Hum Mutat. 2017 Sep;38(9):1182-1192. doi: 10.1002/humu.23280. Epub 2017 Jul 7.

Working toward precision medicine: Predicting phenotypes from exomes in the Critical Assessment of Genome Interpretation (CAGI) challenges.

Daneshjou R¹, Wang Y², Bromberg Y², Bovo S³, Martelli PL³, Babbi G³, Lena PD⁴, Casadio R^3,⁵, Edwards M⁶, Gifford D⁶, Jones DT⁷, Sundaram L⁸, Bhat RR⁸, Li X⁸, Pal LR⁹, Kundu K^9,¹⁰, Yin Y^9,¹⁰, Moult J^9,¹¹, Jiang Y¹², Pejaver V^12,¹³, Pagel KA¹², Li B¹⁴, Mooney SD¹³, Radivojac P¹², Shah S¹⁵, Carraro M¹⁶, Gasparini A^16,¹⁷, Leonardi E¹⁷, Giollo M^16,¹⁸, Ferrari C¹⁸, Tosatto SCE^16,¹⁹, Bachar E²⁰, Azaria JR²⁰, Ofran Y²⁰, Unger R²⁰, Niroula A²¹, Vihinen M²¹, Chang B²², Wang MH^22,²³, Franke A²⁴, Petersen BS²⁴, Pirooznia M²⁵, Zandi P²⁶, McCombie R²⁷, Potash JB²⁸, Altman RB¹, Klein TE¹, Hoskins RA²⁹, Repo S²⁹, Brenner SE²⁹, Morgan AA³⁰.

Author information

1: Department of Genetics, Stanford School of Medicine, Stanford, California.
2: Department of Biochemistry and Microbiology, Rutgers University, New Brunswick, New Jersey.
3: Biocomputing Group, BiGeA/CIG, "Luigi Galvani" Interdepartmental Center for Integrated Studies of Bioinformatics, Biophysics, and Biocomplexity, University of Bologna, Bologna, Italy.
4: Biocomputing Group/Department of Computer Science and Engineering, University of Bologna, Bologna, Italy.
5: "Giorgio Prodi" Interdepartmental Center for Cancer Research, University of Bologna, Bologna, Italy.
6: Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts.
7: Bioinformatics Group, Department of Computer Science, University College London, London, United Kingdom.
8: Large-scale Intelligent Systems Laboratory, NSF Center for Big Learning, University of Florida, Gainesville, Florida.
9: Institute for Bioscience and Biotechnology Research, University of Maryland, Rockville, Maryland.
10: Computational Biology, Bioinformatics and Genomics, Biological Sciences Graduate Program, University of Maryland, College Park, Maryland.
11: Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, Maryland.
12: Department of Computer Science and Informatics, Indiana University, Bloomington, Indiana.
13: Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, Washington.
14: Gilead Sciences, Foster City, California.
15: Qiagen Bioinformatics, Redwood City, California.
16: Department of Biomedical Science, University of Padova, Padova, Italy.
17: Department of Woman and Child Health, University of Padova, Padova, Italy.
18: Department of Information Engineering, University of Padova, Padova, Italy.
19: CNR Institute of Neuroscience, Padova, Italy.
20: The Mina and Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat-Gan, Israel.
21: Protein Structure and Bioinformatics Group, Department of Experimental Medical Science, Lund University, Lund, Sweden.
22: Division of Biostatistics and Centre for Clinical Research and Biostatistics, JC School of Public Health and Primary Care, Chinese University of Hong Kong, Shatin, N.T., Hong Kong.
23: CUHK Shenzhen Research Institute, Shenzhen, China.
24: Institute of Clinical Molecular Biology, Christian-Albrechts-University Kiel, Kiel, Germany.
25: Department of Psychiatry, The Johns Hopkins University School of Medicine, Baltimore, Maryland.
26: Department of Mental Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland.
27: Cold Spring Harbor Laboratory, Cold Spring Harbor, New York.
28: Department of Psychiatry, University of Iowa, Iowa City, Iowa.
29: Department of Plant and Microbial Biology, University of California Berkeley, Berkeley, California.
30: Stanford School of Medicine, Stanford, California.

Abstract

Precision medicine aims to predict a patient's disease risk and best therapeutic options by using that individual's genetic sequencing data. The Critical Assessment of Genome Interpretation (CAGI) is a community experiment consisting of genotype-phenotype prediction challenges; participants build models, undergo assessment, and share key findings. For CAGI 4, three challenges involved using exome-sequencing data: Crohn's disease, bipolar disorder, and warfarin dosing. Previous CAGI challenges included prior versions of the Crohn's disease challenge. Here, we discuss the range of techniques used for phenotype prediction as well as the methods used for assessing predictive models. Additionally, we outline some of the difficulties associated with making predictions and evaluating them. The lessons learned from the exome challenges can be applied to both research and clinical efforts to improve phenotype prediction from genotype. In addition, these challenges serve as a vehicle for sharing clinical and research exome data in a secure manner with scientists who have a broad range of expertise, contributing to a collaborative effort to advance our understanding of genotype-phenotype relationships.