{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_53271"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_53271","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"Classifying the game-theoretic interaction between drug-sensitive and drug-resistant cancer cells","abstract":"Thesis (Ph.D.)--Michigan State University. Computer Science - Doctor of Philosophy, 2026","abstract_html":"Thesis (Ph.D.)--Michigan State University. Computer Science - Doctor of Philosophy, 2026","abstract_has_math":false,"creators":["Leither, Sydney"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Dolson, Emily","Ofria, Charles","Klausmeier, Christopher","Adami, Christoph"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-18T18:59:44Z","subjects":["Biology","Computer science","Oncology"],"languages":["eng"],"rights":["Attribution 4.0 International"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53271","local:Leither_grad.msu_0128D_22319"],"render_values":[{"text":"etd:53271","href":null,"code":true},{"text":"local:Leither_grad.msu_0128D_22319","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/2vr5-k711","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/2vr5-k711","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_53271","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dolson, Emily","Ofria, Charles","Klausmeier, Christopher","Adami, Christoph"]},{"key":"dc:creator","label":"Author","values":["Leither, Sydney"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Biology","Computer science","Oncology"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:53271","local:Leither_grad.msu_0128D_22319","https://doi.org/doi:10.25335/2vr5-k711"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph.D.)--Michigan State University. Computer Science - Doctor of Philosophy, 2026","Cancer occurs when accumulated mutations lead cells to lose restraints on proliferation. As cancer cells reproduce, ongoing mutations, epigenetics, and environmental effects form heterogeneous tumors, which creates a dynamic ecosystem where phenotypically distinct subpopulations of cells compete and cooperate for limited resources. Cancer is therefore an eco-evolutionary system: cancer cells exhibit heritable variation and differential reproduction which produces distinct subpopulations. The standard-of-care treatment approach applies the maximum tolerated dose to kill as many cancer cells as possible. However, this approach ignores the tumor's eco-evolutionary dynamics, often resulting in drug resistance and relapse. Treatment holiday approaches dynamically start and stop drug application to prevent resistant cells from taking over the tumor population. A method to measure the ecological interaction between subpopulations within a tumor would provide insight into whether resistant cells will indeed be reduced during treatment holidays due to competition with sensitive cells. Here, I demonstrate that ecological interactions between drug-sensitive and drug-resistant cancer cells can be inferred from both temporal and spatial data, but classification performance depends on both data modality and predictive model.I start by validating temporal approaches to classifying the game-theoretic interaction between sensitive and resistant cells by fitting mathematical models to synthetic data with ground truth interactions. I then apply the most accurate model to classify the interaction in in vitro data. While the temporal approaches perform well classifying the game-theoretic interaction in synthetic data, temporal approaches are not applicable clinically. Instead, I then focus on classifying game-theoretic interactions from single time-point spatial data. Because single time-point spatial data may require more expressive predictive models, I introduce the quantum machine learning resource estimation framework, which quantifies the potential for quantum machine learning to out-perform classical machine learning on a given learning problem. I apply the framework to a suite of benchmark oncology datasets and find no evidence for a quantum advantage. Finally, the framework shows no evidence for a quantum advantage in classifying interactions from single time-point synthetic spatial data. Instead, I find that a variety of predictive models --- from those trained on spatial data to those trained on spatial statistics extracted from spatial data --- can classify the interaction with up to 80% accuracy. Overall, this work suggests that different game-theoretic interactions produce quantifiably different temporal and spatial patterns that could inform cancer treatment.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (130 p.) : ill."]},{"key":"dc:title","label":"Title","values":["Classifying the game-theoretic interaction between drug-sensitive and drug-resistant cancer cells"]}]}],"canonical_facts":{"dc:contributor":["Dolson, Emily","Ofria, Charles","Klausmeier, Christopher","Adami, Christoph"],"dc:creator":["Leither, Sydney"],"dc:date":["2026"],"dc:description":["Thesis (Ph.D.)--Michigan State University. Computer Science - Doctor of Philosophy, 2026","Cancer occurs when accumulated mutations lead cells to lose restraints on proliferation. As cancer cells reproduce, ongoing mutations, epigenetics, and environmental effects form heterogeneous tumors, which creates a dynamic ecosystem where phenotypically distinct subpopulations of cells compete and cooperate for limited resources. Cancer is therefore an eco-evolutionary system: cancer cells exhibit heritable variation and differential reproduction which produces distinct subpopulations. The standard-of-care treatment approach applies the maximum tolerated dose to kill as many cancer cells as possible. However, this approach ignores the tumor's eco-evolutionary dynamics, often resulting in drug resistance and relapse. Treatment holiday approaches dynamically start and stop drug application to prevent resistant cells from taking over the tumor population. A method to measure the ecological interaction between subpopulations within a tumor would provide insight into whether resistant cells will indeed be reduced during treatment holidays due to competition with sensitive cells. Here, I demonstrate that ecological interactions between drug-sensitive and drug-resistant cancer cells can be inferred from both temporal and spatial data, but classification performance depends on both data modality and predictive model.I start by validating temporal approaches to classifying the game-theoretic interaction between sensitive and resistant cells by fitting mathematical models to synthetic data with ground truth interactions. I then apply the most accurate model to classify the interaction in in vitro data. While the temporal approaches perform well classifying the game-theoretic interaction in synthetic data, temporal approaches are not applicable clinically. Instead, I then focus on classifying game-theoretic interactions from single time-point spatial data. Because single time-point spatial data may require more expressive predictive models, I introduce the quantum machine learning resource estimation framework, which quantifies the potential for quantum machine learning to out-perform classical machine learning on a given learning problem. I apply the framework to a suite of benchmark oncology datasets and find no evidence for a quantum advantage. Finally, the framework shows no evidence for a quantum advantage in classifying interactions from single time-point synthetic spatial data. Instead, I find that a variety of predictive models --- from those trained on spatial data to those trained on spatial statistics extracted from spatial data --- can classify the interaction with up to 80% accuracy. Overall, this work suggests that different game-theoretic interactions produce quantifiably different temporal and spatial patterns that could inform cancer treatment.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (130 p.) : ill."],"dc:identifier":["etd:53271","local:Leither_grad.msu_0128D_22319","https://doi.org/doi:10.25335/2vr5-k711"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["Attribution 4.0 International"],"dc:subject":["Biology","Computer science","Oncology"],"dc:title":["Classifying the game-theoretic interaction between drug-sensitive and drug-resistant cancer cells"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:59:44Z"}