{"id":"https://openalex.org/W7166105545","doi":"https://doi.org/10.5281/zenodo.20900988","title":"Identifying motif combinations with extreme expression","display_name":"Identifying motif combinations with extreme expression","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166105545","doi":"https://doi.org/10.5281/zenodo.20900988"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.20900988","doi":"https://doi.org/10.5281/zenodo.20900988","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20900988","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"volume":null,"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.20900988","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101692889","display_name":"Chaolin Zhang","orcid":"https://orcid.org/0000-0002-8310-7537","observed_orcids":["https://orcid.org/0000-0002-8310-7537"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Chaolin","raw_affiliation_strings":["Columbia University"],"raw_orcid":"https://orcid.org/0000-0002-8310-7537","affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065777782","display_name":"Shane Chu","orcid":"https://orcid.org/0000-0002-8723-3215","observed_orcids":["https://orcid.org/0000-0002-8723-3215"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chu, Shane","raw_affiliation_strings":["Columbia University"],"raw_orcid":"https://orcid.org/0000-0002-8723-3215","affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37990945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9458000063896179,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9458000063896179,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.00989999994635582,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.009200000204145908,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/promoter-expression","display_name":"promoter expression","score":0.5839999914169312},{"id":"https://openalex.org/keywords/motif-combinations","display_name":"motif combinations","score":0.5740000009536743},{"id":"https://openalex.org/keywords/escherichia-coli","display_name":"Escherichia coli","score":0.8820000290870667},{"id":"https://openalex.org/keywords/protoplasts","display_name":"protoplasts","score":0.6890000104904175},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.4779999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6654000282287598},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.65420001745224},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.6161999702453613},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.44940000772476196},{"id":"https://openalex.org/C2776841711","wikidata":"https://www.wikidata.org/wiki/Q856","display_name":"Barcode","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3682999908924103},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2946000099182129},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2825999855995178},{"id":"https://openalex.org/C2779927696","wikidata":"https://www.wikidata.org/wiki/Q6865654","display_name":"Minion","level":5,"score":0.2687000036239624},{"id":"https://openalex.org/C14103023","wikidata":"https://www.wikidata.org/wiki/Q11681459","display_name":"Pairing","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.20900988","doi":"https://doi.org/10.5281/zenodo.20900988","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20900988","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.20900989","doi":"https://doi.org/10.5281/zenodo.20900989","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20900989","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.20900988","doi":"https://doi.org/10.5281/zenodo.20900988","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20900988","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2135579484","https://openalex.org/W7095363974","https://openalex.org/W7098368682","https://openalex.org/W2096164879","https://openalex.org/W2096139934","https://openalex.org/W3200792395","https://openalex.org/W2901786064","https://openalex.org/W2100648873","https://openalex.org/W2522159763","https://openalex.org/W2145333821"],"abstract_inverted_index":{"ATLAS_data:":[0],"Sequence-to-expression":[1],"datasets":[2,132],"and":[3,44,74,133,145,169,194,199],"reproduction":[4],"code":[5,46],"for":[6],"motif":[7,146],"inference":[8],"This":[9],"repository":[10,64],"accompanies":[11],"the":[12,31,41,45,49,82,113,124,131,135,210],"manuscript's":[13],"sequence-to-expression":[14],"analyses.":[15],"It":[16],"provides":[17],"a":[18,37,86,186],"fully":[19],"traceable":[20],"data":[21],"pipeline":[22,54],"\u2014":[23,57,90,112,128],"from":[24],"each":[25,101],"dataset's":[26],"original":[27,83],"public":[28],"source,":[29],"through":[30],"scripts":[32,79,92],"that":[33,47,80,93],"convert":[34,81],"it":[35],"to":[36,40,182,208],"uniform":[38,98],"format,":[39],"analysis-ready":[42,115],"inputs":[43],"reproduces":[48,134],"reported":[50],"results.":[51,211],"Contents":[52],"(four":[53],"stages):":[55],"seq_exp_csv_sources/":[56],"provenance":[58],"of":[59,190],"every":[60,191],"raw":[61],"download:":[62],"upstream":[63],"or":[65],"GEO":[66],"accession,":[67],"exact":[68],"files":[69],"used,":[70],"filtering":[71],"applied,":[72],"citations,":[73],"(where":[75],"needed)":[76],"small":[77],"extraction":[78],"release":[84],"into":[85,97],"parseable":[87],"CSV.":[88],"from_csv_to_jld2/":[89],"Julia":[91,197],"parse":[94],"those":[95],"CSVs":[96],".jld2":[99],"files,":[100],"holding":[102],"one":[103,117],"SEQ2EXP_Dataset":[104],"pairing":[105],"sequences":[106],"with":[107,185,196],"their":[108],"expression/activity":[109],"labels.":[110],"_data_jld2s/":[111],"resulting":[114],"datasets,":[116],"folder":[118],"per":[119],"dataset,":[120],"referenced":[121],"directly":[122],"by":[123],"analysis":[125],"code.":[126],"get_results/":[127],"get_results.jl":[129],"reads":[130],"experimental":[136],"results":[137,179],"(per-dataset":[138],"model":[139],"metrics,":[140],"inferred":[141],"motifs,":[142],"trained":[143],"checkpoints,":[144],"visualizations).":[147],"Datasets":[148],"(eight,":[149],"four":[150],"readout":[151],"types):":[152],"promoter":[153],"expression":[154],"(yeast":[155],"GPRA,":[156],"E.":[157],"coli":[158],"cross-species,":[159],"plant":[160],"leaf/protoplast),":[161],"alternative":[162],"5\u2032":[163,170],"splice-site":[164],"usage":[165],"(Rosenberg":[166],"A5SS,":[167],"SPLIRENT),":[168],"UTR":[171],"translation":[172],"efficiency":[173],"(human":[174],"GSE114002,":[175],"yeast":[176],"GSE104252).":[177],"Reproducibility:":[178],"are":[180],"pinned":[181],"MotifInference":[183],"v0.0.6,":[184],"full":[187],"Manifest.toml":[188],"lock":[189],"dependency.":[192],"Built":[193],"run":[195],"1.12.2":[198],"CUDA.jl":[200],"v5.9.7.":[201],"An":[202],"NVIDIA":[203],"CUDA-capable":[204],"GPU":[205],"is":[206],"required":[207],"reproduce":[209]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-06-27T00:00:00"}