Supervised machine learning is widely used in biology and deserves more scrutiny. We present a set of community-wide recommendations (DOME) aiming to help establish standards of supervised machine learning validation in biology. Formulated as questions, the DOME recommendations improve the assessment and reproducibility of papers when included as supplementary material. ; The work of the Machine Learning Focus Group was funded by ELIXIR, the research infrastructure for life-science data. IW was funded by the A*STAR Career Development Award (project no. C210112057) from the Agency for Science, Technology and Research (A*STAR), Singapore. D.F. was supported by Estonian Research Council grants (PRG1095, PSG59 and ERA-NET TRANSCAN-2 (BioEndoCar)); Project No 2014-2020.4.01.16-0271, ELIXIR and the European Regional Development Fund through EXCITE Center of Excellence. S.C.E.T. has received funding from the European Union's Horizon 2020 research and innovation programme under Marie Skłodowska-Curie Grant agreements No. 778247 and No. 823886, and Italian Ministry of University and Research PRIN 2017 grant 2017483NH8. ; Peer Reviewed ; "Article signat per 8 autors més 28 autors/es de l' ELIXIR Machine Learning Focus Group: Emidio Capriotti, Rita Casadio, Salvador Capella-Gutierrez, Davide Cirillo, Alessio Del Conte, Alexandros C. Dimopoulos, Victoria Dominguez Del Angel, Joaquin Dopazo, Piero Fariselli, José Maria Fernández, Florian Huber, Anna Kreshuk, Tom Lenaerts, Pier Luigi Martelli, Arcadi Navarro, Pilib Ó Broin, Janet Piñero, Damiano Piovesan, Martin Reczko, Francesco Ronzano, Venkata Satagopam, Castrense Savojardo, Vojtech Spiwok, Marco Antonio Tangaro, Giacomo Tartari, David Salgado, Alfonso Valencia & Federico Zambelli" ; Postprint (author's final draft)
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. ; The work of IF was funded, in part, by the National Science Foundation award DBI-1458359. The work of CSG and AJL was funded, in part, by the National Science Foundation award DBI-1458390 and GBMF 4552 from the Gordon and Betty Moore Foundation. The work of DAH and KAL was funded, in part, by the National Science Foundation award DBI-1458390, National Institutes of Health NIGMS P20 GM113132, and the Cystic Fibrosis Foundation CFRDP STANTO19R0. The work of AP, HY, AR, and MT was funded by BBSRC grants BB/K004131/1, BB/F00964X/1 and BB/M025047/1, Consejo Nacional de Ciencia y Tecnología Paraguay (CONACyT) grants 14-INV-088 and PINV15-315, and NSF Advances in BioInformatics grant 1660648. The work of JC was partially supported by an NIH grant (R01GM093123) and two NSF grants (DBI 1759934 and IIS1763246). ACM acknowledges the support by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy - EXC 2155 "RESIST" - Project ID 39087428. DK acknowledges the support from the National Institutes of Health (R01GM123055) and the National Science Foundation (DMS1614777, CMMI1825941). PB acknowledges the support from the National Institutes of Health (R01GM60595). GB and BZK acknowledge the support from the National Science Foundation (NSF 1458390) and NIH DP1MH110234. FS was funded by the ERC StG 757700 "HYPER-INSIGHT" and by the Spanish Ministry of Science, Innovation and Universities grant BFU2017-89833-P. FS further acknowledges the funding from the Severo Ochoa award to the IRB Barcelona. TS was funded by the Centre of Excellence project "BioProspecting of Adriatic Sea", co-financed by the Croatian Government and the European Regional Development Fund (KK.01.1.1.01.0002). The work of SK was funded by ATT Tieto käyttöön grant and Academy of Finland. JB and HM acknowledge the support of the University of Turku, the Academy of Finland and CSC – IT Center for Science Ltd. TB and SM were funded by the NIH awards UL1 TR002319 and U24 TR002306. The work of CZ and ZW was funded by the National Institutes of Health R15GM120650 to ZW and start-up funding from the University of Miami to ZW. The work of PWR was supported by the National Cancer Institute of the National Institutes of Health under Award Number U01CA198942. PR acknowledges NSF grant DBI-1458477. PT acknowledges the support from Helsinki Institute for Life Sciences. The work of AJM was funded by the Academy of Finland (No. 292589). The work of FZ and WT was funded by the National Natural Science Foundation of China (31671367, 31471245, 91631301) and the National Key Research and Development Program of China (2016YFC1000505, 2017YFC0908402]. CS acknowledges the support by the Italian Ministry of Education, University and Research (MIUR) PRIN 2017 project 2017483NH8. SZ is supported by the National Natural Science Foundation of China (No. 61872094 and No. 61572139) and Shanghai Municipal Science and Technology Major Project (No. 2017SHZDZX01). PLF and RLH were supported by the National Institutes of Health NIH R35-GM128637 and R00-GM097033. JG, DTJ, CW, DC, and RF were supported by the UK Biotechnology and Biological Sciences Research Council (BB/N019431/1, BB/L020505/1, and BB/L002817/1) and Elsevier. The work of YZ and CZ was funded in part by the National Institutes of Health award GM083107, GM116960, and AI134678; the National Science Foundation award DBI1564756; and the Extreme Science and Engineering Discovery Environment (XSEDE) award MCB160101 and MCB160124. The work of BG, VP, RD, NS, and NV was funded by the Ministry of Education, Science and Technological Development of the Republic of Serbia, Project No. 173001. The work of YWL, WHL, and JMC was funded by the Taiwan Ministry of Science and Technology (106-2221-E-004-011-MY2). YWL, WHL, and JMC further acknowledge the support from "the Human Project from Mind, Brain and Learning" of the NCCU Higher Education Sprout Project by the Taiwan Ministry of Education and the National Center for High-performance Computing for computer time and facilities. The work of IK and AB was funded by Montana State University and NSF Advances in Biological Informatics program through grant number 0965768. BR, TG, and JR are supported by the Bavarian Ministry for Education through funding to the TUM. The work of RB, VG, MB, and DCEK was supported by the Simons Foundation, NIH NINDS grant number 1R21NS103831-01 and NSF award number DMR-1420073. CJJ acknowledges the funding from a University of Illinois at Chicago (UIC) Cancer Center award, a UIC College of Liberal Arts and Sciences Faculty Award, and a UIC International Development Award. The work of ML was funded by Yad Hanadiv (grant number 9660 /2019). The work of OL and IN was funded by the National Institute of General Medical Science of the National Institute of Health through GM066099 and GM079656. Research Supporting Plan (PSR) of University of Milan number PSR2018-DIP-010-MFRAS. AWV acknowledges the funding from the BBSRC (CASE studentship BB/M015009/1). CD acknowledges the support from the Swiss National Science Foundation (150654). CO and MJM are supported by the EMBL-European Bioinformatics Institute core funds and the CAFA BBSRC BB/N004876/1. GG is supported by CAFA BBSRC BB/N004876/1. SCET acknowledges funding from the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No 778247 (IDPfun) and from COST Action BM1405 (NGP-net). SEB was supported by NIH/NIGMS grant R01 GM071749. The work of MLT, JMR, and JMF was supported by the National Human Genome Research Institute of the National of Health, grant numbers U41 HG007234. The work of JMF and JMR was also supported by INB Grant (PT17/0009/0001 - ISCIII-SGEFI / ERDF). VA acknowledges the funding from TUBITAK EEEAG-116E930. RCA acknowledges the funding from KanSil 2016K121540. GV acknowledges the funding from Università degli Studi di Milano - Project "Discovering Patterns in Multi-Dimensional Data" and Project "Machine Learning and Big Data Analysis for Bioinformatics". SZ is supported by the National Natural Science Foundation of China (No. 61872094 and No. 61572139) and Shanghai Municipal Science and Technology Major Project (No. 2017SHZDZX01). RY and SY are supported by the 111 Project (NO. B18015), the key project of Shanghai Science & Technology (No. 16JC1420402), Shanghai Municipal Science and Technology Major Project (No. 2018SHZDZX01), and ZJLab. ST was supported by project Ribes Network POR-FESR 3S4H (No. TOPP-ALFREVE18-01) and PRID/SID of University of Padova (No. TOPP-SID19-01). CZ and ZW were supported by the NIGMS grant R15GM120650 to ZW and start-up funding from the University of Miami to ZW. The work of MK and RH was supported by the funding from King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. URF/1/3454-01-01 and URF/1/3790-01-01. The work of SDM is funded, in part, by NSF award DBI-1458443 ; Sí
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. ; The work of IF was funded, in part, by the National Science Foundation award DBI-1458359. The work of CSG and AJL was funded, in part, by the National Science Foundation award DBI-1458390 and GBMF 4552 from the Gordon and Betty Moore Foundation. The work of DAH and KAL was funded, in part, by the National Science Foundation award DBI-1458390, National Institutes of Health NIGMS P20 GM113132, and the Cystic Fibrosis Foundation CFRDP STANTO19R0. The work of AP, HY, AR, and MT was funded by BBSRC grants BB/K004131/1, BB/F00964X/1 and BB/M025047/1, Consejo Nacional de Ciencia y Tecnologia Paraguay (CONACyT) grants 14-INV-088 and PINV15-315, and NSF Advances in BioInformatics grant 1660648. The work of JC was partially supported by an NIH grant (R01GM093123) and two NSF grants (DBI 1759934 and IIS1763246). ACM acknowledges the support by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy -EXC 2155 "RESIST" - Project ID 39087428. DK acknowledges the support from the National Institutes of Health (R01GM123055) and the National Science Foundation (DMS1614777, CMMI1825941). PB acknowledges the support from the National Institutes of Health (R01GM60595). GB and BZK acknowledge the support from the National Science Foundation (NSF 1458390) and NIH DP1MH110234. FS was funded by the ERC StG 757700 "HYPER-INSIGHT" and by the Spanish Ministry of Science, Innovation and Universities grant BFU2017-89833-P. FS further acknowledges the funding from the Severo Ochoa award to the IRB Barcelona. TS was funded by the Centre of Excellence project "BioProspecting of Adriatic Sea", co-financed by the Croatian Government and the European Regional Development Fund (KK.01.1.1.01.0002). The work of SK was funded by ATT Tieto kayttoon grant and Academy of Finland. JB and HM acknowledge the support of the University of Turku, the Academy of Finland and CSC -IT Center for Science Ltd. TB and SM were funded by the NIH awards UL1 TR002319 and U24 TR002306. The work of CZ and ZW was funded by the National Institutes of Health R15GM120650 to ZW and start-up funding from the University of Miami to ZW. The work of PWR was supported by the National Cancer Institute of the National Institutes of Health under Award Number U01CA198942. PR acknowledges NSF grant DBI-1458477. PT acknowledges the support from Helsinki Institute for Life Sciences. The work of AJM was funded by the Academy of Finland (No. 292589). The work of FZ and WT was funded by the National Natural Science Foundation of China (31671367, 31471245, 91631301) and the National Key Research and Development Program of China (2016YFC1000505, 2017YFC0908402]. CS acknowledges the support by the Italian Ministry of Education, University and Research (MIUR) PRIN 2017 project 2017483NH8. SZ is supported by the National Natural Science Foundation of China (No. 61872094 and No. 61572139) and Shanghai Municipal Science and Technology Major Project (No. 2017SHZDZX01). PLF and RLH were supported by the National Institutes of Health NIH R35-GM128637 and R00-GM097033. JG, DTJ, CW, DC, and RF were supported by the UK Biotechnology and Biological Sciences Research Council (BB/N019431/1, BB/L020505/1, and BB/L002817/1) and Elsevier. The work of YZ and CZ was funded in part by the National Institutes of Health award GM083107, GM116960, and AI134678; the National Science Foundation award DBI1564756; and the Extreme Science and Engineering Discovery Environment (XSEDE) award MCB160101 and MCB160124. The work of BG, VP, RD, NS, and NV was funded by the Ministry of Education, Science and Technological Development of the Republic of Serbia, Project No. 173001. The work of YWL, WHL, and JMC was funded by the Taiwan Ministry of Science and Technology (106-2221-E-004-011-MY2). YWL, WHL, and JMC further acknowledge the support from "the Human Project from Mind, Brain and Learning" of the NCCU Higher Education Sprout Project by the Taiwan Ministry of Education and the National Center for High-performance Computing for computer time and facilities. The work of IK and AB was funded by Montana State University and NSF Advances in Biological Informatics program through grant number 0965768. BR, TG, and JR are supported by the Bavarian Ministry for Education through funding to the TUM. The work of RB, VG, MB, and DCEK was supported by the Simons Foundation, NIH NINDS grant number 1R21NS103831-01 and NSF award number DMR-1420073. CJJ acknowledges the funding from a University of Illinois at Chicago (UIC) Cancer Center award, a UIC College of Liberal Arts and Sciences Faculty Award, and a UIC International Development Award. The work of ML was funded by Yad Hanadiv (grant number 9660/2019). The work of OL and IN was funded by the National Institute of General Medical Science of the National Institute of Health through GM066099 and GM079656. Research Supporting Plan (PSR) of University of Milan number PSR2018-DIP-010-MFRAS. AWV acknowledges the funding from the BBSRC (CASE studentship BB/M015009/1). CD acknowledges the support from the Swiss National Science Foundation (150654). CO and MJM are supported by the EMBL-European Bioinformatics Institute core funds and the CAFA BBSRC BB/N004876/1. GG is supported by CAFA BBSRC BB/N004876/1. SCET acknowledges funding from the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No 778247 (IDPfun) and from COST Action BM1405 (NGP-net). SEB was supported by NIH/NIGMS grant R01 GM071749. The work of MLT, JMR, and JMF was supported by the National Human Genome Research Institute of the National of Health, grant numbers U41 HG007234. The work of JMF and JMR was also supported by INB Grant (PT17/0009/0001 - ISCIII-SGEFI/ERDF). VA acknowledges the funding from TUBITAK EEEAG-116E930. RCA acknowledges the funding from KanSil 2016K121540. GV acknowledges the funding from Universita degli Studi di Milano - Project "Discovering Patterns in Multi-Dimensional Data" and Project "Machine Learning and Big Data Analysis for Bioinformatics". SZ is supported by the National Natural Science Foundation of China (No. 61872094 and No. 61572139) and Shanghai Municipal Science and Technology Major Project (No. 2017SHZDZX01). RY and SY are supported by the 111 Project (NO. B18015), the key project of Shanghai Science & Technology (No. 16JC1420402), Shanghai Municipal Science and Technology Major Project (No. 2018SHZDZX01), and ZJLab. ST was supported by project Ribes Network POR-FESR 3S4H (No. TOPP-ALFREVE18-01) and PRID/SID of University of Padova (No. TOPP-SID19-01). CZ and ZW were supported by the NIGMS grant R15GM120650 to ZW and start-up funding from the University of Miami to ZW. The work of MK and RH was supported by the funding from King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. URF/1/3454-01-01 and URF/1/3790-01-01. The work of SDM is funded, in part, by NSF award DBI-1458443. ; Sí
