{"id":"https://openalex.org/W7064853550","doi":null,"title":"Designing Novel DNA-Binding Proteins with Generative Deep Learning","display_name":"Designing Novel DNA-Binding Proteins with Generative Deep Learning","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W7064853550"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/152003","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0009-0007-4177-4415","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/152003/1/calman-calman-SM-MAS-2023-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dspace.mit.edu/bitstream/1721.1/152003/1/calman-calman-SM-MAS-2023-thesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071831273","display_name":"Ido Calman","orcid":"https://orcid.org/0009-0007-4177-4415","observed_orcids":["https://orcid.org/0009-0007-4177-4415"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Calman, Ido","raw_affiliation_strings":["Sciences Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sciences Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071831273"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9419000148773193,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9419000148773193,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.027799999341368675,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.013100000098347664,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dna-binding-proteins","display_name":"DNA-binding proteins","score":0.7279999852180481},{"id":"https://openalex.org/keywords/protein-design","display_name":"protein design","score":0.8349999785423279},{"id":"https://openalex.org/keywords/protein-dna-interactions","display_name":"protein-DNA interactions","score":0.8169999718666077},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.7549999952316284},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.9089999794960022},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.4320000112056732},{"id":"https://openalex.org/keywords/synthetic-biology","display_name":"synthetic biology","score":0.7699999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6151000261306763},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.555899977684021},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5541999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5504000186920166},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C191908910","wikidata":"https://www.wikidata.org/wiki/Q862838","display_name":"Synthetic biology","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.3425999879837036},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3174999952316284},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C147816474","wikidata":"https://www.wikidata.org/wiki/Q169525","display_name":"Protein engineering","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C38764148","wikidata":"https://www.wikidata.org/wiki/Q17098245","display_name":"Interaction information","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/152003","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0009-0007-4177-4415","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/152003/1/calman-calman-SM-MAS-2023-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/152003","doi":null,"is_oa":true,"landing_page_url":"https://orcid.org/0009-0007-4177-4415","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/152003/1/calman-calman-SM-MAS-2023-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7064853550.pdf","grobid_xml":"https://content.openalex.org/works/W7064853550.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1824346003","https://openalex.org/W2129069237","https://openalex.org/W2519887557","https://openalex.org/W2552391307","https://openalex.org/W2606780347","https://openalex.org/W2607264901","https://openalex.org/W2626778328","https://openalex.org/W2766453196","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2975166957","https://openalex.org/W2981852735","https://openalex.org/W3030163527","https://openalex.org/W3036167779","https://openalex.org/W3131204112","https://openalex.org/W3164401570","https://openalex.org/W3178087467","https://openalex.org/W4281781228","https://openalex.org/W4298289240","https://openalex.org/W4302307901","https://openalex.org/W4319452608"],"related_works":["https://openalex.org/W7157126132","https://openalex.org/W7014909185","https://openalex.org/W4410494741","https://openalex.org/W7140029136","https://openalex.org/W7112436565","https://openalex.org/W4401142912","https://openalex.org/W6958211198","https://openalex.org/W4391741137","https://openalex.org/W4408092511","https://openalex.org/W6940933178"],"abstract_inverted_index":{"Protein-DNA":[0],"interactions":[1],"play":[2],"a":[3,26,39,116,121],"critical":[4],"role":[5],"in":[6,81,150],"various":[7],"biological":[8],"processes,":[9],"such":[10,152],"as":[11,111,153],"gene":[12,156],"regulation":[13],"and":[14,66,119,141,158],"genome":[15],"maintenance.":[16],"Designing":[17],"protein":[18,45,63,83,105,128],"backbones":[19,46],"specifically":[20],"tailored":[21],"for":[22,42,50,61,69,86,138],"DNA":[23,51,95,109,144],"binding":[24,145],"remains":[25],"challenging":[27],"task,":[28],"requiring":[29],"the":[30,75,82,87,101,139],"exploration":[31],"of":[32,90,104,143],"novel":[33,40],"computational":[34],"approaches.":[35],"This":[36],"thesis":[37,114],"presents":[38],"framework":[41],"gen-":[43],"erating":[44],"that":[47],"exhibit":[48],"affinity":[49],"molecules.":[52],"The":[53,72,97,113,130],"proposed":[54],"methodology":[55],"leverages":[56],"Graph":[57],"Neural":[58],"Networks":[59],"(GNNs)":[60],"encoding":[62,89],"struc-":[64],"tures":[65],"diffusion":[67,98],"models":[68,99],"conditional":[70,102],"sampling.":[71],"GNNs":[73],"capture":[74],"intricate":[76],"relationships":[77],"between":[78],"amino":[79],"acids":[80],"backbone,":[84],"allowing":[85],"effective":[88],"structural":[91],"information":[92],"relevant":[93],"to":[94,124],"binding.":[96],"enable":[100],"generation":[103],"backbones,":[106],"given":[107],"specific":[108],"sequences":[110],"input.":[112],"proposes":[115],"Transformer":[117],"architecture":[118],"provides":[120],"practical":[122],"way":[123],"diffuse":[125],"from":[126,132],"its":[127],"encoding.":[129],"findings":[131],"this":[133],"research":[134],"have":[135],"significant":[136],"implications":[137],"design":[140],"engineering":[142],"proteins,":[146],"facilitating":[147],"ad-":[148],"vancements":[149],"fields":[151],"synthetic":[154],"biology,":[155],"therapy,":[157],"drug":[159],"development.":[160]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}