{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:39:25Z","timestamp":1743086365829,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9781071639887"},{"type":"electronic","value":"9781071639894"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-1-0716-3989-4_12","type":"book-chapter","created":{"date-parts":[[2024,5,16]],"date-time":"2024-05-16T08:02:38Z","timestamp":1715846558000},"page":"185-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CELL-E: A Text-to-Image Transformer for\u00a0Protein Image Prediction"],"prefix":"10.1007","author":[{"given":"Emaad","family":"Khwaja","sequence":"first","affiliation":[]},{"given":"Yun S.","family":"Song","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1704-4141","authenticated-orcid":false,"given":"Bo","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,5,17]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","unstructured":"Almagro\u00a0Armenteros, J.J., S\u00f8nderby, C.K., S\u00f8nderby, S.K., Nielsen, H., Winther, O.: DeepLoc: prediction of protein subcellular localization using deep learning. Bioinformatics 33(21), 3387\u20133395 (Nov 2017). https:\/\/doi.org\/10.1093\/bioinformatics\/btx431, https:\/\/doi.org\/10.1093\/bioinformatics\/btx431","DOI":"10.1093\/bioinformatics\/btx431"},{"issue":"18","key":"12_CR2","doi-asserted-by":"publisher","first-page":"12408","DOI":"10.1016\/S0021-9258(18)42288-0","volume":"267","author":"J Alsner","year":"1992","unstructured":"Alsner, J., Svejstrup, J.Q., Kjeldsen, E., S\u00f8rensen, B.S., Westergaard, O.: Identification of an N-terminal domain of eukaryotic DNA topoisomerase I dispensable for catalytic activity but essential for in vivo function. J. Biol. Chem. 267(18), 12408\u201312411 (1992)","journal-title":"J. Biol. Chem."},{"key":"12_CR3","doi-asserted-by":"publisher","unstructured":"Bepler, T., Berger, B.: Learning the protein language: Evolution, structure, and function. Cell Systems 12(6), 654\u2013669.e3 (Jun 2021). https:\/\/doi.org\/10.1016\/j.cels.2021.05.017, https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2405471221002039","DOI":"10.1016\/j.cels.2021.05.017"},{"key":"12_CR4","doi-asserted-by":"publisher","unstructured":"Chacinska, A., Koehler, C.M., Milenkovic, D., Lithgow, T., Pfanner, N.: Importing Mitochondrial Proteins: Machineries and Mechanisms. Cell 138(4), 628\u2013644 (Aug 2009). https:\/\/doi.org\/10.1016\/j.cell.2009.08.005, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0092867409009672","DOI":"10.1016\/j.cell.2009.08.005"},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Cho, N.H., Cheveralls, K.C., Brunner, A.D., Kim, K., Michaelis, A.C., Raghavan, P., Kobayashi, H., Savy, L., Li, J.Y., Canaj, H., Kim, J.Y.S., Stewart, E.M., Gnann, C., McCarthy, F., Cabrera, J.P., Brunetti, R.M., Chhun, B.B., Dingle, G., Hein, M.Y., Huang, B., Mehta, S.B., Weissman, J.S., G\u00f3mez-Sj\u00f6berg, R., Itzhak, D.N., Royer, L.A., Mann, M., Leonetti, M.D.: OpenCell: Endogenous tagging for the cartography of human cellular organization. Science (New York, N.Y.) 375(6585), eabi6983 (Mar 2022). https:\/\/doi.org\/10.1126\/science.abi6983, place: United States","DOI":"10.1126\/science.abi6983"},{"key":"12_CR6","unstructured":"Ding, M., Yang, Z., Hong, W., Zheng, W., Zhou, C., Yin, D., Lin, J., Zou, X., Shao, Z., Yang, H., Tang, J.: CogView: Mastering Text-to-Image Generation via Transformers. arXiv:2105.13290 [cs] (Nov 2021), http:\/\/arxiv.org\/abs\/2105.13290, arXiv: 2105.13290"},{"key":"12_CR7","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1083\/jcb.107.3.841","volume":"107","author":"C Dingwall","year":"1988","unstructured":"Dingwall, C., Robbins, J., Dilworth, S.M., Roberts, B., Richardson, W.D.: The Nucleoplasmin Nuclear Location Sequence Is Larger and MoreComplex than That of SV-40 Large T Antigen. J. Cell Biol. 107, 9 (1988)","journal-title":"J. Cell Biol."},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming Transformers for High-Resolution Image Synthesis. arXiv:2012.09841 [cs] (Jun 2021), http:\/\/arxiv.org\/abs\/2012.09841, arXiv: 2012.09841","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"12_CR9","doi-asserted-by":"publisher","unstructured":"Gardy, J.L., Brinkman, F.S.L.: Methods for predicting bacterial protein subcellular localization. Nature Reviews Microbiology 4(10), 741\u2013751 (Oct 2006). https:\/\/doi.org\/10.1038\/nrmicro1494, https:\/\/www.nature.com\/articles\/nrmicro1494, bandiera_abtest: a Cg_type: Nature Research Journals Number: 10 Primary_atype: Reviews Publisher: Nature Publishing Group","DOI":"10.1038\/nrmicro1494"},{"key":"12_CR10","doi-asserted-by":"publisher","unstructured":"Hu, T., Chitnis, N., Monos, D., Dinh, A.: Next-generation sequencing technologies: An overview. Human Immunology 82(11), 801\u2013811 (Nov 2021). https:\/\/doi.org\/10.1016\/j.humimm.2021.02.012, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0198885921000628","DOI":"10.1016\/j.humimm.2021.02.012"},{"key":"12_CR11","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical Reparameterization with Gumbel-Softmax. arXiv:1611.01144 [cs, stat] (Aug 2017), http:\/\/arxiv.org\/abs\/1611.01144, arXiv: 1611.01144"},{"key":"12_CR12","doi-asserted-by":"publisher","unstructured":"Jiang, Y., Wang, D., Wang, W., Xu, D.: Computational methods for protein localization prediction. Computational and Structural Biotechnology Journal 19, 5834\u20135844 (Jan 2021). https:\/\/doi.org\/10.1016\/j.csbj.2021.10.023, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2001037021004451","DOI":"10.1016\/j.csbj.2021.10.023"},{"key":"12_CR13","unstructured":"Kingma, D.P., Welling, M.: Auto-Encoding Variational Bayes. arXiv:1312.6114 [cs, stat] (May 2014), http:\/\/arxiv.org\/abs\/1312.6114, arXiv: 1312.6114"},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Kobayashi, H., Cheveralls, K.C., Leonetti, M.D., Royer, L.A.: Self-Supervised Deep Learning Encodes High-Resolution Features of Protein Subcellular Localization. preprint, Cell Biology (Mar 2021). https:\/\/doi.org\/10.1101\/2021.03.29.437595, http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2021.03.29.437595","DOI":"10.1101\/2021.03.29.437595"},{"key":"12_CR15","unstructured":"Liu, P.J., Saleh*, M., Pot, E., Goodrich, B., Sepassi, R., Kaiser, L., Shazeer, N.: Generating Wikipedia by Summarizing Long Sequences (Apr 2023), https:\/\/openreview.net\/forum?id=Hyg0vbWC-"},{"key":"12_CR16","doi-asserted-by":"publisher","unstructured":"Lu, J., Wu, T., Zhang, B., Liu, S., Song, W., Qiao, J., Ruan, H.: Types of nuclear localization signals and mechanisms of protein import into the nucleus. Cell Communication and Signaling 19(1), \u00a060 (May 2021). https:\/\/doi.org\/10.1186\/s12964-021-00741-y, https:\/\/doi.org\/10.1186\/s12964-021-00741-y","DOI":"10.1186\/s12964-021-00741-y"},{"key":"12_CR17","doi-asserted-by":"publisher","unstructured":"Mo, Y.Y., Wang, C., Beck, W.T.: A Novel Nuclear Localization Signal in Human DNA Topoisomerase I*. Journal of Biological Chemistry 275(52), 41107\u201341113 (Dec 2000). https:\/\/doi.org\/10.1074\/jbc.M003135200, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0021925819556435","DOI":"10.1074\/jbc.M003135200"},{"key":"12_CR18","doi-asserted-by":"publisher","unstructured":"Palma, C.A., Cecchini, M., Samor\u00ec, P.: Predicting self-assembly: from empirism to determinism. Chemical Society Reviews 41(10), 3713\u20133730 (Apr 2012). https:\/\/doi.org\/10.1039\/C2CS15302E, https:\/\/pubs.rsc.org\/en\/content\/articlelanding\/2012\/cs\/c2cs15302e, publisher: The Royal Society of Chemistry","DOI":"10.1039\/C2CS15302E"},{"key":"12_CR19","doi-asserted-by":"publisher","unstructured":"Popel, M., Bojar, O.: Training Tips for the Transformer Model. The Prague Bulletin of Mathematical Linguistics 110(1), 43\u201370 (Apr 2018). https:\/\/doi.org\/10.2478\/pralin-2018-0002, http:\/\/content.sciendo.com\/view\/journals\/pralin\/110\/1\/article-p43.xml","DOI":"10.2478\/pralin-2018-0002"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical Text-Conditional Image Generation with CLIP Latents (Apr 2022). https:\/\/doi.org\/10.48550\/arXiv.2204.06125, http:\/\/arxiv.org\/abs\/2204.06125, arXiv:2204.06125 [cs]","DOI":"10.48550\/arXiv.2204.06125"},{"key":"12_CR21","unstructured":"Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., Sutskever, I.: Zero-Shot Text-to-Image Generation. arXiv:2102.12092 [cs] (Feb 2021), http:\/\/arxiv.org\/abs\/2102.12092, arXiv: 2102.12092"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Rao, R., Bhattacharya, N., Thomas, N., Duan, Y., Chen, X., Canny, J., Abbeel, P., Song, Y.S.: Evaluating Protein Transfer Learning with TAPE. arXiv:1906.08230 [cs, q-bio, stat] (Jun 2019), http:\/\/arxiv.org\/abs\/1906.08230, arXiv: 1906.08230","DOI":"10.1101\/676825"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Ray, M., Tang, R., Jiang, Z., Rotello, V.M.: Quantitative Tracking of Protein Trafficking to the Nucleus Using Cytosolic Protein Delivery by Nanoparticle-Stabilized Nanocapsules. Bioconjugate Chemistry 26(6), 1004\u20131007 (Jun 2015). https:\/\/doi.org\/10.1021\/acs.bioconjchem.5b00141, https:\/\/doi.org\/10.1021\/acs.bioconjchem.5b00141, publisher: American Chemical Society","DOI":"10.1021\/acs.bioconjchem.5b00141"},{"key":"12_CR24","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic Backpropagation and Approximate Inference in Deep Generative Models. In: Proceedings of the 31st International Conference on Machine Learning. pp. 1278\u20131286. PMLR (Jun 2014), https:\/\/proceedings.mlr.press\/v32\/rezende14.html, iSSN: 1938-7228"},{"key":"12_CR25","doi-asserted-by":"publisher","unstructured":"Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C.L., Ma, J., Fergus, R.: Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proceedings of the National Academy of Sciences 118(15), e2016239118 (2021). https:\/\/doi.org\/10.1073\/pnas.2016239118, https:\/\/www.pnas.org\/doi\/abs\/10.1073\/pnas.2016239118, _eprint: https:\/\/www.pnas.org\/doi\/pdf\/10.1073\/pnas.2016239118","DOI":"10.1073\/pnas.2016239118"},{"key":"12_CR26","doi-asserted-by":"publisher","unstructured":"Salvatore, M., Warholm, P., Shu, N., Basile, W., Elofsson, A.: SubCons: a new ensemble method for improved human subcellular localization predictions. Bioinformatics 33(16), 2464\u20132470 (Aug 2017). https:\/\/doi.org\/10.1093\/bioinformatics\/btx219, https:\/\/doi.org\/10.1093\/bioinformatics\/btx219","DOI":"10.1093\/bioinformatics\/btx219"},{"key":"12_CR27","doi-asserted-by":"publisher","unstructured":"The UniProt Consortium: UniProt: the universal protein knowledgebase. Nucleic acids research 45(D1), D158\u2013D169 (Jan 2017). https:\/\/doi.org\/10.1093\/nar\/gkw1099, place: England","DOI":"10.1093\/nar\/gkw1099"},{"issue":"1","key":"12_CR28","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1002\/pro.3307","volume":"27","author":"PJ Thul","year":"2018","unstructured":"Thul, P.J., Lindskog, C.: The human protein atlas: A spatial map of the human proteome. Protein Science: A Publication of the Protein Society 27(1), 233\u2013244 (2018). https:\/\/doi.org\/10.1002\/pro.3307","journal-title":"Protein Science: A Publication of the Protein Society"},{"key":"12_CR29","doi-asserted-by":"publisher","unstructured":"Tiessen, A., P\u00e9rez-Rodr\u00edguez, P., Delaye-Arredondo, L.J.: Mathematical modeling and comparison of protein size distribution in different plant, animal, fungal and microbial species reveals a negative correlation between protein size and protein number, thus providing insight into the evolution of proteomes. BMC Research Notes 5(1), 1\u201323 (Dec 2012). https:\/\/doi.org\/10.1186\/1756-0500-5-85, https:\/\/bmcresnotes.biomedcentral.com\/articles\/10.1186\/1756-0500-5-85, number: 1 Publisher: BioMed Central","DOI":"10.1186\/1756-0500-5-85"},{"key":"12_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, u., Polosukhin, I.: Attention is All you Need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol.\u00a030. Curran Associates, Inc. (2017), https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"12_CR31","unstructured":"Wang, P.: DALL-E in Pytorch (Apr 2022), https:\/\/github.com\/lucidrains\/DALLE-pytorch, original-date: 2021-01-05T20:35:16Z"}],"container-title":["Lecture Notes in Computer Science","Research in Computational Molecular Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-0716-3989-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,16]],"date-time":"2024-05-16T08:04:14Z","timestamp":1715846654000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-0716-3989-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9781071639887","9781071639894"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-1-0716-3989-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 May 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Our model is a heavily modified version of an open source text-to-image transformer [], available via the MIT license (Copyright (c) 2021 Phil Wang). Our code and more detailed descriptions of the training process are available at  via the MIT license (Copyright (c) 2022 Emaad Khwaja, Yun Song,  Bo Huang).","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"E.K. played a key role in the advancement of the approach, carrying out the majority of the coding, designing and conducting a significant number of the experiments, and producing an initial version of the manuscript. The remaining authors also offered consistent input on all aspects of the project, assessed the code, and helped with the final draft of the manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Author information"}},{"value":"RECOMB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Research in Computational Molecular Biology","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambridge, MA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"recomb2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/recomb.org\/recomb2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}