{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/137647"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/137647","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"CancerSubtyper: A Web-Based Deep Learning Platform for Cancer Subtyping Through DNA Methylation Data","abstract":"Cancer subtyping plays a critical role in understanding tumor heterogeneity, predicting patient outcomes, and guiding personalized therapies. While DNA methylation data offers an informative molecular source for subtyping, leveraging its signals across cohorts remains challenging due to high dimensionality, batch effects, and lack of standardized tools. In this thesis, we present CancerSubtyper, a web-based deep learning platform that enables both supervised classification and semi-supervised discovery of cancer subtypes using methylation data. The platform incorporates two models: BCtypeFinder, designed for subtype prediction with domain adaptation, and CancerSubminer, a flexible model for subtype discovery or refinement with potential applicability across different cancer types. Users can upload labeled and unlabeled datasets, select models, and visualize results through various interactive plots including UMAP projections, boxplots, and Kaplan–Meier survival curves. We evaluate the platform using The Cancer Genome Atlas (TCGA) breast cancer cohort, demonstrating distinct cancer subtypes, effective batch correction, and clinical relevance via survival analysis. CancerSubtyper provides a reproducible, user-oriented platform that streamlines cancer subtype analysis using DNA methylation data. It bridges a methodological gap by enabling both classification and discovery tasks, supports batch correction across datasets, and facilitates result interpretation through interactive visualizations. Designed for accessibility, the platform requires no programming expertise, making it a practical tool for researchers and clinicians to explore cancer subtypes and contribute to personalized care.","abstract_html":"Cancer subtyping plays a critical role in understanding tumor heterogeneity, predicting patient outcomes, and guiding personalized therapies. While DNA methylation data offers an informative molecular source for subtyping, leveraging its signals across cohorts remains challenging due to high dimensionality, batch effects, and lack of standardized tools. In this thesis, we present CancerSubtyper, a web-based deep learning platform that enables both supervised classification and semi-supervised discovery of cancer subtypes using methylation data. The platform incorporates two models: BCtypeFinder, designed for subtype prediction with domain adaptation, and CancerSubminer, a flexible model for subtype discovery or refinement with potential applicability across different cancer types. Users can upload labeled and unlabeled datasets, select models, and visualize results through various interactive plots including UMAP projections, boxplots, and Kaplan–Meier survival curves. We evaluate the platform using The Cancer Genome Atlas (TCGA) breast cancer cohort, demonstrating distinct cancer subtypes, effective batch correction, and clinical relevance via survival analysis. CancerSubtyper provides a reproducible, user-oriented platform that streamlines cancer subtype analysis using DNA methylation data. It bridges a methodological gap by enabling both classification and discovery tasks, supports batch correction across datasets, and facilitates result interpretation through interactive visualizations. Designed for accessibility, the platform requires no programming expertise, making it a practical tool for researchers and clinicians to explore cancer subtypes and contribute to personalized care.","abstract_has_math":false,"creators":["Cheung, Yat Fei"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Computer Science & Applications","degree_department":"Computer Science and#38; Applications","school":null,"contributors":[],"advisors":[],"committee_chairs":["Zhang, Liqing"],"committee_members":["Lu, Chang Tien","Meng, Na"],"year":2025,"date_issued":"2025-09-08","date_published":"2025-09-08","updated_at":"2026-07-22T22:18:47Z","subjects":["Bioinformatics","Deep Learning","Web Development","Cancer Subtyping","DNA Methylation","Epigenetics"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44631"],"render_values":[{"text":"vt_gsexam:44631","href":null,"code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10919/137647","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Zhang, Liqing"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Lu, Chang Tien","Meng, Na"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science and#38; Applications"]},{"key":"dc:creator","label":"Author","values":["Cheung, Yat Fei"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-09T08:01:43Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-09T08:01:43Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-09-08"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science & Applications"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Bioinformatics","Deep Learning","Web Development","Cancer Subtyping","DNA Methylation","Epigenetics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:44631"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10919/137647"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Cancer subtyping plays a critical role in understanding tumor heterogeneity, predicting patient outcomes, and guiding personalized therapies. While DNA methylation data offers an informative molecular source for subtyping, leveraging its signals across cohorts remains challenging due to high dimensionality, batch effects, and lack of standardized tools. In this thesis, we present CancerSubtyper, a web-based deep learning platform that enables both supervised classification and semi-supervised discovery of cancer subtypes using methylation data. The platform incorporates two models: BCtypeFinder, designed for subtype prediction with domain adaptation, and CancerSubminer, a flexible model for subtype discovery or refinement with potential applicability across different cancer types. Users can upload labeled and unlabeled datasets, select models, and visualize results through various interactive plots including UMAP projections, boxplots, and Kaplan–Meier survival curves. We evaluate the platform using The Cancer Genome Atlas (TCGA) breast cancer cohort, demonstrating distinct cancer subtypes, effective batch correction, and clinical relevance via survival analysis. CancerSubtyper provides a reproducible, user-oriented platform that streamlines cancer subtype analysis using DNA methylation data. It bridges a methodological gap by enabling both classification and discovery tasks, supports batch correction across datasets, and facilitates result interpretation through interactive visualizations. Designed for accessibility, the platform requires no programming expertise, making it a practical tool for researchers and clinicians to explore cancer subtypes and contribute to personalized care."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["This thesis presents CancerSubtyper, a web-based platform that uses deep learning to support cancer subtyping with DNA methylation data. The platform integrates BCtypeFinder for supervised subtype prediction and CancerSubminer for semi-supervised subtype discovery or refinement, all within an automated workflow that requires no programming expertise. Users can upload labeled or unlabeled datasets, after which the system performs preprocessing, batch effect correction, and subtype analysis, and then provides results through interactive visualizations including UMAP projections, heatmaps, boxplots, and Kaplan–Meier survival curves. The platform was evaluated on The Cancer Genome Atlas breast cancer cohort, where it successfully recovered distinct subtypes, corrected for batch effects, and revealed clinically relevant differences in patient survival. Overall, CancerSubtyper delivers accurate, interpretable, and reproducible subtyping analyses, lowering the barrier for researchers to conduct large-scale methylation-based cancer studies."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["CancerSubtyper: A Web-Based Deep Learning Platform for Cancer Subtyping Through DNA Methylation Data"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Zhang, Liqing"],"dc:contributor.committeemember":["Lu, Chang Tien","Meng, Na"],"dc:contributor.department":["Computer Science and#38; Applications"],"dc:creator":["Cheung, Yat Fei"],"dc:date.accessioned":["2025-09-09T08:01:43Z"],"dc:date.available":["2025-09-09T08:01:43Z"],"dc:date.issued":["2025-09-08"],"dc:description.abstract":["Cancer subtyping plays a critical role in understanding tumor heterogeneity, predicting patient outcomes, and guiding personalized therapies. While DNA methylation data offers an informative molecular source for subtyping, leveraging its signals across cohorts remains challenging due to high dimensionality, batch effects, and lack of standardized tools. In this thesis, we present CancerSubtyper, a web-based deep learning platform that enables both supervised classification and semi-supervised discovery of cancer subtypes using methylation data. The platform incorporates two models: BCtypeFinder, designed for subtype prediction with domain adaptation, and CancerSubminer, a flexible model for subtype discovery or refinement with potential applicability across different cancer types. Users can upload labeled and unlabeled datasets, select models, and visualize results through various interactive plots including UMAP projections, boxplots, and Kaplan–Meier survival curves. We evaluate the platform using The Cancer Genome Atlas (TCGA) breast cancer cohort, demonstrating distinct cancer subtypes, effective batch correction, and clinical relevance via survival analysis. CancerSubtyper provides a reproducible, user-oriented platform that streamlines cancer subtype analysis using DNA methylation data. It bridges a methodological gap by enabling both classification and discovery tasks, supports batch correction across datasets, and facilitates result interpretation through interactive visualizations. Designed for accessibility, the platform requires no programming expertise, making it a practical tool for researchers and clinicians to explore cancer subtypes and contribute to personalized care."],"dc:description.abstractgeneral":["This thesis presents CancerSubtyper, a web-based platform that uses deep learning to support cancer subtyping with DNA methylation data. The platform integrates BCtypeFinder for supervised subtype prediction and CancerSubminer for semi-supervised subtype discovery or refinement, all within an automated workflow that requires no programming expertise. Users can upload labeled or unlabeled datasets, after which the system performs preprocessing, batch effect correction, and subtype analysis, and then provides results through interactive visualizations including UMAP projections, heatmaps, boxplots, and Kaplan–Meier survival curves. The platform was evaluated on The Cancer Genome Atlas breast cancer cohort, where it successfully recovered distinct subtypes, corrected for batch effects, and revealed clinically relevant differences in patient survival. Overall, CancerSubtyper delivers accurate, interpretable, and reproducible subtyping analyses, lowering the barrier for researchers to conduct large-scale methylation-based cancer studies."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:44631"],"dc:identifier.uri":["https://hdl.handle.net/10919/137647"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Bioinformatics","Deep Learning","Web Development","Cancer Subtyping","DNA Methylation","Epigenetics"],"dc:title":["CancerSubtyper: A Web-Based Deep Learning Platform for Cancer Subtyping Through DNA Methylation Data"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science & Applications"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:18:47Z"}