Lane’s research sits at the intersection of data science, network biology, and high-performance computing, with the goal of understanding and predicting behavior in complex biological systems. He combines statistical modeling, graph theory, and machine/deep learning to analyze large-scale, multi-omics data and extract mechanistic insight from biological networks. A major focus of his work is developing scalable, automated approaches for systems biology analysis, including LLM-powered agent pipelines for gene set interpretation and explainable AI methods for reverse-engineering large Predictive Expression Networks. Lane is also interested in how perturbations propagate through biological networks, using topological and geometric deep learning approaches to predict phenotypic outcomes of genetic modulation. Much of this work is enabled by leadership-class computing resources at Oak Ridge National Laboratory, where he develops and maintains well-documented, reproducible scientific software and applies these methods to metabolomics, transcriptomics, and other high-dimensional biological data. Overall, his research aims to turn massive, complex biological datasets into interpretable models that can generate testable biological hypotheses at scale.