Deep neural networks with knockoff features identify nonlinear causal relations and estimate effect sizes in complex biological systems.

Journal: GigaScience
PMID: 37395630

Abstract

BACKGROUND: Learning the causal structure helps identify risk factors, disease mechanisms, and candidate therapeutics for complex diseases. However, although complex biological systems are characterized by nonlinear associations, existing bioinformatic methods of causal inference cannot identify the nonlinear relationships and estimate their effect size.

Authors

  • Zhenjiang Fan
    Department of Computer Science, University of Pittsburgh, Pittsburgh, PA 15213, USA.
  • Kate F Kernan
    Division of Pediatric Critical Care Medicine, Department of Critical Care Medicine, Children's Hospital of Pittsburgh, Center for Critical Care Nephrology and Clinical Research Investigation and Systems Modeling of Acute Illness Center, University of Pittsburgh, Pittsburgh, PA 15260,USA.
  • Aditya Sriram
    Department of Human Genetics, University of Pittsburgh, Pittsburgh, PA 15213, USA.
  • Panayiotis V Benos
    Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA, USA.
  • Scott W Canna
    Pediatric Rheumatology, The Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA.
  • Joseph A Carcillo
    Division of Pediatric Critical Care Medicine, Department of Critical Care Medicine, Children's Hospital of Pittsburgh, Center for Critical Care Nephrology and Clinical Research Investigation and Systems Modeling of Acute Illness Center, University of Pittsburgh, Pittsburgh, PA 15260,USA.
  • Soyeon Kim
    Department of Pediatrics, School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, United States.
  • Hyun Jung Park
    Department of Human Genetics, Graduate School of Public Health, University of Pittsburgh, Pennsylvania, United States.

Keywords

External Resources

Popular Topics
Recent Journals