2021/01/13 by Jeremy Zucker, Zucker, Jeremy, Kaushal Paneri +19
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial Intelligence (cs.AI) #Bioinformatics and Genomic Networks #Computational Drug Discovery Methods #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Quantitative Methods (q-bio.QM)
paper · pdf · doi:10.48550/arxiv.2101.05136
openalex publication_date 2021/01/13 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Counterfactual inference is a useful tool for comparing outcomes of\ninterventions on complex systems. It requires us to represent the system in\nform of a structural causal model, complete with a causal diagram,\nprobabilistic assumptions on exogenous variables, and functional assignments.\nSpecifying such models can be extremely difficult in practice. The process\nrequires substantial domain expertise, and does not scale easily to large\nsystems, multiple systems, or novel system modifications. At the same time,\nmany application domains, such as molecular biology, are rich in structured\ncausal knowledge that is qualitative in nature. This manuscript proposes a\ngeneral approach for querying a causal biological knowledge graph, and\nconverting the qualitative result into a quantitative structural causal model\nthat can learn from data to answer the question. We demonstrate the\nfeasibility, accuracy and versatility of this approach using two case studies\nin systems biology. The first demonstrates the appropriateness of the\nunderlying assumptions and the accuracy of the results. The second demonstrates\nthe versatility of the approach by querying a knowledge base for the molecular\ndeterminants of a severe acute respiratory syndrome coronavirus 2\n(SARS-CoV-2)-induced cytokine storm, and performing counterfactual inference to\nestimate the causal effect of medical countermeasures for severely ill\npatients.\n