Show Figures

Figure 1

15 pages, 1837 KiB

Open AccessArticle

A Mouse-Specific Model to Detect Genes under Selection in Tumors

by Hai Chen, Jingmin Shu, Carlo C. Maley and Li Liu

Cancers 2023, 15(21), 5156; https://doi.org/10.3390/cancers15215156 - 26 Oct 2023

Viewed by 930

Abstract

The mouse is a widely used model organism in cancer research. However, no computational methods exist to identify cancer driver genes in mice due to a lack of labeled training data. To address this knowledge gap, we adapted the GUST (Genes Under Selection [...] Read more.

The mouse is a widely used model organism in cancer research. However, no computational methods exist to identify cancer driver genes in mice due to a lack of labeled training data. To address this knowledge gap, we adapted the GUST (Genes Under Selection in Tumors) model, originally trained on human exomes, to mouse exomes via transfer learning. The resulting tool, called GUST-mouse, can estimate long-term and short-term evolutionary selection in mouse tumors, and distinguish between oncogenes, tumor suppressor genes, and passenger genes using high-throughput sequencing data. We applied GUST-mouse to analyze 65 exomes of mouse primary breast cancer models and 17 exomes of mouse leukemia models. Comparing the predictions between cancer types and between human and mouse tumors revealed common and unique driver genes. The GUST-mouse method is available as an open-source R package on github. Full article

(This article belongs to the Special Issue Novel Computational and Artificial Intelligence (AI) Models in Cancer Research)

► Show Figures

Figure 1

17 pages, 4439 KiB

Open AccessArticle

scGEM: Unveiling the Nested Tree-Structured Gene Co-Expressing Modules in Single Cell Transcriptome Data

by Han Zhang, Xinghua Lu, Binfeng Lu and Lujia Chen

Cancers 2023, 15(17), 4277; https://doi.org/10.3390/cancers15174277 - 26 Aug 2023

Viewed by 948

Abstract

Background: Single-cell transcriptome analysis has fundamentally changed biological research by allowing higher-resolution computational analysis of individual cells and subsets of cell types. However, few methods have met the need to recognize and quantify the underlying cellular programs that determine the specialization and differentiation [...] Read more.

Background: Single-cell transcriptome analysis has fundamentally changed biological research by allowing higher-resolution computational analysis of individual cells and subsets of cell types. However, few methods have met the need to recognize and quantify the underlying cellular programs that determine the specialization and differentiation of the cell types. Methods: In this study, we present scGEM, a nested tree-structured nonparametric Bayesian model, to reveal the gene co-expression modules (GEMs) reflecting transcriptome processes in single cells. Results: We show that scGEM can discover shared and specialized transcriptome signals across different cell types using peripheral blood mononuclear single cells and early brain development single cells. scGEM outperformed other methods in perplexity and topic coherence (p < 0.001) on our simulation data. Larger datasets, deeper trees and pre-trained models are shown to be positively associated with better scGEM performance. The GEMs obtained from triple-negative breast cancer single cells exhibited better correlations with lymphocyte infiltration (p = 0.009) and the cell cycle (p < 0.001) than other methods in additional validation on the bulk RNAseq dataset. Conclusions: Altogether, we demonstrate that scGEM can be used to model the hidden cellular functions of single cells, thereby unveiling the specialization and generalization of transcriptomic programs across different types of cells. Full article

(This article belongs to the Special Issue Novel Computational and Artificial Intelligence (AI) Models in Cancer Research)

► Show Figures

Figure 1

21 pages, 8813 KiB

Open AccessArticle

A Comprehensive Benchmark of Transcriptomic Biomarkers for Immune Checkpoint Blockades

by Hongen Kang, Xiuli Zhu, Ying Cui, Zhuang Xiong, Wenting Zong, Yiming Bao and Peilin Jia

Cancers 2023, 15(16), 4094; https://doi.org/10.3390/cancers15164094 - 14 Aug 2023

Viewed by 1130

Abstract

Immune checkpoint blockades (ICBs) have revolutionized cancer therapy by inducing durable clinical responses, but only a small percentage of patients can benefit from ICB treatments. Many studies have established various biomarkers to predict ICB responses. However, different biomarkers were found with diverse performances [...] Read more.

Immune checkpoint blockades (ICBs) have revolutionized cancer therapy by inducing durable clinical responses, but only a small percentage of patients can benefit from ICB treatments. Many studies have established various biomarkers to predict ICB responses. However, different biomarkers were found with diverse performances in practice, and a timely and unbiased assessment has yet to be conducted due to the complexity of ICB-related studies and trials. In this study, we manually curated 29 published datasets with matched transcriptome and clinical data from more than 1400 patients, and uniformly preprocessed these datasets for further analyses. In addition, we collected 39 sets of transcriptomic biomarkers, and based on the nature of the corresponding computational methods, we categorized them into the gene-set-like group (with the self-contained design and the competitive design, respectively) and the deconvolution-like group. Next, we investigated the correlations and patterns of these biomarkers and utilized a standardized workflow to systematically evaluate their performance in predicting ICB responses and survival statuses across different datasets, cancer types, antibodies, biopsy times, and combinatory treatments. In our benchmark, most biomarkers showed poor performance in terms of stability and robustness across different datasets. Two scores (TIDE and CYT) had a competitive performance for ICB response prediction, and two others (PASS-ON and EIGS_ssGSEA) showed the best association with clinical outcome. Finally, we developed ICB-Portal to host the datasets, biomarkers, and benchmark results and to implement the computational methods for researchers to test their custom biomarkers. Our work provided valuable resources and a one-stop solution to facilitate ICB-related research. Full article

(This article belongs to the Special Issue Novel Computational and Artificial Intelligence (AI) Models in Cancer Research)

► Show Figures

Figure 1

24 pages, 4502 KiB

Open AccessArticle

Identifying Significantly Perturbed Subnetworks in Cancer Using Multiple Protein–Protein Interaction Networks

by Le Yang, Runpu Chen, Thomas Melendy, Steve Goodison and Yijun Sun

Cancers 2023, 15(16), 4090; https://doi.org/10.3390/cancers15164090 - 14 Aug 2023

Viewed by 1036

Abstract

Background: The identification of cancer driver genes and key molecular pathways has been the focus of large-scale cancer genome studies. Network-based methods detect significantly perturbed subnetworks as putative cancer pathways by incorporating genomics data with the topological information of PPI networks. However, commonly [...] Read more.

Background: The identification of cancer driver genes and key molecular pathways has been the focus of large-scale cancer genome studies. Network-based methods detect significantly perturbed subnetworks as putative cancer pathways by incorporating genomics data with the topological information of PPI networks. However, commonly used PPI networks have distinct topological structures, making the results of the same method vary widely when applied to different networks. Furthermore, emerging context-specific PPI networks often have incomplete topological structures, which pose serious challenges for existing subnetwork detection algorithms. Methods: In this paper, we propose a novel method, referred to as MultiFDRnet, to address the above issues. The basic idea is to model a set of PPI networks as a multiplex network to preserve the topological structure of individual networks, while introducing dependencies among them, and, then, to detect significantly perturbed subnetworks on the modeled multiplex network using all the structural information simultaneously. Results: To illustrate the effectiveness of the proposed approach, an extensive benchmark analysis was conducted on both simulated and real cancer data. The experimental results showed that the proposed method is able to detect significantly perturbed subnetworks jointly supported by multiple PPI networks and to identify novel modular structures in context-specific PPI networks. Full article

(This article belongs to the Special Issue Novel Computational and Artificial Intelligence (AI) Models in Cancer Research)

► Show Figures

Figure 1

24 pages, 1251 KiB

Open AccessArticle

Revealing the Impact of Genomic Alterations on Cancer Cell Signaling with an Interpretable Deep Learning Model

by Jonathan D. Young, Shuangxia Ren, Lujia Chen and Xinghua Lu

Cancers 2023, 15(15), 3857; https://doi.org/10.3390/cancers15153857 - 29 Jul 2023

Cited by 1 | Viewed by 986

Abstract

Cancer is a disease of aberrant cellular signaling resulting from somatic genomic alterations (SGAs). Heterogeneous SGA events in tumors lead to tumor-specific signaling system aberrations. We interpret the cancer signaling system as a causal graphical model, where SGAs affect signaling proteins, propagate their [...] Read more.

Cancer is a disease of aberrant cellular signaling resulting from somatic genomic alterations (SGAs). Heterogeneous SGA events in tumors lead to tumor-specific signaling system aberrations. We interpret the cancer signaling system as a causal graphical model, where SGAs affect signaling proteins, propagate their effects through signal transduction, and ultimately change gene expression. To represent such a system, we developed a deep learning model called redundant-input neural network (RINN) with a transparent redundant-input architecture. Our findings demonstrate that by utilizing SGAs as inputs, the RINN can encode their impact on the signaling system and predict gene expression accurately when measured as the area under ROC curves. Moreover, the RINN can discover the shared functional impact (similar embeddings) of SGAs that perturb a common signaling pathway (e.g., PI3K, Nrf2, and TGF). Furthermore, the RINN exhibits the ability to discover known relationships in cellular signaling systems. Full article

(This article belongs to the Special Issue Novel Computational and Artificial Intelligence (AI) Models in Cancer Research)

► Show Figures

Figure 1

23 pages, 6857 KiB

Open AccessArticle

Prediction of Prognosis, Immunotherapy and Chemotherapy with an Immune-Related Risk Score Model for Endometrial Cancer

by Wei Wei, Bo Ye, Zhenting Huang, Xiaoling Mu, Jing Qiao, Peng Zhao, Yuehang Jiang, Jingxian Wu and Xiaohui Zhan

Cancers 2023, 15(14), 3673; https://doi.org/10.3390/cancers15143673 - 19 Jul 2023

Viewed by 1473

Abstract

Endometrial cancer (EC) is the most common gynecologic cancer. The overall survival remains unsatisfying due to the lack of effective treatment screening approaches. Immunotherapy as a promising therapy has been applied for EC treatment, but still fails in many cases. Therefore, there is [...] Read more.

Endometrial cancer (EC) is the most common gynecologic cancer. The overall survival remains unsatisfying due to the lack of effective treatment screening approaches. Immunotherapy as a promising therapy has been applied for EC treatment, but still fails in many cases. Therefore, there is a strong need to optimize the screening approach for clinical treatment. In this study, we employed co-expression network (GCN) analysis to mine immune-related GCN modules and key genes and further constructed an immune-related risk score model (IRSM). The IRSM was proved effective as an independent predictor of poor prognosis. The roles of IRSM-related genes in EC were confirmed by IHC. The molecular basis, tumor immune microenvironment and clinical characteristics of the IRSM were revealed. Moreover, the IRSM effectiveness was associated with immunotherapy and chemotherapy. Patients in the low-risk group were more sensitive to immunotherapy and chemotherapy than those in the high-risk group. Interestingly, the patients responding to immunotherapy were also more sensitive to chemotherapy. Overall, we developed an IRSM which could be used to predict the prognosis, immunotherapy response and chemotherapy sensitivity of EC patients. Our analysis not only improves the treatment of EC but also offers targets for personalized therapeutic interventions. Full article

(This article belongs to the Special Issue Novel Computational and Artificial Intelligence (AI) Models in Cancer Research)

► Show Figures

Figure 1

27 pages, 6086 KiB

Open AccessArticle

Quantifying the Growth of Glioblastoma Tumors Using Multimodal MRI Brain Images

by Anisha Das, Shengxian Ding, Rongjie Liu and Chao Huang

Cancers 2023, 15(14), 3614; https://doi.org/10.3390/cancers15143614 - 14 Jul 2023

Cited by 1 | Viewed by 1126

Abstract

Predicting the eventual volume of tumor cells, that might proliferate from a given tumor, can help in cancer early detection and medical procedure planning to prevent their migration to other organs. In this work, a new statistical framework is proposed using Bayesian techniques [...] Read more.

Predicting the eventual volume of tumor cells, that might proliferate from a given tumor, can help in cancer early detection and medical procedure planning to prevent their migration to other organs. In this work, a new statistical framework is proposed using Bayesian techniques for detecting the eventual volume of cells expected to proliferate from a glioblastoma (GBM) tumor. Specifically, the tumor region was first extracted using a parallel image segmentation algorithm. Once the tumor region was determined, we were interested in the number of cells that could proliferate from this tumor until its survival time. For this, we constructed the posterior distribution of the tumor cell numbers based on the proposed likelihood function and a certain prior volume. Furthermore, we extended the detection model and conducted a Bayesian regression analysis by incorporating radiomic features to discover those non-tumor cells that remained undetected. The main focus of the study was to develop a time-independent prediction model that could reliably predict the ultimate volume a malignant tumor of the fourth-grade severity could attain and which could also determine if the incorporation of the radiomic properties of the tumor enhanced the chances of no malignant cells remaining undetected. Full article

(This article belongs to the Special Issue Novel Computational and Artificial Intelligence (AI) Models in Cancer Research)

► Show Figures

Figure 1

17 pages, 1788 KiB

Open AccessArticle

Systematic Assessment of Small RNA Profiling in Human Extracellular Vesicles

by Jing Wang, Hua-Chang Chen, Quanhu Sheng, T. Renee Dawson, Robert J. Coffey, James G. Patton, Alissa M. Weaver, Yu Shyr and Qi Liu

Cancers 2023, 15(13), 3446; https://doi.org/10.3390/cancers15133446 - 30 Jun 2023

Cited by 1 | Viewed by 1225

Abstract

Motivation: Extracellular vesicles (EVs) are produced and released by most cells and are now recognized to play a role in intercellular communication through the delivery of molecular cargo, including proteins, lipids, and RNA. Small RNA sequencing (small RNA-seq) has been widely used to [...] Read more.

Motivation: Extracellular vesicles (EVs) are produced and released by most cells and are now recognized to play a role in intercellular communication through the delivery of molecular cargo, including proteins, lipids, and RNA. Small RNA sequencing (small RNA-seq) has been widely used to characterize the small RNA content in EVs. However, there is a lack of a systematic assessment of the quality, technical biases, RNA composition, and RNA biotypes enrichment for small RNA profiling of EVs across cell types, biofluids, and conditions. Methods: We collected and reanalyzed small RNA-seq datasets for 2756 samples from 83 studies involving 55 with EVs only and 28 with both EVs and matched donor cells. We assessed their quality by the total number of reads after adapter trimming, the overall alignment rate to the host and non-host genomes, and the proportional abundance of total small RNA and specific biotypes, such as miRNA, tRNA, rRNA, and Y RNA. Results: We found that EV extraction methods varied in their reproducibility in isolating small RNAs, with effects on small RNA composition. Comparing proportional abundances of RNA biotypes between EVs and matched donor cells, we discovered that rRNA and tRNA fragments were relatively enriched, but miRNAs and snoRNA were depleted in EVs. Except for the export of eight miRNAs being context-independent, the selective release of most miRNAs into EVs was study-specific. Conclusion: This work guides quality control and the selection of EV isolation methods and enhances the interpretation of small RNA contents and preferential loading in EVs. Full article

(This article belongs to the Special Issue Novel Computational and Artificial Intelligence (AI) Models in Cancer Research)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Novel Computational and Artificial Intelligence (AI) Models in Cancer Research

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI