Domain-PFP allows protein function prediction using function-aware domain embedding representations.

Domain-PFP allows protein function prediction using function-aware domain embedding representations.
复制标题

DOI:
10.1038/s42003-023-05476-9
复制
发表时间:
2023-10-31
影响因子:
5.9
通讯作者:
Kihara, Daisuke
Kihara, Daisuke
中科院分区:
生物学2区
文献类型:
--
作者:
Ibtehaz, Nabil;Kagaya, Yuki;Kihara, Daisuke

文献摘要

参考文献

相似文献

结构域是蛋白质的功能和结构单元,其控制由蛋白质执行的各种生物学功能。因此,蛋白质中结构域的表征可以作为蛋白质的适当功能表示。在这里,我们采用了一个自我监督的协议,通过学习域基因本体(GO)的同现和关联,获得功能一致的表示域。我们构建的域嵌入在执行实际的函数预测任务时是有效的。广泛的评估表明,使用域嵌入的蛋白质表示是上级的大规模蛋白质语言模型在GO预测任务。此外,新的功能预测方法建立在域嵌入,命名为域PFP,大大优于国家的最先进的功能预测。此外,Domain-PFP在CAFA 3评估中表现出了竞争力,在参加评估的顶级团队中取得了最佳表现。一种自监督学习方法,用于生成蛋白质结构域的功能性嵌入表示,能够以最先进的精度进行蛋白质功能预测。
Domains are functional and structural units of proteins that govern various biological functions performed by the proteins. Therefore, the characterization of domains in a protein can serve as a proper functional representation of proteins. Here, we employ a self-supervised protocol to derive functionally consistent representations for domains by learning domain-Gene Ontology (GO) co-occurrences and associations. The domain embeddings we constructed turned out to be effective in performing actual function prediction tasks. Extensive evaluations showed that protein representations using the domain embeddings are superior to those of large-scale protein language models in GO prediction tasks. Moreover, the new function prediction method built on the domain embeddings, named Domain-PFP, substantially outperformed the state-of-the-art function predictors. Additionally, Domain-PFP demonstrated competitive performance in the CAFA3 evaluation, achieving overall the best performance among the top teams that participated in the assessment. A self-supervised learning method to generate functionally informed embedding representations for protein domains, capable of performing protein function prediction with state-of-the-art accuracy.
DOI: 10.1093/nar/gkaa977
发表时间: 2021-01-08
影响因子: 14.9
作者:
Blum M;Chang HY;Chuguransky S;Grego T;Kandasaamy S;Mitchell A;Nuka G;Paysan-Lafosse T;Qureshi M;Raj S;Richardson L;Salazar GA;Williams L;Bork P;Bridge A;Gough J;Haft DH;Letunic I;Marchler-Bauer A;Mi H;Natale DA;Necci M;Orengo CA;Pandurangan AP;Rivoire C;Sigrist CJA;Sillitoe I;Thanki N;Thomas PD;Tosatto SCE;Wu CH;Bateman A;Finn RD
通讯作者: Finn RD
DOI: 10.1093/database/bar068
发表时间: 2012
期刊: Database : the journal of biological databases and curation
影响因子: --
作者:
Burge S;Kelly E;Lonsdale D;Mutowo-Muellenet P;McAnulla C;Mitchell A;Sangrador-Vegas A;Yong SY;Mulder N;Hunter S
通讯作者: Hunter S
DOI: 10.1109/tpami.2021.3095381
发表时间: 2022-10-01
影响因子: 23.6
作者:
Elnaggar, Ahmed;Heinzinger, Michael;Rost, Burkhard
通讯作者: Rost, Burkhard
DOI: 10.1038/s41592-019-0598-1
发表时间: 2019-12-01
期刊: NATURE METHODS
影响因子: 48
作者:
Alley, Ethan C.;Khimulya, Grigory;Church, George M.
通讯作者: Church, George M.
DOI: 10.1371/journal.pone.0141287
发表时间: 2015
期刊: PloS one
影响因子: 3.7
作者:
Asgari E;Mofrad MR
通讯作者: Mofrad MR