{"doi":"10.1101/2023.10.05.561066","title":"CELL-E 2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer","abstract":"Abstract We present CELL-E 2, a novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (and vice versa ). Protein localization is a challenging problem that requires integrating sequence and image information, which most existing methods ignore. CELL-E 2 extends the work of CELL-E, not only capturing the spatial complexity of protein localization and produce probability estimates of localization atop a nucleus image, but also being able to generate sequences from images, enabling de novo protein design. We train and finetune CELL-E 2 on two large-scale datasets of human proteins. We also demonstrate how to use CELL-E 2 to create hundreds of novel nuclear localization signals (NLS). Results and interactive demos are featured at https://bohuanglab.github.io/CELL-E_2/ .","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2023,"id":395199,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":3,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9566,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":4942,"name":"Yun S. Song","orcid":"0000-0002-0734-9868","position":1,"is_corresponding":false},{"id":626758,"name":"Aaron Agarunov","orcid":null,"position":2,"is_corresponding":false},{"id":406504,"name":"Bo Huang","orcid":"0000-0003-1704-4141","position":3,"is_corresponding":false},{"id":676001,"name":"Emaad Khwaja","orcid":null,"position":0,"is_corresponding":true}],"reference_count":65,"raw_metadata":null,"created_at":"2026-07-19T01:19:18.686170Z","pmid":"39021511","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}