@unpublished{18648,
  abstract     = {Statistical causal learning in genomics relies on the instrumental variable method of
Mendelian Randomization (MR). Currently, an overwhelming number of MR studies
purport to show causal relationships among a wide range of risk factors and outcomes.
Here, we show that selecting instrument variables from genome-wide association study
estimates leads to high false discovery rates for many MR approaches, which can be
greatly reduced by employing a graphical inference approach which: (i) explicitly tests
instrumental variable assumptions; (ii) distinguishes direct from indirect factors in very
high-dimensional data; (iii) discriminates pleiotropic from trait-specific markers, controlling for LD genome-wide; (iv) accommodates rare variants and binary outcomes in a
principled way; and (v) identifies potential unobserved latent confounding. For 17 traits
and 8.4M variants recorded for 458,747 individuals in the UK Biobank, we show that
standard MR analysis gives an abundance of findings that disappear under stringent
assumption checks, with many relationships reflecting potential unmeasured confounding. This implies that mixtures of temporal precedence and potential for reverse-causality
prohibit understanding the underlying nature of phenotypic and genetic correlations in
biobank data. We propose that well-curated longitudinal records are likely needed and
that our approach provides a first-step toward robust principled screening for potential
causal links.
},
  author       = {Machnik, Nick N and Mahmoudi, Seyed Mahdi and Borczyk, Malgorzata and Krätschmer, Ilse and Bauer, Markus J. and Robinson, Matthew Richard},
  booktitle    = {bioRxiv},
  title        = {{Causal inference for multiple risk factors and diseases from genomics data}},
  doi          = {10.1101/2023.12.06.570392},
  year         = {2024},
}