Dataset Information

The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens.

ABSTRACT: BACKGROUND:The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function. RESULTS:Here, we report on the results of the third CAFA challenge, CAFA3, that featured an expanded analysis over the previous CAFA rounds, both in terms of volume of data analyzed and the types of analysis performed. In a novel and major new development, computational predictions and assessment goals drove some of the experimental assays, resulting in new functional annotations for more than 1000 genes. Specifically, we performed experimental whole-genome mutation screening in Candida albicans and Pseudomonas aureginosa genomes, which provided us with genome-wide experimental data for genes associated with biofilm formation and motility. We further performed targeted assays on selected genes in Drosophila melanogaster, which we suspected of being involved in long-term memory. CONCLUSION:We conclude that while predictions of the molecular function and biological process annotations have slightly improved over time, those of the cellular component have not. Term-centric prediction of experimental annotations remains equally challenging; although the performance of the top methods is significantly better than the expectations set by baseline methods in C. albicans and D. melanogaster, it leaves considerable room and need for improvement. Finally, we report that the CAFA community now involves a broad range of participants with expertise in bioinformatics, biological experimentation, biocuration, and bio-ontologies, working together to improve functional annotation, computational function prediction, and our ability to manage big data in the era of large experimental screens.

SUBMITTER: Zhou N

PROVIDER: S-EPMC6864930 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens.

Zhou Naihui N Jiang Yuxiang Y Bergquist Timothy R TR Lee Alexandra J AJ Kacsoh Balint Z BZ Crocker Alex W AW Lewis Kimberley A KA Georghiou George G Nguyen Huy N HN Hamid Md Nafiz MN Davis Larry L Dogan Tunca T Atalay Volkan V Rifaioglu Ahmet S AS Dalkıran Alperen A Cetin Atalay Rengul R Zhang Chengxin C Hurto Rebecca L RL Freddolino Peter L PL Zhang Yang Y Bhat Prajwal P Supek Fran F Fernández José M JM Gemovic Branislava B Perovic Vladimir R VR Davidović Radoslav S RS Sumonja Neven N Veljkovic Nevena N Asgari Ehsaneddin E Mofrad Mohammad R K MRK Profiti Giuseppe G Savojardo Castrense C Martelli Pier Luigi PL Casadio Rita R Boecker Florian F Schoof Heiko H Kahanda Indika I Thurlby Natalie N McHardy Alice C AC Renaux Alexandre A Saidi Rabie R Gough Julian J Freitas Alex A AA Antczak Magdalena M Fabris Fabio F Wass Mark N MN Hou Jie J Cheng Jianlin J Wang Zheng Z Romero Alfonso E AE Paccanaro Alberto A Yang Haixuan H Goldberg Tatyana T Zhao Chenguang C Holm Liisa L Törönen Petri P Medlar Alan J AJ Zosa Elaine E Borukhov Itamar I Novikov Ilya I Wilkins Angela A Lichtarge Olivier O Chi Po-Han PH Tseng Wei-Cheng WC Linial Michal M Rose Peter W PW Dessimoz Christophe C Vidulin Vedrana V Dzeroski Saso S Sillitoe Ian I Das Sayoni S Lees Jonathan Gill JG Jones David T DT Wan Cen C Cozzetto Domenico D Fa Rui R Torres Mateo M Warwick Vesztrocy Alex A Rodriguez Jose Manuel JM Tress Michael L ML Frasca Marco M Notaro Marco M Grossi Giuliano G Petrini Alessandro A Re Matteo M Valentini Giorgio G Mesiti Marco M Roche Daniel B DB Reeb Jonas J Ritchie David W DW Aridhi Sabeur S Alborzi Seyed Ziaeddin SZ Devignes Marie-Dominique MD Koo Da Chen Emily DCE Bonneau Richard R Gligorijević Vladimir V Barot Meet M Fang Hai H Toppo Stefano S Lavezzo Enrico E Falda Marco M Berselli Michele M Tosatto Silvio C E SCE Carraro Marco M Piovesan Damiano D Ur Rehman Hafeez H Mao Qizhong Q Zhang Shanshan S Vucetic Slobodan S Black Gage S GS Jo Dane D Suh Erica E Dayton Jonathan B JB Larsen Dallas J DJ Omdahl Ashton R AR McGuffin Liam J LJ Brackenridge Danielle A DA Babbitt Patricia C PC Yunes Jeffrey M JM Fontana Paolo P Zhang Feng F Zhu Shanfeng S You Ronghui R Zhang Zihan Z Dai Suyang S Yao Shuwei S Tian Weidong W Cao Renzhi R Chandler Caleb C Amezola Miguel M Johnson Devon D Chang Jia-Ming JM Liao Wen-Hung WH Liu Yi-Wei YW Pascarelli Stefano S Frank Yotam Y Hoehndorf Robert R Kulmanov Maxat M Boudellioua Imane I Politano Gianfranco G Di Carlo Stefano S Benso Alfredo A Hakala Kai K Ginter Filip F Mehryary Farrokh F Kaewphan Suwisa S Björne Jari J Moen Hans H Tolvanen Martti E E MEE Salakoski Tapio T Kihara Daisuke D Jain Aashish A Šmuc Tomislav T Altenhoff Adrian A Ben-Hur Asa A Rost Burkhard B Brenner Steven E SE Orengo Christine A CA Jeffery Constance J CJ Bosco Giovanni G Hogan Deborah A DA Martin Maria J MJ O'Donovan Claire C Mooney Sean D SD Greene Casey S CS Radivojac Predrag P Friedberg Iddo I

Genome biology 20191119 1

<h4>Background</h4>The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function.<h4>Results</h4>Here, we report on the results of the third CAFA challenge, CAFA3, that featured an expanded analysis over the previous CAFA rounds, both in terms of volume of data analyzed and the types of analysis performed. In a novel and major new development, computational predictions and assessment ...[more]

PMID: 31744546

Similar Datasets

Project description:BACKGROUND: Advances in sequencing technology over the past decade have resulted in an abundance of sequenced proteins whose function is yet unknown. As such, computational systems that can automatically predict and annotate protein function are in demand. Most computational systems use features derived from protein sequence or protein structure to predict function. In an earlier work, we demonstrated the utility of biomedical literature as a source of text features for predicting protein subcellular location. We have also shown that the combination of text-based and sequence-based prediction improves the performance of location predictors. Following up on this work, for the Critical Assessment of Function Annotations (CAFA) Challenge, we developed a text-based system that aims to predict molecular function and biological process (using Gene Ontology terms) for unannotated proteins. In this paper, we present the preliminary work and evaluation that we performed for our system, as part of the CAFA challenge. RESULTS: We have developed a preliminary system that represents proteins using text-based features and predicts protein function using a k-nearest neighbour classifier (Text-KNN). We selected text features for our classifier by extracting key terms from biomedical abstracts based on their statistical properties. The system was trained and tested using 5-fold cross-validation over a dataset of 36,536 proteins. System performance was measured using the standard measures of precision, recall, F-measure and overall accuracy. The performance of our system was compared to two baseline classifiers: one that assigns function based solely on the prior distribution of protein function (Base-Prior) and one that assigns function based on sequence similarity (Base-Seq). The overall prediction accuracy of Text-KNN, Base-Prior, and Base-Seq for molecular function classes are 62%, 43%, and 58% while the overall accuracy for biological process classes are 17%, 11%, and 28% respectively. Results obtained as part of the CAFA evaluation itself on the CAFA dataset are reported as well. CONCLUSIONS: Our evaluation shows that the text-based classifier consistently outperforms the baseline classifier that is based on prior distribution, and typically has comparable performance to the baseline classifier that uses sequence similarity. Moreover, the results suggest that combining text features with other types of features can potentially lead to improved prediction performance. The preliminary results also suggest that while our text-based classifier can be used to predict both molecular function and biological process in which a protein is involved, the classifier performs significantly better for predicting molecular function than for predicting biological process. A similar trend was observed for other classifiers participating in the CAFA challenge.

Dataset Information

The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens.

Publications

The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets