Format

Send to

Choose Destination
Hum Mutat. 2019 Jul 1. doi: 10.1002/humu.23856. [Epub ahead of print]

Performance of computational methods for the evaluation of Pericentriolar Material 1 missense variants in CAGI-5.

Author information

1
Department of Biomedical Sciences, University of Padua, Padua, Italy.
2
Department of Information Engineering, University of Padua, Padua, Italy.
3
Department of Medicine, University of California San Diego, La Jolla, CA, 92093.
4
Department of Biochemistry and Microbiology, Rutgers University, New Brunswick, NJ, 08873, USA.
5
Institute for Advanced Study, Technical University of Munich (TUM), Munich, 85748, Germany.
6
BioFolD Unit, Department of Pharmacy and Biotechnology, University of Bologna, Via F Selmi 3, 40126, Bologna, Italy.
7
Biocomputing Group, Department of Pharmacy and Biotechnology, University of Bologna, Italy.
8
Department of Molecular and Human Genetics, Baylor College of Medicine, Houston, TX, 77030, USA.
9
MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), Broad Institute of MIT and Harvard, Massachusetts, USA.
10
Center for Human Disease Modeling, Duke University Medical Center, Durham, North Carolina, USA.
11
Institute for Bioscience and Biotechnology Research, University of Maryland, 9600 Gudelsky Drive, Rockville, MD, 20850, USA.
12
Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, MD, 20742, USA.
13
Department of Woman and Child Health, University of Padua, Padua, Italy.
14
CNR Institute of Neuroscience, Padua, Italy.
15
Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA.

Abstract

The CAGI-5 PCM1 challenge aimed to predict the effect of 38 transgenic human missense mutations in the Pericentriolar Material 1 (PCM1) protein implicated in schizophrenia. Participants were provided with 16 benign variants (negative controls), 10 hypomorphic, and 12 loss of function variants. Six groups participated and were asked to predict the probability of effect and standard deviation associated to each mutation. Here, we present the challenge assessment. Prediction performance were evaluated using different measures to conclude in a final ranking which highlights the strengths and weaknesses of each group. The results show a great variety of predictions where some methods performed significantly better than others. Benign variants played an important role as negative controls, highlighting predictors biased to identify disease phenotypes. The best predictor, Bromberg lab used a neural-network based method able to discriminate between neutral and non-neutral single nucleotide polymorphisms. The CAGI-5 PCM1 challenge allowed us to evaluate the state of the art techniques for interpreting the effect of novel variants for a difficult target protein. This article is protected by copyright. All rights reserved.

KEYWORDS:

Critical assessment; bioinformatics tools; community challenge; effect prediction; missense mutations; variant interpretation

PMID:
31260570
DOI:
10.1002/humu.23856

Supplemental Content

Full text links

Icon for Wiley
Loading ...
Support Center