An expanded evaluation of protein function prediction methods shows an improvement in accuracy
Ofer D; Toppo S; Salakoski T; O'Donovan C; Tian WD; Lin A; Fontana P; Bankapur AR; Mesiti M; Gemovic B; Wass MN; Tranchevent LC; Ning W; Foulger RE; Falda M; Romero AE; Gong QT; Pichler K; Glisic S; del Pozo A; Ginter F; Funk CS; Almeida-e-Silva DC; Stern A; Benso A; Nepusz T; Valentini G; Moreau Y; Profiti G; Martelli PL; Pavlidis P; Cibrian-Uhalte E; D'Andrea D; Bryson K; Hsu WL; Supek F; Lovering RC; Casadio R; Oates M; Khan IK; Radivojac P; Kihara D; Hamp T; Valencia A; Oron TR; Tosatto SCE; Paccanaro A; Giollo M; Vencio RZN; Youngs N; Mutowo-Meullenet P; Toronen P; Chen CT; Koo DCE; Clark WT; Dukka BKC; Vogel J; Zhou YP; Rost B; Altenhoff A; Fernandez JM; Piovesan D; Sasidharan R; Cozzetto D; Brenner SE; Rehman HU; Greene CS; Lee D; Fang H; Politano G; Das S; Jiang YX; Sillitoe I; Re M; Ferrari C; Kaewphan S; Zhang S; Gough J; Hieta R; Shypitsyna A; Bonneau R; Hakala K; Bargsten JW; Huntley RP; Tramontano A; Dogan T; Minneci F; Dawson NL; Cejuela JM; Cheng JL; Kansakar L; Robinson PN; Maietta P; Skunca N; Yang HX; Holm L; Zakeri P; Mehryary F; Zhong Z; Lepore R; Martin MJ; Friedberg I; Gillis J; Di Carlo S; Rappoport N; Jones DT; Penfold-Brown D; Tress ML; Gabaldon T; Perovic V; Shasha D; Ben-Hur A; Babbitt PC; Lavezzo E; Sharan M; Melidoni AN; Legge D; Denny P; Feng S; Richter L; van Dijk ADJ; Veljkovic V; Li B; Goldberg T; Koskinen P; Mooney SD; Cao RZ; Savino A; Magrane M; Wang Z; Orengo CA; Vucetic S; Kahanda I; Salamov A; Lees JG; Verspoor KM; Veljkovic N; Sternberg MJE; Dessimoz C; ElShal S; Smithers B; Marcet-Houben M; Bhat P; Sahraeian SME; Sedeno-Cortes AE; Linial M; Chapman S
An expanded evaluation of protein function prediction methods shows an improvement in accuracy
Ofer D
Toppo S
Salakoski T
O'Donovan C
Tian WD
Lin A
Fontana P
Bankapur AR
Mesiti M
Gemovic B
Wass MN
Tranchevent LC
Ning W
Foulger RE
Falda M
Romero AE
Gong QT
Pichler K
Glisic S
del Pozo A
Ginter F
Funk CS
Almeida-e-Silva DC
Stern A
Benso A
Nepusz T
Valentini G
Moreau Y
Profiti G
Martelli PL
Pavlidis P
Cibrian-Uhalte E
D'Andrea D
Bryson K
Hsu WL
Supek F
Lovering RC
Casadio R
Oates M
Khan IK
Radivojac P
Kihara D
Hamp T
Valencia A
Oron TR
Tosatto SCE
Paccanaro A
Giollo M
Vencio RZN
Youngs N
Mutowo-Meullenet P
Toronen P
Chen CT
Koo DCE
Clark WT
Dukka BKC
Vogel J
Zhou YP
Rost B
Altenhoff A
Fernandez JM
Piovesan D
Sasidharan R
Cozzetto D
Brenner SE
Rehman HU
Greene CS
Lee D
Fang H
Politano G
Das S
Jiang YX
Sillitoe I
Re M
Ferrari C
Kaewphan S
Zhang S
Gough J
Hieta R
Shypitsyna A
Bonneau R
Hakala K
Bargsten JW
Huntley RP
Tramontano A
Dogan T
Minneci F
Dawson NL
Cejuela JM
Cheng JL
Kansakar L
Robinson PN
Maietta P
Skunca N
Yang HX
Holm L
Zakeri P
Mehryary F
Zhong Z
Lepore R
Martin MJ
Friedberg I
Gillis J
Di Carlo S
Rappoport N
Jones DT
Penfold-Brown D
Tress ML
Gabaldon T
Perovic V
Shasha D
Ben-Hur A
Babbitt PC
Lavezzo E
Sharan M
Melidoni AN
Legge D
Denny P
Feng S
Richter L
van Dijk ADJ
Veljkovic V
Li B
Goldberg T
Koskinen P
Mooney SD
Cao RZ
Savino A
Magrane M
Wang Z
Orengo CA
Vucetic S
Kahanda I
Salamov A
Lees JG
Verspoor KM
Veljkovic N
Sternberg MJE
Dessimoz C
ElShal S
Smithers B
Marcet-Houben M
Bhat P
Sahraeian SME
Sedeno-Cortes AE
Linial M
Chapman S
BIOMED CENTRAL LTD
Julkaisun pysyvä osoite on:
https://urn.fi/URN:NBN:fi-fe2021042715680
https://urn.fi/URN:NBN:fi-fe2021042715680
Tiivistelmä
Background: A major bottleneck in our understanding of the molecular underpinnings of life is the assignment of function to proteins. While molecular experiments provide the most reliable annotation of proteins, their relatively low throughput and restricted purview have led to an increasing role for computational function prediction. However, assessing methods for protein function prediction and tracking progress in the field remain challenging.Results: We conducted the second critical assessment of functional annotation (CAFA), a timed challenge to assess computational methods that automatically assign protein function. We evaluated 126 methods from 56 research groups for their ability to predict biological functions using Gene Ontology and gene-disease associations using Human Phenotype Ontology on a set of 3681 proteins from 18 species. CAFA2 featured expanded analysis compared with CAFA1, with regards to data set size, variety, and assessment metrics. To review progress in the field, the analysis compared the best methods from CAFA1 to those of CAFA2.Conclusions: The top-performing methods in CAFA2 outperformed those from CAFA1. This increased accuracy can be attributed to a combination of the growing number of experimental annotations and improved methods for function prediction. The assessment also revealed that the definition of top-performing algorithms is ontology specific, that different performance metrics can be used to probe the nature of accurate predictions, and the relative diversity of predictions in the biological process and human phenotype ontologies. While there was methodological improvement between CAFA1 and CAFA2, the interpretation of results and usefulness of individual methods remain context-dependent.
Kokoelmat
- Rinnakkaistallenteet [19207]