{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/157173"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/157173","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Understanding tumor cell plasticity in spatial transcriptomics with graph attention networks and walk-based pseudotime analysis","abstract":"Tumor cell plasticity in cancer is a key driver in tumor progression, heterogeneity, metastasis, and treatment resistance. Tumor cells change states from the conventionally easier to treat epithelial state to the more resistant mesenchymal state. Understanding the transition dynamics of these states and the extrinsic factors influencing them is crucial for improving therapeutic strategies and patient outcomes. Utilizing spatial transcriptomics extrinsic driving factors of plasticity can be probed. We introduce PlastiNet, which uses a graphical attention-based network to create a spatial aware embedding. The utility of our approach is validated in model systems, specifically in the brain and colon, where it successfully identifies biologically relevant neighborhoods and maps differentiation pathways. When applied to pancreatic ductal adenocarcinoma (PDAC), distinct, conserved neighborhoods within the tissue, including diverse immune and cancer clusters. By estimating a differentiation path from epithelial to mesenchymal-like cells, we can identify intermediate states despite a limited set of tumor marker genes. This cellular differentiation path shows enrichment and depletion of certain cell types within local neighborhoods aligning with known correlations, and by leveraging inferred ligand-receptor interactions, we can pinpoint potential drivers of plasticity to test in vitro. PlastiNet effectively generates hypotheses directly from patient-derived spatial transcriptomics samples, offering insights into the cellular mechanisms driving tumor plasticity.","abstract_html":"Tumor cell plasticity in cancer is a key driver in tumor progression, heterogeneity, metastasis, and treatment resistance. Tumor cells change states from the conventionally easier to treat epithelial state to the more resistant mesenchymal state. Understanding the transition dynamics of these states and the extrinsic factors influencing them is crucial for improving therapeutic strategies and patient outcomes. Utilizing spatial transcriptomics extrinsic driving factors of plasticity can be probed. We introduce PlastiNet, which uses a graphical attention-based network to create a spatial aware embedding. The utility of our approach is validated in model systems, specifically in the brain and colon, where it successfully identifies biologically relevant neighborhoods and maps differentiation pathways. When applied to pancreatic ductal adenocarcinoma (PDAC), distinct, conserved neighborhoods within the tissue, including diverse immune and cancer clusters. By estimating a differentiation path from epithelial to mesenchymal-like cells, we can identify intermediate states despite a limited set of tumor marker genes. This cellular differentiation path shows enrichment and depletion of certain cell types within local neighborhoods aligning with known correlations, and by leveraging inferred ligand-receptor interactions, we can pinpoint potential drivers of plasticity to test in vitro. PlastiNet effectively generates hypotheses directly from patient-derived spatial transcriptomics samples, offering insights into the cellular mechanisms driving tumor plasticity.","abstract_has_math":false,"creators":["Zamora, Izabella"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Hacohen, Nir","Uhler, Caroline"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:21:12Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/157173","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Hacohen, Nir","Uhler, Caroline"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Zamora, Izabella"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-10-09T18:26:09Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-10-09T18:26:09Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/157173"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Tumor cell plasticity in cancer is a key driver in tumor progression, heterogeneity, metastasis, and treatment resistance. Tumor cells change states from the conventionally easier to treat epithelial state to the more resistant mesenchymal state. Understanding the transition dynamics of these states and the extrinsic factors influencing them is crucial for improving therapeutic strategies and patient outcomes. Utilizing spatial transcriptomics extrinsic driving factors of plasticity can be probed. We introduce PlastiNet, which uses a graphical attention-based network to create a spatial aware embedding. The utility of our approach is validated in model systems, specifically in the brain and colon, where it successfully identifies biologically relevant neighborhoods and maps differentiation pathways. When applied to pancreatic ductal adenocarcinoma (PDAC), distinct, conserved neighborhoods within the tissue, including diverse immune and cancer clusters. By estimating a differentiation path from epithelial to mesenchymal-like cells, we can identify intermediate states despite a limited set of tumor marker genes. This cellular differentiation path shows enrichment and depletion of certain cell types within local neighborhoods aligning with known correlations, and by leveraging inferred ligand-receptor interactions, we can pinpoint potential drivers of plasticity to test in vitro. PlastiNet effectively generates hypotheses directly from patient-derived spatial transcriptomics samples, offering insights into the cellular mechanisms driving tumor plasticity."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Understanding tumor cell plasticity in spatial transcriptomics with graph attention networks and walk-based pseudotime analysis"]}]}],"canonical_facts":{"dc:contributor.advisor":["Hacohen, Nir","Uhler, Caroline"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Zamora, Izabella"],"dc:date.accessioned":["2024-10-09T18:26:09Z"],"dc:date.available":["2024-10-09T18:26:09Z"],"dc:date.issued":["2024-05"],"dc:description.abstract":["Tumor cell plasticity in cancer is a key driver in tumor progression, heterogeneity, metastasis, and treatment resistance. Tumor cells change states from the conventionally easier to treat epithelial state to the more resistant mesenchymal state. Understanding the transition dynamics of these states and the extrinsic factors influencing them is crucial for improving therapeutic strategies and patient outcomes. Utilizing spatial transcriptomics extrinsic driving factors of plasticity can be probed. We introduce PlastiNet, which uses a graphical attention-based network to create a spatial aware embedding. The utility of our approach is validated in model systems, specifically in the brain and colon, where it successfully identifies biologically relevant neighborhoods and maps differentiation pathways. When applied to pancreatic ductal adenocarcinoma (PDAC), distinct, conserved neighborhoods within the tissue, including diverse immune and cancer clusters. By estimating a differentiation path from epithelial to mesenchymal-like cells, we can identify intermediate states despite a limited set of tumor marker genes. This cellular differentiation path shows enrichment and depletion of certain cell types within local neighborhoods aligning with known correlations, and by leveraging inferred ligand-receptor interactions, we can pinpoint potential drivers of plasticity to test in vitro. PlastiNet effectively generates hypotheses directly from patient-derived spatial transcriptomics samples, offering insights into the cellular mechanisms driving tumor plasticity."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/157173"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Understanding tumor cell plasticity in spatial transcriptomics with graph attention networks and walk-based pseudotime analysis"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:12Z"}