{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/147430"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/147430","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"A Transformer for scATAC-scRNA Translation","abstract":"scATAC-seq gives a comprehensive picture of the chromatin accessibility profile of a cell, covering not only protein-coding regions but also non-coding regulatory regions which are in theory missed by scRNA-seq. However, scATAC-seq data is highdimensional and noisy, aspects which when compounded with data scarcity present challenges for modeling on even seemingly-simple downstream tasks such as cell-type prediction. As such, researchers may benefit from access to a large library of models to evaluate. While we do not demonstrate state of the art results in any capacity, we provide an implementation of a simple representation of sparse tabular data that allows it to be inputted into the popular transformer family of architectures, and use this representation to train a transformer that predicts scRNA-seq given scATAC-seq. Our code is made available here https://github.com/rogershijin/GANOLI.","abstract_html":"scATAC-seq gives a comprehensive picture of the chromatin accessibility profile of a cell, covering not only protein-coding regions but also non-coding regulatory regions which are in theory missed by scRNA-seq. However, scATAC-seq data is highdimensional and noisy, aspects which when compounded with data scarcity present challenges for modeling on even seemingly-simple downstream tasks such as cell-type prediction. As such, researchers may benefit from access to a large library of models to evaluate. While we do not demonstrate state of the art results in any capacity, we provide an implementation of a simple representation of sparse tabular data that allows it to be inputted into the popular transformer family of architectures, and use this representation to train a transformer that predicts scRNA-seq given scATAC-seq. Our code is made available here https://github.com/rogershijin/GANOLI.","abstract_has_math":false,"creators":["Jin, Roger"],"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":["Kellis, Manolis"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-09","date_published":"2022-09","updated_at":"2026-07-22T22:22:09Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/147430","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kellis, Manolis"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Jin, Roger"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-01-19T19:49:51Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-01-19T19:49:51Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-09"]},{"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 MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/147430"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["scATAC-seq gives a comprehensive picture of the chromatin accessibility profile of a cell, covering not only protein-coding regions but also non-coding regulatory regions which are in theory missed by scRNA-seq. However, scATAC-seq data is highdimensional and noisy, aspects which when compounded with data scarcity present challenges for modeling on even seemingly-simple downstream tasks such as cell-type prediction. As such, researchers may benefit from access to a large library of models to evaluate. While we do not demonstrate state of the art results in any capacity, we provide an implementation of a simple representation of sparse tabular data that allows it to be inputted into the popular transformer family of architectures, and use this representation to train a transformer that predicts scRNA-seq given scATAC-seq. Our code is made available here https://github.com/rogershijin/GANOLI."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["A Transformer for scATAC-scRNA Translation"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kellis, Manolis"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Jin, Roger"],"dc:date.accessioned":["2023-01-19T19:49:51Z"],"dc:date.available":["2023-01-19T19:49:51Z"],"dc:date.issued":["2022-09"],"dc:description.abstract":["scATAC-seq gives a comprehensive picture of the chromatin accessibility profile of a cell, covering not only protein-coding regions but also non-coding regulatory regions which are in theory missed by scRNA-seq. However, scATAC-seq data is highdimensional and noisy, aspects which when compounded with data scarcity present challenges for modeling on even seemingly-simple downstream tasks such as cell-type prediction. As such, researchers may benefit from access to a large library of models to evaluate. While we do not demonstrate state of the art results in any capacity, we provide an implementation of a simple representation of sparse tabular data that allows it to be inputted into the popular transformer family of architectures, and use this representation to train a transformer that predicts scRNA-seq given scATAC-seq. Our code is made available here https://github.com/rogershijin/GANOLI."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/147430"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["A Transformer for scATAC-scRNA Translation"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:09Z"}