Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.4
5.2
Journals
Cancers
Special Issues
Bioinformatics, Big Data and Cancer
share announcement

Bioinformatics, Big Data and Cancer

A special issue of Cancers (ISSN 2072-6694). This special issue belongs to the section "Cancer Informatics and Big Data".

Deadline for manuscript submissions: closed (30 April 2022) | Viewed by 77189

Special Issue Editors

Prof. Dr. Alan Hutson

E-Mail Website
Guest Editor
Department of Biostatistics and Bioinformatics, Roswell Park Comprehensive Cancer Center, Buffalo, NY 14263, USA
Interests: biostatistics; clinical trials; design of experiments; computational methods
Prof. Dr. Song Liu

E-Mail Website
Guest Editor
Department of Biostatistics and Bioinformatics, Roswell Park Comprehensive Cancer Center, Buffalo, NY 14263, USA
Interests: translational bioinformatics; biomarker discovery; cancer therapeutics; immuno-oncology

Special Issue Information

Dear Colleagues,

Cancer is a multifaceted ecosystem whose complexity is orchestrated by the heterogeneities of tumor cells, tumor microenvironment, and their spatiotemporal interplay. The advent of single-cell assays has shifted oncology research to a new paradigm, where tumor-immune landscapes are being depicted at unprecedented resolution. Furthermore, rapid technology development has enabled the measurement of multiple modes of omics information, including genome, epigenome, chromatin, transcriptome, proteome, metabolome, and imaging phenotype. The availability of multi-omics oncology data, at both single-cell and bulk levels from both preclinical models and patient specimens, will help researchers to understand how the tumor-immune ecosystem operates and responds to treatment and develop better biomarkers and therapies.

Innovations in computational analysis and data integration will be instrumental in overcoming challenges in oncology. For example, analysis of single-cell omics data needs to address multiple intrinsic challenges associated with handling very large, sparse data sets. Novel challenges also arise in data representation, management, and analysis, attempting to gain insights from multiassay studies; these challenges exist even when well-established data models and analysis workflows exist for each assay individually. This Special Issue will highlight advances in bioinformatics and data science in cancer in all its diversity, covering both method developments and their applications in oncology.

Prof. Dr. Alan Hutson
Prof. Dr. Song Liu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Cancers is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2900 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • bioinformatics
  • data science
  • multi-omics
  • oncology
  • data representation
  • data management
  • data visualization
  • data analysis
  • data integration
  • data dissemination
  • reproducibility
  • high performance computing

Published Papers (21 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

25 pages, 9370 KiB  
Article
Novel Necroptosis-Related Gene Signature for Predicting Early Diagnosis and Prognosis and Immunotherapy of Gastric Cancer
by Xiaozhu Zhou, Baizhuo Zhang, Guoliang Zheng, Zhen Zhang, Jiaoqi Wu, Ke Du and Jing Zhang
Cancers 2022, 14(16), 3891; https://doi.org/10.3390/cancers14163891 - 11 Aug 2022
Cited by 5 | Viewed by 2055
Abstract
Necroptosis is a kind of programmed necrosis, which is different from apoptosis and pyroptosis. Its molecular mechanism has been described in inflammatory diseases. Gastric cancer (GC) is one of the most common malignancies worldwide with the third highest mortality. However, the role of [...] Read more.
Necroptosis is a kind of programmed necrosis, which is different from apoptosis and pyroptosis. Its molecular mechanism has been described in inflammatory diseases. Gastric cancer (GC) is one of the most common malignancies worldwide with the third highest mortality. However, the role of necroptosis in the occurrence and progression of GC remains largely unexplored. Therefore, we investigated necroptosis-related genes (NRGs) by analyzing public transcriptomic data from GC samples. Our results indicate that 83 of 740 NRGs are dysregulated in GC tissues. Next, we identified necroptosis-associated early diagnosis and prognostic gene signatures for GC using machine learning. 2-NRGs (CCT6A and FAP) and 4-NRGs (ZFP36, TP53I3, FAP, and CCT6A), respectively, can effectively assess the risk of early GC (AUC = 0.943) and the prognosis of GC patients (AUC = 0.866). Through in-depth analysis, we were pleasantly surprised to find that there was a significant correlation between the 4-NRGs and GC immunotherapy effect and immune checkpoint inhibitors (ICIs), which could be used for the evaluation of immunosuppressants. Finally, we identified the core gene FAP, and established the relationship between FAP and ICIs in GC. These findings could provide a new target for immunotherapy for GC and a more effective treatment scheme for GC patients. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

14 pages, 1527 KiB  
Article
Artificial Intelligence-Based Prognostic Model for Urologic Cancers: A SEER-Based Study
by Okyaz Eminaga, Eugene Shkolyar, Bernhard Breil, Axel Semjonow, Martin Boegemann, Lei Xing, Ilker Tinay and Joseph C. Liao
Cancers 2022, 14(13), 3135; https://doi.org/10.3390/cancers14133135 - 26 Jun 2022
Cited by 4 | Viewed by 3187
Abstract
Background: Prognostication is essential to determine the risk profile of patients with urologic cancers. Methods: We utilized the SEER national cancer registry database with approximately 2 million patients diagnosed with urologic cancers (penile, testicular, prostate, bladder, ureter, and kidney). The cohort was randomly [...] Read more.
Background: Prognostication is essential to determine the risk profile of patients with urologic cancers. Methods: We utilized the SEER national cancer registry database with approximately 2 million patients diagnosed with urologic cancers (penile, testicular, prostate, bladder, ureter, and kidney). The cohort was randomly divided into the development set (90%) and the out-held test set (10%). Modeling algorithms and clinically relevant parameters were utilized for cancer-specific mortality prognosis. The model fitness for the survival estimation was assessed using the differences between the predicted and observed Kaplan–Meier estimates on the out-held test set. The overall concordance index (c-index) score estimated the discriminative accuracy of the survival model on the test set. A simulation study assessed the estimated minimum follow-up duration and time points with the risk stability. Results: We achieved a well-calibrated prognostic model with an overall c-index score of 0.800 (95% CI: 0.795–0.805) on the representative out-held test set. The simulation study revealed that the suggestions for the follow-up duration covered the minimum duration and differed by the tumor dissemination stages and affected organs. Time points with a high likelihood for risk stability were identifiable. Conclusions: A personalized temporal survival estimation is feasible using artificial intelligence and has potential application in clinical settings, including surveillance management. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

20 pages, 3167 KiB  
Article
The Expression and Role Analysis of Methylation-Regulated Differentially Expressed Gene UBE2C in Pan-Cancer, Especially for HGSOC
by Jiajia Li, Yating Sun, Xiuling Zhi, Qin Li, Liangqing Yao and Mo Chen
Cancers 2022, 14(13), 3121; https://doi.org/10.3390/cancers14133121 - 25 Jun 2022
Cited by 2 | Viewed by 1998
Abstract
High-grade serous ovarian cancer (HGSOC) is the most fatal gynecological malignant tumor. DNA methylation is associated with the occurrence and development of a variety of tumor types, including HGSOC. However, the signatures regarding DNA methylation changes for HGSOC diagnosis and prognosis are less [...] Read more.
High-grade serous ovarian cancer (HGSOC) is the most fatal gynecological malignant tumor. DNA methylation is associated with the occurrence and development of a variety of tumor types, including HGSOC. However, the signatures regarding DNA methylation changes for HGSOC diagnosis and prognosis are less explored. Here, we screened differentially methylated genes and differentially expressed genes in HGSOC through the GEO database. We identified that UBE2C was hypomethylation and overexpression in ovarian cancer, which was associated with more advanced cancer stages and poor prognoses. Additionally, the pan-cancer analysis showed that UBE2C was overexpressed and hypomethylation in almost all cancer types and was related to poor prognoses for various cancers. Next, we established a risk or prognosis model related to UBE2C methylation sites and screened out the three sites (cg03969725, cg02838589, and cg00242976). Furthermore, we experimentally validated the overexpression of UBE2C in HGSOC clinical samples and ovarian cell lines using quantitative real-time PCR, Western blot, and immunohistochemistry. Importantly, we discovered that ovarian cancer cell lines had lower DNA methylation levels of UBE2C than IOSE-80 cells (normal ovarian epithelial cell line) by bisulfite sequencing PCR. Consistently, treatment with 5-Azacytidine (a methylation inhibitor) was able to restore the expression of UBE2C. Taken together, our study may help us to understand the underlying molecular mechanism of UBE2C in pan-cancer tumorigenesis; it may be a useful biomarker for diagnosis, treatment, and monitoring, not only of ovarian cancer but a variety of cancers. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

13 pages, 2647 KiB  
Article
Whole-Genome Sequencing Identifies PPARGC1A as a Putative Modifier of Cancer Risk in BRCA1/2 Mutation Carriers
by Qianqian Zhu, Jie Wang, Han Yu, Qiang Hu, Nicholas W. Bateman, Mark Long, Spencer Rosario, Emily Schultz, Clifton L. Dalgard, Matthew D. Wilkerson, Gauthaman Sukumar, Ruea-Yea Huang, Jasmine Kaur, Shashikant B. Lele, Emese Zsiros, Jeannine Villella, Amit Lugade, Kirsten Moysich, Thomas P. Conrads, George L. Maxwell and Kunle Odunsiadd Show full author list remove Hide full author list
Cancers 2022, 14(10), 2350; https://doi.org/10.3390/cancers14102350 - 10 May 2022
Cited by 1 | Viewed by 2068
Abstract
While BRCA1 and BRCA2 mutations are known to confer the largest risk of breast cancer and ovarian cancer, the incomplete penetrance of the mutations and the substantial variability in age at cancer onset among carriers suggest additional factors modifying the risk of cancer [...] Read more.
While BRCA1 and BRCA2 mutations are known to confer the largest risk of breast cancer and ovarian cancer, the incomplete penetrance of the mutations and the substantial variability in age at cancer onset among carriers suggest additional factors modifying the risk of cancer in BRCA1/2 mutation carriers. To identify genetic modifiers of BRCA1/2, we carried out a whole-genome sequencing study of 66 ovarian cancer patients that were enriched with BRCA carriers, followed by validation using data from the Pan-Cancer Analysis of Whole Genomes Consortium. We found PPARGC1A, a master regulator of mitochondrial biogenesis and function, to be highly mutated in BRCA carriers, and patients with both PPARGC1A and BRCA1/2 mutations were diagnosed with breast or ovarian cancer at significantly younger ages, while the mutation status of each gene alone did not significantly associate with age of onset. Our study suggests PPARGC1A as a possible BRCA modifier gene. Upon further validation, this finding can help improve cancer risk prediction and provide personalized preventive care for BRCA carriers. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

22 pages, 5557 KiB  
Article
A Bioinformatics Evaluation of the Role of Dual-Specificity Tyrosine-Regulated Kinases in Colorectal Cancer
by Amina Jamal Laham, Raafat El-Awady, Jean-Jacques Lebrun and Maha Saber Ayad
Cancers 2022, 14(8), 2034; https://doi.org/10.3390/cancers14082034 - 18 Apr 2022
Cited by 5 | Viewed by 3092
Abstract
Colorectal cancer (CRC) is the third most common cancer worldwide and has an increasing incidence in younger populations. The dual-specificity tyrosine-regulated kinase (DYRK) family has been implicated in various diseases, including cancer. However, the role and contribution of the distinct family members in [...] Read more.
Colorectal cancer (CRC) is the third most common cancer worldwide and has an increasing incidence in younger populations. The dual-specificity tyrosine-regulated kinase (DYRK) family has been implicated in various diseases, including cancer. However, the role and contribution of the distinct family members in regulating CRC tumorigenesis has not been addressed yet. Herein, we used publicly available CRC patient datasets (TCGA RNA sequence) and several bioinformatics webtools to perform in silico analysis (GTEx, GENT2, GEPIA2, cBioPortal, GSCALite, TIMER2, and UALCAN). We aimed to investigate the DYRK family member expression pattern, prognostic value, and oncological roles in CRC. This study shed light on the role of distinct DYRK family members in CRC and their potential outcome predictive value. Based on mRNA level, DYRK1A is upregulated in late tumor stages, with lymph node and distant metastasis. All DYRKs were found to be implicated in cancer-associated pathways, indicating their key role in CRC pathogenesis. No significant DYRK mutations were identified, suggesting that DYRK expression variation in normal vs. tumor samples is likely linked to epigenetic regulation. The expression of DYRK1A and DYRK3 expression correlated with immune-infiltrating cells in the tumor microenvironment and was upregulated in MSI subtypes, pointing to their potential role as biomarkers for immunotherapy. This comprehensive bioinformatics analysis will set directions for future biological studies to further exploit the molecular basis of these findings and explore the potential of DYRK1A modulation as a novel targeted therapy for CRC. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

15 pages, 3144 KiB  
Article
Simulating the Dynamic Intra-Tumor Heterogeneity and Therapeutic Responses
by Yongjing Liu, Cong Feng, Yincong Zhou, Xiaotian Shao and Ming Chen
Cancers 2022, 14(7), 1645; https://doi.org/10.3390/cancers14071645 - 24 Mar 2022
Viewed by 2167
Abstract
A tumor is a complex tissue comprised of heterogeneous cell subpopulations which exhibit substantial diversity at morphological, genetic and epigenetic levels. Under the selective pressure of cancer therapies, a minor treatment-resistant subpopulation could survive and repopulate. Therefore, the intra-tumor heterogeneity is recognized as [...] Read more.
A tumor is a complex tissue comprised of heterogeneous cell subpopulations which exhibit substantial diversity at morphological, genetic and epigenetic levels. Under the selective pressure of cancer therapies, a minor treatment-resistant subpopulation could survive and repopulate. Therefore, the intra-tumor heterogeneity is recognized as a major obstacle to effective treatment. In this paper, we propose a stochastic clonal expansion model to simulate the dynamic evolution of tumor subpopulations and the therapeutic effect at different times during tumor progression. The model is incorporated in the CES webserver, for the convenience of simulation according to initial user input. Based on this model, we investigate the influence of various factors on tumor progression and treatment consequences and present conclusions drawn from observations, highlighting the importance of treatment timing. The model provides an intuitive illustration to deepen the understanding of temporal intra-tumor heterogeneity dynamics and treatment responses, thus helping the improvement of personalized diagnostic and therapeutic strategies. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

16 pages, 2455 KiB  
Article
Classification of Breast Cancer Nottingham Prognostic Index Using High-Dimensional Embedding and Residual Neural Network
by Li Zhou, Maria Rueda and Abedalrhman Alkhateeb
Cancers 2022, 14(4), 934; https://doi.org/10.3390/cancers14040934 - 13 Feb 2022
Cited by 48 | Viewed by 4275
Abstract
The Nottingham Prognostics Index (NPI) is a prognostics measure that predicts operable primary breast cancer survival. The NPI value is calculated based on the size of the tumor, the number of lymph nodes, and the tumor grade. Next-generation sequencing advancements have led to [...] Read more.
The Nottingham Prognostics Index (NPI) is a prognostics measure that predicts operable primary breast cancer survival. The NPI value is calculated based on the size of the tumor, the number of lymph nodes, and the tumor grade. Next-generation sequencing advancements have led to measuring different biological indicators called multi-omics data. The availability of multi-omics data triggered the challenge of integrating and analyzing these various biological measures to understand the progression of the diseases. High-dimensional embedding techniques are incorporated to present the features in the lower dimension, i.e., in a 2-dimensional map. The dataset consists of three -omics: gene expression, copy number alteration (CNA), and mRNA from 1885 female patients. The model creates a gene similarity network (GSN) map for each omic using t-distributed stochastic neighbor embedding (t-SNE) before being merged into the residual neural network (ResNet) classification model. The aim of this work was to (i) extract multi-omics biomarkers that are associated with the prognosis and prediction of breast cancer survival; and (ii) build a prediction model for multi-class breast cancer NPI classes. We evaluated this model and compared it to different high-dimensional embedding techniques and neural network combinations. The proposed model outperformed the other methods with an accuracy of 98.48%, and the area under the curve (AUC) equals 0.9999. The findings in the literature confirm associations between some of the extracted omics and breast cancer prognosis and survival including CDCA5, IL17RB, MUC2, NOD2 and NXPH4 from the gene expression dataset; MED30, RAD21, EIF3H and EIF3E from the CNA dataset; and CENPA, MACF1, UGT2B7 and SEMA3B from the mRNA dataset. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

27 pages, 86576 KiB  
Article
UMAP Based Anomaly Detection for Minimal Residual Disease Quantification within Acute Myeloid Leukemia
by Lisa Weijler, Florian Kowarsch, Matthias Wödlinger, Michael Reiter, Margarita Maurer-Granofszky, Angela Schumich and Michael N. Dworzak
Cancers 2022, 14(4), 898; https://doi.org/10.3390/cancers14040898 - 11 Feb 2022
Cited by 6 | Viewed by 3946
Abstract
Leukemia is the most frequent malignancy in children and adolescents, with acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML) as the most common subtypes. Minimal residual disease (MRD) measured by flow cytometry (FCM) has proven to be a strong prognostic factor in [...] Read more.
Leukemia is the most frequent malignancy in children and adolescents, with acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML) as the most common subtypes. Minimal residual disease (MRD) measured by flow cytometry (FCM) has proven to be a strong prognostic factor in ALL as well as in AML. Machine learning techniques have been emerging in the field of automated MRD quantification with the objective of superseding subjective and time-consuming manual analysis of FCM-MRD data. In contrast to ALL, where supervised multi-class classification methods have been successfully deployed for MRD detection, AML poses new challenges: AML is rarer (with fewer available training data) than ALL and much more heterogeneous in its immunophenotypic appearance, where one-class classification (anomaly detection) methods seem more suitable. In this work, a new semi-supervised approach based on the UMAP algorithm for MRD detection utilizing only labels of blast free FCM samples is presented. The method is tested on a newly gathered set of AML FCM samples and results are compared to state-of-the-art methods. We reach a median F1-score of 0.794, while providing a transparent classification pipeline with explainable results that facilitates inter-disciplinary work between medical and technical experts. This work shows that despite several issues yet to overcome, the merits of automated MRD quantification can be fully exploited also in AML. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

20 pages, 5036 KiB  
Article
Implications of Stemness Features in 1059 Hepatocellular Carcinoma Patients from Five Cohorts: Prognosis, Treatment Response, and Identification of Potential Compounds
by Haoming Mai, Haisheng Xie, Mengqi Luo, Jia Hou, Jiaxuan Chen, Jinlin Hou and De-ke Jiang
Cancers 2022, 14(3), 563; https://doi.org/10.3390/cancers14030563 - 23 Jan 2022
Cited by 9 | Viewed by 3227
Abstract
Cancer stemness has been reported to drive hepatocellular carcinoma (HCC) tumorigenesis and treatment resistance. In this study, five HCC cohorts with 1059 patients were collected to calculate transcriptional stemness indexes (mRNAsi) by the one-class logistic regression machine learning algorithm. In the TCGA-LIHC cohort, [...] Read more.
Cancer stemness has been reported to drive hepatocellular carcinoma (HCC) tumorigenesis and treatment resistance. In this study, five HCC cohorts with 1059 patients were collected to calculate transcriptional stemness indexes (mRNAsi) by the one-class logistic regression machine learning algorithm. In the TCGA-LIHC cohort, we found mRNAsi was an independent prognostic factor, and 626 mRNAsi-related genes were identified by Spearman correlation analysis. The HCC stemness risk model (HSRM) was trained in the TCGA-LIHC cohort and significantly discriminated overall survival in four independent cohorts. HSRM was also significantly associated with transarterial chemoembolization treatment response and rapid tumor growth in HCC patients. Consensus clustering was conducted based on mRNAsi-related genes to divide 1059 patients into two stemness subtypes. On gene set variation analysis, samples of subtype I were found enriched with pathways such as DNA replication and cell cycle, while several liver-specific metabolic pathways were inhibited in these samples. Somatic mutation analysis revealed more frequent mutations of TP53 and RB1 in the subtype I samples. In silico analysis suggested topoisomerase, cyclin-dependent kinase, and histone deacetylase as potential targets to inhibit HCC stemness. In vitro assay showed two predicted compounds, Aminopurvalanol-a and NCH-51, effectively suppressed oncosphere formation and impaired viability of HCC cell lines, which may shed new light on HCC treatment. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

18 pages, 6470 KiB  
Article
Comprehensive Analysis of Co-Mutations Identifies Cooperating Mechanisms of Tumorigenesis
by Limin Jiang, Hui Yu, Scott Ness, Peng Mao, Fei Guo, Jijun Tang and Yan Guo
Cancers 2022, 14(2), 415; https://doi.org/10.3390/cancers14020415 - 14 Jan 2022
Cited by 8 | Viewed by 2888
Abstract
Somatic mutations are one of the most important factors in tumorigenesis and are the focus of most cancer-sequencing efforts. The co-occurrence of multiple mutations in one tumor has gained increasing attention as a means of identifying cooperating mutations or pathways that contribute to [...] Read more.
Somatic mutations are one of the most important factors in tumorigenesis and are the focus of most cancer-sequencing efforts. The co-occurrence of multiple mutations in one tumor has gained increasing attention as a means of identifying cooperating mutations or pathways that contribute to cancer. Using multi-omics, phenotypical, and clinical data from 29,559 cancer subjects and 1747 cancer cell lines covering 78 distinct cancer types, we show that co-mutations are associated with prognosis, drug sensitivity, and disparities in sex, age, and race. Some co-mutation combinations displayed stronger effects than their corresponding single mutations. For example, co-mutation TP53:KRAS in pancreatic adenocarcinoma is significantly associated with disease specific survival (hazard ratio = 2.87, adjusted p-value = 0.0003) and its prognostic predictive power is greater than either TP53 or KRAS as individually mutated genes. Functional analyses revealed that co-mutations with higher prognostic values have higher potential impact and cause greater dysregulation of gene expression. Furthermore, many of the prognostically significant co-mutations caused gains or losses of binding sequences of RNA binding proteins or micro RNAs with known cancer associations. Thus, detailed analyses of co-mutations can identify mechanisms that cooperate in tumorigenesis. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

15 pages, 1937 KiB  
Article
Classification of Clinically Significant Prostate Cancer on Multi-Parametric MRI: A Validation Study Comparing Deep Learning and Radiomics
by Jose M. Castillo T., Muhammad Arif, Martijn P. A. Starmans, Wiro J. Niessen, Chris H. Bangma, Ivo G. Schoots and Jifke F. Veenland
Cancers 2022, 14(1), 12; https://doi.org/10.3390/cancers14010012 - 21 Dec 2021
Cited by 21 | Viewed by 3812
Abstract
The computer-aided analysis of prostate multiparametric MRI (mpMRI) could improve significant-prostate-cancer (PCa) detection. Various deep-learning- and radiomics-based methods for significant-PCa segmentation or classification have been reported in the literature. To be able to assess the generalizability of the performance of these methods, using [...] Read more.
The computer-aided analysis of prostate multiparametric MRI (mpMRI) could improve significant-prostate-cancer (PCa) detection. Various deep-learning- and radiomics-based methods for significant-PCa segmentation or classification have been reported in the literature. To be able to assess the generalizability of the performance of these methods, using various external data sets is crucial. While both deep-learning and radiomics approaches have been compared based on the same data set of one center, the comparison of the performances of both approaches on various data sets from different centers and different scanners is lacking. The goal of this study was to compare the performance of a deep-learning model with the performance of a radiomics model for the significant-PCa diagnosis of the cohorts of various patients. We included the data from two consecutive patient cohorts from our own center (n = 371 patients), and two external sets of which one was a publicly available patient cohort (n = 195 patients) and the other contained data from patients from two hospitals (n = 79 patients). Using multiparametric MRI (mpMRI), the radiologist tumor delineations and pathology reports were collected for all patients. During training, one of our patient cohorts (n = 271 patients) was used for both the deep-learning- and radiomics-model development, and the three remaining cohorts (n = 374 patients) were kept as unseen test sets. The performances of the models were assessed in terms of their area under the receiver-operating-characteristic curve (AUC). Whereas the internal cross-validation showed a higher AUC for the deep-learning approach, the radiomics model obtained AUCs of 0.88, 0.91 and 0.65 on the independent test sets compared to AUCs of 0.70, 0.73 and 0.44 for the deep-learning model. Our radiomics model that was based on delineated regions resulted in a more accurate tool for significant-PCa classification in the three unseen test sets when compared to a fully automated deep-learning model. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

15 pages, 4052 KiB  
Article
Identification of Genetic Variants Associated with Sex-Specific Lung-Cancer Risk
by Xiaoshun Shi, Sylvia Young and Grant Morahan
Cancers 2021, 13(24), 6379; https://doi.org/10.3390/cancers13246379 - 20 Dec 2021
Cited by 3 | Viewed by 1968
Abstract
Background: The incidence of lung cancer differs between men and women, suggesting the potential role of sex-specific influences in susceptibility to this cancer. While behavioural differences may account for some of the risk, another possibility is that X chromosome susceptibility genes may have [...] Read more.
Background: The incidence of lung cancer differs between men and women, suggesting the potential role of sex-specific influences in susceptibility to this cancer. While behavioural differences may account for some of the risk, another possibility is that X chromosome susceptibility genes may have an effect. Little is known about genetic variants on the X chromosome that contribute to sex-specific lung-cancer risk, so we investigated this in a previously characterized cohort. Methods: We conducted a genetic association reanalysis of 518 lung cancer patients and 844 controls to test for lung cancer susceptibility variants on the X chromosome. Annotated gene expression, co-expression analysis, pathway, and immune infiltration analyses were also performed. Results: 24 SNPs were identified as significantly associated with male, but not female, lung cancer cases. These resided in blocks near the annotated genes DMD, PTCHD1-AS, and AL008633.1. Of these, DMD was differentially expressed in lung cancer cases curated in The Cancer Genome Atlas. A functional enrichment and a KEGG pathway analysis of co-expressed genes revealed that differences in immune function could play a role in sex-specific susceptibility. Conclusions: Our analyses identified potential genetic variants associated with sex-specific lung cancer risk. Integrating GWAS and RNA-sequencing data revealed potential targets for lung cancer prevention. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Graphical abstract

13 pages, 1556 KiB  
Article
Machine Learning Incorporating Host Factors for Predicting Survival in Head and Neck Squamous Cell Carcinoma Patients
by Han Yu, Sung Jun Ma, Mark Farrugia, Austin J. Iovoli, Kimberly E. Wooten, Vishal Gupta, Ryan P. McSpadden, Moni A. Kuriakose, Michael R. Markiewicz, Jon M. Chan, Wesley L. Hicks, Jr., Mary E. Platek and Anurag K. Singh
Cancers 2021, 13(18), 4559; https://doi.org/10.3390/cancers13184559 - 11 Sep 2021
Cited by 6 | Viewed by 2053
Abstract
Prognostication for cancer patients is integral for patient counseling and treatment planning, yet providing accurate prediction can be challenging using existing patient-specific clinical indicators and host factors. In this work, we evaluated common machine learning models in predicting head and neck squamous cell [...] Read more.
Prognostication for cancer patients is integral for patient counseling and treatment planning, yet providing accurate prediction can be challenging using existing patient-specific clinical indicators and host factors. In this work, we evaluated common machine learning models in predicting head and neck squamous cell carcinoma (HNSCC) patients’ overall survival based on demographic, clinical features and host factors. We found random survival forest had best performance among the models evaluated, which achieved a C-index of 0.729 and AUROC of 0.792 in predicting two-year overall survival. In addition, we verified that host factors are independently predictive of HNSCC overall survival, which improved the C-index by a margin of 0.026 and the AUROC by 0.034. Due to the strong correlation among host factors, we showed that proper dimension reduction is an important step before their incorporation into the machine learning models, which provides a host factor score reflecting the patients’ nutrition and inflammation status. The score by itself showed excellent discriminating capacity with the high-risk group having a hazard ratio of 3.76 (1.93–7.32, p < 0.0001) over the low-risk group. The hazard ratios were further improved to 7.41 (3.66–14.98, p < 0.0001) by the random survival forest model after including demographic and clinical features. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

22 pages, 4731 KiB  
Article
Whole-Genome Analysis of De Novo Somatic Point Mutations Reveals Novel Mutational Biomarkers in Pancreatic Cancer
by Amin Ghareyazi, Amir Mohseni, Hamed Dashti, Amin Beheshti, Abdollah Dehzangi, Hamid R. Rabiee and Hamid Alinejad-Rokny
Cancers 2021, 13(17), 4376; https://doi.org/10.3390/cancers13174376 - 30 Aug 2021
Cited by 9 | Viewed by 2786
Abstract
It is now known that at least 10% of samples with pancreatic cancers (PC) contain a causative mutation in the known susceptibility genes, suggesting the importance of identifying cancer-associated genes that carry the causative mutations in high-risk individuals for early detection of PC. [...] Read more.
It is now known that at least 10% of samples with pancreatic cancers (PC) contain a causative mutation in the known susceptibility genes, suggesting the importance of identifying cancer-associated genes that carry the causative mutations in high-risk individuals for early detection of PC. In this study, we develop a statistical pipeline using a new concept, called gene-motif, that utilizes both mutated genes and mutational processes to identify 4211 3-nucleotide PC-associated gene-motifs within 203 significantly mutated genes in PC. Using these gene-motifs as distinguishable features for pancreatic cancer subtyping results in identifying five PC subtypes with distinguishable phenotypes and genotypes. Our comprehensive biological characterization reveals that these PC subtypes are associated with different molecular mechanisms including unique cancer related signaling pathways, in which for most of the subtypes targeted treatment options are currently available. Some of the pathways we identified in all five PC subtypes, including cell cycle and the Axon guidance pathway are frequently seen and mutated in cancer. We also identified Protein kinase C, EGFR (epidermal growth factor receptor) signaling pathway and P53 signaling pathways as potential targets for treatment of the PC subtypes. Altogether, our results uncover the importance of considering both the mutation type and mutated genes in the identification of cancer subtypes and biomarkers. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Graphical abstract

22 pages, 3067 KiB  
Article
Transcriptional Reprogramming and Constitutive PD-L1 Expression in Melanoma Are Associated with Dedifferentiation and Activation of Interferon and Tumour Necrosis Factor Signalling Pathways
by Antonio Ahn, Euan J. Rodger, Jyoti Motwani, Gregory Gimenez, Peter A. Stockwell, Matthew Parry, Peter Hersey, Aniruddha Chatterjee and Michael R. Eccles
Cancers 2021, 13(17), 4250; https://doi.org/10.3390/cancers13174250 - 24 Aug 2021
Cited by 12 | Viewed by 3452
Abstract
Melanoma is the most aggressive type of skin cancer, with increasing incidence worldwide. Advances in targeted therapy and immunotherapy have improved the survival of melanoma patients experiencing recurrent disease, but unfortunately treatment resistance frequently reduces patient survival. Resistance to targeted therapy is associated [...] Read more.
Melanoma is the most aggressive type of skin cancer, with increasing incidence worldwide. Advances in targeted therapy and immunotherapy have improved the survival of melanoma patients experiencing recurrent disease, but unfortunately treatment resistance frequently reduces patient survival. Resistance to targeted therapy is associated with transcriptomic changes and has also been shown to be accompanied by increased expression of programmed death ligand 1 (PD-L1), a potent inhibitor of immune response. Intrinsic upregulation of PD-L1 is associated with genome-wide DNA hypomethylation and widespread alterations in gene expression in melanoma cell lines. However, an in-depth analysis of the transcriptomic landscape of melanoma cells with intrinsically upregulated PD-L1 expression is lacking. To determine the transcriptomic landscape of intrinsically upregulated PD-L1 expression in melanoma, we investigated transcriptomes in melanomas with constitutive versus inducible PD-L1 expression (referred to as PD-L1CON and PD-L1IND). RNA-Seq analysis was performed on seven PD-L1CON melanoma cell lines and ten melanoma cell lines with low inducible PD-L1IND expression. We observed that PD-L1CON melanoma cells had a reprogrammed transcriptome with a characteristic pattern of dedifferentiated gene expression, together with active interferon (IFN) and tumour necrosis factor (TNF) signalling pathways. Furthermore, we identified key transcription factors that were also differentially expressed in PD-L1CON versus PD-L1IND melanoma cell lines. Overall, our studies describe transcriptomic reprogramming of melanomas with PD-L1CON expression. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Graphical abstract

20 pages, 6827 KiB  
Article
Identification of Cancer Hub Gene Signatures Associated with Immune-Suppressive Tumor Microenvironment and Ovatodiolide as a Potential Cancer Immunotherapeutic Agent
by Jia-Hong Chen, Alexander T. H. Wu, Bashir Lawal, David T. W. Tzeng, Jih-Chin Lee, Ching-Liang Ho and Tsu-Yi Chao
Cancers 2021, 13(15), 3847; https://doi.org/10.3390/cancers13153847 - 30 Jul 2021
Cited by 24 | Viewed by 3844
Abstract
Despite the significant advancement in therapeutic strategies, breast, colorectal, gastric, lung, liver, and prostate cancers remain the most prevalent cancers in terms of incidence and mortality worldwide. The major causes ascribed to these burdens are lack of early diagnosis, high metastatic tendency, and [...] Read more.
Despite the significant advancement in therapeutic strategies, breast, colorectal, gastric, lung, liver, and prostate cancers remain the most prevalent cancers in terms of incidence and mortality worldwide. The major causes ascribed to these burdens are lack of early diagnosis, high metastatic tendency, and drug resistance. Therefore, exploring reliable early diagnostic and prognostic biomarkers universal to most cancer types is a clinical emergency. Consequently, in the present study, the differentially expressed genes (DEGs) from the publicly available microarray datasets of six cancer types (liver, lung colorectal, gastric, prostate, and breast cancers), termed hub cancers, were analyzed to identify the universal DEGs, termed hub genes. Gene set enrichment analysis (GSEA) and KEGG mapping of the hub genes suggested their crucial involvement in the tumorigenic properties, including distant metastases, treatment failure, and survival prognosis. Notably, our results suggested high frequencies of genetic and epigenetic alterations of the DEGs in association with tumor staging, immune evasion, poor prognosis, and therapy resistance. Translationally, we intended to identify a drug candidate with the potential for targeting the hub genes. Using a molecular docking platform, we estimated that ovatodiolide, a bioactive anti-cancer phytochemical, has high binding affinities to the binding pockets of the hub genes. Collectively, our results suggested that the hub genes were associated with establishing an immune-suppressive tumor microenvironment favorable for disease progression and promising biomarkers for the early diagnosis and prognosis in multiple cancer types and could serve as potential druggable targets for ovatodiolide. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

27 pages, 5400 KiB  
Article
High-Resolution Cartography of the Transcriptome and Methylome Landscapes of Diffuse Gliomas
by Edith Willscher, Lydia Hopp, Markus Kreuz, Maria Schmidt, Siras Hakobyan, Arsen Arakelyan, Bettina Hentschel, David T. W. Jones, Stefan M. Pfister, Markus Loeffler, Henry Loeffler-Wirth and Hans Binder
Cancers 2021, 13(13), 3198; https://doi.org/10.3390/cancers13133198 - 26 Jun 2021
Cited by 6 | Viewed by 2738
Abstract
Molecular mechanisms of lower-grade (II–III) diffuse gliomas (LGG) are still poorly understood, mainly because of their heterogeneity. They split into astrocytoma- (IDH-A) and oligodendroglioma-like (IDH-O) tumors both carrying mutations(s) at the isocitrate dehydrogenase (IDH) gene and into IDH wild type (IDH-wt) gliomas of [...] Read more.
Molecular mechanisms of lower-grade (II–III) diffuse gliomas (LGG) are still poorly understood, mainly because of their heterogeneity. They split into astrocytoma- (IDH-A) and oligodendroglioma-like (IDH-O) tumors both carrying mutations(s) at the isocitrate dehydrogenase (IDH) gene and into IDH wild type (IDH-wt) gliomas of glioblastoma resemblance. We generated detailed maps of the transcriptomes and DNA methylomes, revealing that cell functions divided into three major archetypic hallmarks: (i) increased proliferation in IDH-wt and, to a lesser degree, IDH-O; (ii) increased inflammation in IDH-A and IDH-wt; and (iii) the loss of synaptic transmission in all subtypes. Immunogenic properties of IDH-A are diverse, partly resembling signatures observed in grade IV mesenchymal glioblastomas or in grade I pilocytic astrocytomas. We analyzed details of coregulation between gene expression and DNA methylation and of the immunogenic micro-environment presumably driving tumor development and treatment resistance. Our transcriptome and methylome maps support personalized, case-by-case views to decipher the heterogeneity of glioma states in terms of data portraits. Thereby, molecular cartography provides a graphical coordinate system that links gene-level information with glioma subtypes, their phenotypes, and clinical context. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

33 pages, 8333 KiB  
Article
A Comprehensive Bioinformatics Analysis of Notch Pathways in Bladder Cancer
by Chuan Zhang, Mandy Berndt-Paetz and Jochen Neuhaus
Cancers 2021, 13(12), 3089; https://doi.org/10.3390/cancers13123089 - 21 Jun 2021
Cited by 15 | Viewed by 3958
Abstract
Background: A hallmark of Notch signaling is its variable role in tumor biology, ranging from tumor-suppressive to oncogenic effects. Until now, the mechanisms and functions of Notch pathways in bladder cancer (BCa) are still unclear. Methods: We used publicly available data from the [...] Read more.
Background: A hallmark of Notch signaling is its variable role in tumor biology, ranging from tumor-suppressive to oncogenic effects. Until now, the mechanisms and functions of Notch pathways in bladder cancer (BCa) are still unclear. Methods: We used publicly available data from the GTEx and TCGA-BLCA databases to explore the role of the canonical Notch pathways in BCa on the basis of the RNA expression levels of Notch receptors, ligands, and downstream genes. For statistical analyses of cancer and non-cancerous samples, we used R software packages and public databases/webservers. Results: We found differential expression between control and BCa samples for all Notch receptors (NOTCH1, 2, 3, 4), the delta-like Notch ligands (DLL1, 3, 4), and the typical downstream gene hairy and enhancer of split 1 (HES1). NOTCH2/3 and DLL4 can significantly differentiate non-cancerous samples from cancers and were broadly altered in subgroups. High expression levels of NOTCH2/3 receptors correlated with worse overall survival (OS) and shorter disease-free survival (DFS). However, at long-term (>8 years) follow-up, NOTCH2 expression was associated with a better OS and DFS. Furthermore, the cases with the high levels of DLL4 were associated with worse OS but improved DFS. Pathway network analysis revealed that NOTCH2/3 in particular correlated with cell cycle, epithelial–mesenchymal transition (EMT), numbers of lymphocyte subtypes, and modulation of the immune system. Conclusions: NOTCH2/3 and DLL4 are potential drivers of Notch signaling in BCa, indicating that Notch and associated pathways play an essential role in the progression and prognosis of BCa through directly modulating immune cells or through interaction with cell cycle and EMT. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Graphical abstract

33 pages, 477 KiB  
Article
Structured Reporting of Rectal Cancer Staging and Restaging: A Consensus Proposal
by Vincenza Granata, Damiano Caruso, Roberto Grassi, Salvatore Cappabianca, Alfonso Reginelli, Roberto Rizzati, Gabriele Masselli, Rita Golfieri, Marco Rengo, Daniele Regge, Giuseppe Lo Re, Silvia Pradella, Roberta Fusco, Lorenzo Faggioni, Andrea Laghi, Vittorio Miele, Emanuele Neri and Francesca Coppola
Cancers 2021, 13(9), 2135; https://doi.org/10.3390/cancers13092135 - 28 Apr 2021
Cited by 33 | Viewed by 3016
Abstract
Background: Structured reporting (SR) in oncologic imaging is becoming necessary and has recently been recognized by major scientific societies. The aim of this study was to build MRI-based structured reports for rectal cancer (RC) staging and restaging in order to provide clinicians all [...] Read more.
Background: Structured reporting (SR) in oncologic imaging is becoming necessary and has recently been recognized by major scientific societies. The aim of this study was to build MRI-based structured reports for rectal cancer (RC) staging and restaging in order to provide clinicians all critical tumor information. Materials and Methods: A panel of radiologist experts in abdominal imaging, called the members of the Italian Society of Medical and Interventional Radiology, was established. The modified Delphi process was used to build the SR and to assess the level of agreement in all sections. The Cronbach’s alpha (Cα) correlation coefficient was used to assess the internal consistency of each section and to measure the quality analysis according to the average inter-item correlation. The intraclass correlation coefficient (ICC) was also evaluated. Results: After the second Delphi round of the SR RC staging, the panelists’ single scores and sum of scores were 3.8 (range 2–4) and 169, and the SR RC restaging panelists’ single scores and sum of scores were 3.7 (range 2–4) and 148, respectively. The Cα correlation coefficient was 0.79 for SR staging and 0.81 for SR restaging. The ICCs for the SR RC staging and restaging were 0.78 (p < 0.01) and 0.82 (p < 0.01), respectively. The final SR version was built and included 53 items for RC staging and 50 items for RC restaging. Conclusions: The final version of the structured reports of MRI-based RC staging and restaging should be a helpful and promising tool for clinicians in managing cancer patients properly. Structured reports collect all Patient Clinical Data, Clinical Evaluations and relevant key findings of Rectal Cancer, both in staging and restaging, and can facilitate clinical decision-making. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Figure 1

24 pages, 2209 KiB  
Article
Reverse Engineering of Ewing Sarcoma Regulatory Network Uncovers PAX7 and RUNX3 as Master Regulators Associated with Good Prognosis
by Marcel da Câmara Ribeiro-Dantas, Danilo Oliveira Imparato, Matheus Gibeke Siqueira Dalmolin, Caroline Brunetto de Farias, André Tesainer Brunetto, Mariane da Cunha Jaeger, Rafael Roesler, Marialva Sinigaglia and Rodrigo Juliani Siqueira Dalmolin
Cancers 2021, 13(8), 1860; https://doi.org/10.3390/cancers13081860 - 13 Apr 2021
Cited by 9 | Viewed by 3464
Abstract
Ewing Sarcoma (ES) is a rare malignant tumor occurring most frequently in adolescents and young adults. The ES hallmark is a chromosomal translocation between the chromosomes 11 and 22 that results in an aberrant transcription factor (TF) through the fusion of genes from [...] Read more.
Ewing Sarcoma (ES) is a rare malignant tumor occurring most frequently in adolescents and young adults. The ES hallmark is a chromosomal translocation between the chromosomes 11 and 22 that results in an aberrant transcription factor (TF) through the fusion of genes from the FET and ETS families, commonly EWSR1 and FLI1. The regulatory mechanisms behind the ES transcriptional alterations remain poorly understood. Here, we reconstruct the ES regulatory network using public available transcriptional data. Seven TFs were identified as potential MRs and clustered into two groups: one composed by PAX7 and RUNX3, and another composed by ARNT2, CREB3L1, GLI3, MEF2C, and PBX3. The MRs within each cluster act as reciprocal agonists regarding the regulation of shared genes, regulon activity, and implications in clinical outcome, while the clusters counteract each other. The regulons of all the seven MRs were differentially methylated. PAX7 and RUNX3 regulon activity were associated with good prognosis while ARNT2, CREB3L1, GLI3, and PBX3 were associated with bad prognosis. PAX7 and RUNX3 appear as highly expressed in ES biopsies and ES cell lines. This work contributes to the understanding of the ES regulome, identifying candidate MRs, analyzing their methilome and pointing to potential prognostic factors. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Graphical abstract

Review

Jump to: Research

16 pages, 1771 KiB  
Review
Bias and Class Imbalance in Oncologic Data—Towards Inclusive and Transferrable AI in Large Scale Oncology Data Sets
by Erdal Tasci, Ying Zhuge, Kevin Camphausen and Andra V. Krauze
Cancers 2022, 14(12), 2897; https://doi.org/10.3390/cancers14122897 - 12 Jun 2022
Cited by 37 | Viewed by 14069
Abstract
Recent technological developments have led to an increase in the size and types of data in the medical field derived from multiple platforms such as proteomic, genomic, imaging, and clinical data. Many machine learning models have been developed to support precision/personalized medicine initiatives [...] Read more.
Recent technological developments have led to an increase in the size and types of data in the medical field derived from multiple platforms such as proteomic, genomic, imaging, and clinical data. Many machine learning models have been developed to support precision/personalized medicine initiatives such as computer-aided detection, diagnosis, prognosis, and treatment planning by using large-scale medical data. Bias and class imbalance represent two of the most pressing challenges for machine learning-based problems, particularly in medical (e.g., oncologic) data sets, due to the limitations in patient numbers, cost, privacy, and security of data sharing, and the complexity of generated data. Depending on the data set and the research question, the methods applied to address class imbalance problems can provide more effective, successful, and meaningful results. This review discusses the essential strategies for addressing and mitigating the class imbalance problems for different medical data types in the oncologic domain. Full article
(This article belongs to the Special Issue Bioinformatics, Big Data and Cancer)
►▼ Show Figures

Graphical abstract

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-21
Back to TopTop