arrow
返回

ProtNote: a multimodal method for protein-function annotation

delete2025-04-15
delete0
PRE
AI
S
S Char
N
Nathaniel Corley
S
Sarah Alamdari
K
Kevin Yang
A
Ava P. Amini *
DOI:10.1093/bioinformatics/btaf170delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
动机 理解蛋白质序列-功能关系对于推动蛋白质生物学和蛋白质工程的发展至关重要。然而,仅有<1%的已知蛋白质序列具有经过人工验证的功能。尽管深度学习方法已在蛋白质功能预测方面显示出潜力,但当前模型仅限于预测它们所训练的功能。结果 在此,我们介绍了ProtNote,一种利用自由文本的多模态深度学习模型,以实现监督学习和零样本蛋白质功能预测。ProtNote不仅在其训练集的注释上保持了接近当前最佳的性能,还能在零样本测试设置中推广到未见过的和新型功能。通过捕捉精细的序列-功能关系,ProtNote在预测新型基因本体论注释和酶学委员会编号方面表现出优于基线模型的性能,从而解锁了先前模型无法访问的一系列生物学应用场景。我们设想,ProtNote将通过使科学家能够使用不受预定义标签限制的自由文本输入,来增强蛋白质功能发现——这是应对蛋白质生物学动态发展的必要能力。可用性与实现 代码可在GitHub上获取:https://github.com/microsoft/protnote;模型权重、数据集和评估指标通过Zenodo提供:https://zenodo.org/records/13897920。
Keyword:
MODELS

期刊

Bioinformatics 封面图
Bioinformatics
IF:
5.4
论文数:
1.4K
被引数:
17.9W

机构

M
microsoft
学者数:
29
论文数: 8
被引数: 0
引用论文

引用论文

The ENZYME database in 2000
err2000-01-01
err1.0K
errOAAI
errBairoch, A
err分享
err收藏
Gene Ontology: tool for the unification of biology基因本体论: 统一生物学的工具
err2000-05-01
err3.4W
errOAAI
errAshburner, M; Ball, CA; Blake, JA; Botstein, D; Butler, H; Cherry, JM; Davis, AP; Dolinski, K; Dwight, SS; Eppig, JT; Harris, MA; Hill, DP; Issel-Tarver, L; Kasarskis, A; Lewis, S; Matese, JC; Richardson, JE; Ringwald, M; Rubin, GM; Sherlock, G
err分享
err收藏
The Gene Ontology knowledgebase in 2023基因本体知识库2023年
err2023-03-03
err774
errOAAI
errAleksander, Suzi A.; Balhoff, James; Carbon, Seth; Cherry, J. Michael; Drabkin, Harold J.; Ebert, Dustin; Feuermann, Marc; Gaudet, Pascale; Harris, Nomi L.; Hill, David P.; Lee, Raymond; Mi, Huaiyu; Moxon, Sierra; Mungall, Christopher J.; Muruganugan, Anushya; Mushayahama, Tremayne; Sternberg, Paul W.; Thomas, Paul D.; Van Auken, Kimberly; Ramsey, Jolene; Siegele, Deborah A.; Chisholm, Rex L.; Fey, Petra; Aspromonte, Maria Cristina; Nugnes, Maria Victoria; Quaglia, Federica; Tosatto, Silvio; Giglio, Michelle; Nadendla, Suvarna; Antonazzo, Giulia; Attrill, Helen; dos Santos, Gil; Marygold, Steven; Strelets, Victor; Tabone, Christopher J.; Thurmond, Jim; Zhou, Pinglei; Ahmed, Saadullah H.; Asanitthong, Praoparn; Luna Buitrago, Diana; Erdol, Meltem N.; Gage, Matthew C.; Ali Kadhum, Mohamed; Li, Kan Yan Chloe; Long, Miao; Michalak, Aleksandra; Pesala, Angeline; Pritazahra, Armalya; Saverimuttu, Shirin C. C.; Su, Renzhi; Thurlow, Kate E.; Lovering, Ruth C.; Logie, Colin; Oliferenko, Snezhana; Blake, Judith; Christie, Karen; Corbani, Lori; Dolan, Mary E.; Sitnikov, Dmitry; Smith, Cynthia; Cuzick, Alayne; Seager, James; Cooper, Laurel; Elser, Justin; Jaiswal, Pankaj; Gupta, Parul; Naithani, Sushma; Lera-Ramirez, Manuel; Rutherford, Kim; Wood, Valerie; De Pons, Jeffrey L.; Dwinell, Melinda R.; Hayman, G. Thomas; Kaldunski, Mary L.; Kwitek, Anne E.; Laulederkind, Stanley J. F.; Tutaj, Marek A.; Vedi, Mahima; Wang, Shur-Jen; D'Eustachio, Peter; Aimo, Lucila; Axelsen, Kristian; Bridge, Alan; Hyka-Nouspikel, Nevila; Morgat, Anne; Engel, Stacia R.; Karra, Kalpana; Miyasato, Stuart R.; Nash, Robert S.; Skrzypek, Marek S.; Weng, Shuai; Wong, Edith D.; Bakker, Erika; Berardini, Tanya Z.; Reiser, Leonore; Auchincloss, Andrea; Argoud-Puy, Ghislaine; Blatter, Marie-Claude; Boutet, Emmanuel; Breuza, Lionel; Casals-Casas, Cristina; Coudert, Elisabeth; Estreicher, Anne; Livia Famiglietti, Maria; Gos, Arnaud; Gruaz-Gumowski, Nadine; Hulo, Chantal; Jungo, Florence; Le Mercier, Philippe; Lieberherr, Damien; Masson, Patrick; Pedruzzi, Ivo; Pourcel, Lucille; Poux, Sylvain; Rivoire, Catherine; Sundaram, Shyamala; Bateman, Alex; Bowler-Barnett, Emily; Bye-A-Jee, Hema; Denny, Paul; Ignatchenko, Alexandr; Ishtiaq, Rizwan; Lock, Antonia; Lussi, Yvonne; Magrane, Michele; Martin, Maria J.; Orchard, Sandra; Raposo, Pedro; Speretta, Elena; Tyagi, Nidhi; Warner, Kate; Zaru, Rossana; Diehl, Alexander D.; Chan, Juancarlos; Diamantakis, Stavros; Raciti, Daniela; Zarowiecki, Magdalena; Fisher, Malcolm; James-Zorn, Christina; Ponferrada, Virgilio; Zorn, Aaron; Ramachandran, Sridhar; Ruzicka, Leyla; Westerfield, Monte
err分享
err收藏
Proteins in Synthetic Biology with Agricultural and Environmental Applications合成生物学中具有农业和环境应用前景的蛋白质
err2022-11-21
err0
errOAAI
errMadison M. Mann; Toriana N. Vigil; Samantha M. Felton; William E. Fahy; Mason A. Kinkeade; Victoria K. Kartseva; Mary-Jean C. Rowson; Abigail J. Frost; Bryan W. Berger
err分享
err收藏
Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing面向生物医学自然语言处理的领域语言模型预训练
err2021-10-15
err0
errOAAI
errYu Gu; Robert Tinn; Hao Cheng; Michael Lucas; Naoto Usuyama; Xiaodong Liu; Tristan Naumann; Jianfeng Gao; Hoifung Poon
err分享
err收藏
学者 查看更多内容