Scaling structural learning with NO-BEARS to infer causal transcriptome networks
This work addresses the challenge of efficiently inferring causal networks in genomics, which is crucial for understanding disease mechanisms, but it is incremental as it builds directly on an existing method.
The authors tackled the problem of constructing gene regulatory networks from transcriptomic data by developing NO-BEARS, a novel algorithm that improves upon NOTEARS with faster computation and better handling of non-linearity, demonstrating reduced processing time from hours to seconds and enhanced accuracy on synthetic data.
Constructing gene regulatory networks is a critical step in revealing disease mechanisms from transcriptomic data. In this work, we present NO-BEARS, a novel algorithm for estimating gene regulatory networks. The NO-BEARS algorithm is built on the basis of the NOTEARS algorithm with two improvements. First, we propose a new constraint and its fast approximation to reduce the computational cost of the NO-TEARS algorithm. Next, we introduce a polynomial regression loss to handle non-linearity in gene expressions. Our implementation utilizes modern GPU computation that can decrease the time of hours-long CPU computation to seconds. Using synthetic data, we demonstrate improved performance, both in processing time and accuracy, on inferring gene regulatory networks from gene expression data.