Rxivist logo

Automating Mendelian randomization through machine learning to construct a putative causal map of the human phenome

By Gibran Hemani, Jack Bowden, Philip C Haycock, Jie Zheng, Oliver Davis, Peter Flach, Tom Gaunt, George Davey Smith

Posted 10 Aug 2017
bioRxiv DOI: 10.1101/173682

A major application for genome-wide association studies (GWAS) has been the emerging field of causal inference using Mendelian randomization (MR), where the causal effect between a pair of traits can be estimated using only summary level data. MR depends on SNPs exhibiting vertical pleiotropy, where the SNP influences an outcome phenotype only through an exposure phenotype. Issues arise when this assumption is violated due to SNPs exhibiting horizontal pleiotropy. We demonstrate that across a range of pleiotropy models, instrument selection will be increasingly liable to selecting invalid instruments as GWAS sample sizes continue to grow. Methods have been developed in an attempt to protect MR from different patterns of horizontal pleiotropy, and here we have designed a mixture-of-experts machine learning framework (MR-MoE 1.0) that predicts the most appropriate model to use for any specific causal analysis, improving on both power and false discovery rates. Using the approach, we systematically estimated the causal effects amongst 2407 phenotypes. Almost 90% of causal estimates indicated some level of horizontal pleiotropy. The causal estimates are organised into a publicly available graph database (http://eve.mrbase.org), and we use it here to highlight the numerous challenges that remain in automated causal inference.

Download data

  • Downloaded 2,889 times
  • Download rankings, all-time:
    • Site-wide: 1,851 out of 85,151
    • In epidemiology: 13 out of 1,556
  • Year to date:
    • Site-wide: 9,305 out of 85,151
  • Since beginning of last month:
    • Site-wide: 8,860 out of 85,151

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

Sign up for the Rxivist weekly newsletter! (Click here for more details.)


News