Leveraging Structured Biological Knowledge for Counterfactual Inference: A Case Study of Viral Pathogenesis

Abstract

Counterfactual inference is a useful tool for comparing outcomes of interventions on complex systems. It requires us to represent the system in form of a structural causal model, complete with a causal diagram, probabilistic assumptions on exogenous variables, and functional assignments. Specifying such models can be extremely difficult in practice. The process requires substantial domain expertise, and does not scale easily to large systems, multiple systems, or novel system modifications. At the same time, many application domains, such as molecular biology, are rich in structured causal knowledge that is qualitative in nature. This manuscript proposes a general approach for querying a causal biological knowledge graph, and converting the qualitative result into a quantitative structural causal model that can learn from data to answer the question. We demonstrate the feasibility, accuracy and versatility of this approach using two case studies in systems biology. The first demonstrates the appropriateness of the underlying assumptions and the accuracy of the results. The second demonstrates the versatility of the approach by querying a knowledge base for the molecular determinants of a severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-induced cytokine storm, and performing counterfactual inference to estimate the causal effect of medical countermeasures for severely ill patients.

Automated assembly of molecular mechanisms at scale from text mining and curated databases

“…Others can make use of INDRA tools since they are open source (https://github.com/sorgerlab/indra) and welldocumented (https://indra.readthedocs.io). INDRA has already been used for diverse knowledge assembly, curation, and analysis tasks, including network-based gene function enrichment (Ietswaart et al, 2021), causal analysis of viral pathogenesis (Zucker et al, 2021), drug target prioritization for acute myeloid leukemia (Wooten et al, 2021), assembling knowledge about protein kinases (Moret et al, 2021), assisting manual biocuration efforts (Glavaški and Velicki, 2021;Hoyt et al, 2019a;Ostaszewski et al, 2021), and helping authors capture mechanistic findings in computable form (Wong et al, 2021).…”

Rethinking the framework constructed by counterfactual functional model

“…For example, it is difficult for current smart devices to make counterfactual inferences. A large number of researchers are increasingly interested in combining counterfactual inference with AI [27,28], such as explaining consumer behavior [29], the study of viral pathogenesis [30], and predicting the risk of flight delays [31]. In addition, counterfactual inference has shown advantages in improving the robustness of the model [32,33] and optimizing text generation tasks [34] and classification tasks [35].…”

Do-calculus enables estimation of causal effects in partially observed biomolecular pathways

“…The system in Figure 5a is a well-studied insulin-like growth factor signaling system regulating growth and energy metabolism of a cell ( Zucker et al , 2021 ). IGF and EGF are latent.…”

“…The network was extracted from COVID-19 Open Research Dataset (CORD-19) (13) document corpus using the Integrated Dynamical Reasoner and Assembler (INDRA) ( Gyori et al , 2017 ) workflow ( Zucker et al , 2021 ), and by quering and expressing the corresponding causal statements in the Biological Expression Language (BEL) ( Slater, 2014 ) using PyBEL ( Hoyt et al , 2018 ). Presence of latent variables was determined by querying pairs of entities in the network for common causes in the corpus.…”