{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/156959"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/156959","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Towards a Prime Factorization of Proteins","abstract":"A classical problem of machine learning is the interpretability of a model’s latent information processing. This is particularly the case in the richly complex field of protein analysis, whereby unique and novel insights into the structural organization of proteins can help illuminate their functional space, and in particular lead toward a factorization of the structural space into a set of motif building blocks, which completely span this universe. This thesis creates a new inference interface for performing such analysis, by leveraging the sequential learning process of a neural autoencoder to construct a decomposition of proteins as a hierarchical sequence of embedded representation vectors. The further development of this work could lead to a greater understanding of the organizational complexity of natural phenomena, and in particular, as it relates to the uniquely complex relationship between protein structures and their function.","abstract_html":"A classical problem of machine learning is the interpretability of a model’s latent information processing. This is particularly the case in the richly complex field of protein analysis, whereby unique and novel insights into the structural organization of proteins can help illuminate their functional space, and in particular lead toward a factorization of the structural space into a set of motif building blocks, which completely span this universe. This thesis creates a new inference interface for performing such analysis, by leveraging the sequential learning process of a neural autoencoder to construct a decomposition of proteins as a hierarchical sequence of embedded representation vectors. The further development of this work could lead to a greater understanding of the organizational complexity of natural phenomena, and in particular, as it relates to the uniquely complex relationship between protein structures and their function.","abstract_has_math":false,"creators":["Radev, Simeon"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Program in Media Arts and Sciences (Massachusetts Institute of Technology)","school":null,"contributors":[],"advisors":["Jacobson, Joseph"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:22:07Z","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/1721.1/156959","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Jacobson, Joseph"]},{"key":"dc:contributor.department","label":"Department","values":["Program in Media Arts and Sciences (Massachusetts Institute of Technology)"]},{"key":"dc:creator","label":"Author","values":["Radev, Simeon"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-09-24T18:23:01Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-09-24T18:23:01Z"]},{"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 Science in Media Arts and Sciences"]}]},{"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/1721.1/156959"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["A classical problem of machine learning is the interpretability of a model’s latent information processing. This is particularly the case in the richly complex field of protein analysis, whereby unique and novel insights into the structural organization of proteins can help illuminate their functional space, and in particular lead toward a factorization of the structural space into a set of motif building blocks, which completely span this universe. This thesis creates a new inference interface for performing such analysis, by leveraging the sequential learning process of a neural autoencoder to construct a decomposition of proteins as a hierarchical sequence of embedded representation vectors. The further development of this work could lead to a greater understanding of the organizational complexity of natural phenomena, and in particular, as it relates to the uniquely complex relationship between protein structures and their function."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Towards a Prime Factorization of Proteins"]}]}],"canonical_facts":{"dc:contributor.advisor":["Jacobson, Joseph"],"dc:contributor.department":["Program in Media Arts and Sciences (Massachusetts Institute of Technology)"],"dc:creator":["Radev, Simeon"],"dc:date.accessioned":["2024-09-24T18:23:01Z"],"dc:date.available":["2024-09-24T18:23:01Z"],"dc:date.issued":["2024-05"],"dc:description.abstract":["A classical problem of machine learning is the interpretability of a model’s latent information processing. This is particularly the case in the richly complex field of protein analysis, whereby unique and novel insights into the structural organization of proteins can help illuminate their functional space, and in particular lead toward a factorization of the structural space into a set of motif building blocks, which completely span this universe. This thesis creates a new inference interface for performing such analysis, by leveraging the sequential learning process of a neural autoencoder to construct a decomposition of proteins as a hierarchical sequence of embedded representation vectors. The further development of this work could lead to a greater understanding of the organizational complexity of natural phenomena, and in particular, as it relates to the uniquely complex relationship between protein structures and their function."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/156959"],"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":["Towards a Prime Factorization of Proteins"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Media Arts and Sciences"]},"updated_at":"2026-07-22T22:22:07Z"}