G2Φnet: Relating genotype and biomechanical phenotype of tissues with deep learning

Abstract

Many genetic mutations adversely affect the structure and function of load-bearing soft tissues, with clinical sequelae often responsible for disability or death. Parallel advances in genetics and histomechanical characterization provide significant insight into these conditions, but there remains a pressing need to integrate such information. We present a novel genotype-to-biomechanical phenotype neural network (G2Φnet) for characterizing and classifying biomechanical properties of soft tissues, which serve as important functional readouts of tissue health or disease. We illustrate the utility of our approach by inferring the nonlinear, genotype-dependent constitutive behavior of the aorta for four mouse models involving defects or deficiencies in extracellular constituents. We show that G2Φnet can infer the biomechanical response while simultaneously ascribing the associated genotype by utilizing limited, noisy, and unstructured experimental data. More broadly, G2Φnet provides a powerful method and a paradigm shift for correlating genotype and biomechanical phenotype quantitatively, promising a better understanding of their interplay in biological tissues.

Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review

“…In the past few years, neural operators have been extensively applied to diverse engineering problems. In solid mechanics applications, neural operators have been successfully used for elastoplasticity [103], fracture mechanics [104], multiscale mechanics [41], and biomechanics [105,106,107].…”

“…(c), Zhang et al[105] developed a DeepONet-based model, genotype-to-biomechanical phenotype neural network (G2Φnet), to characterize mechanical properties of soft tissues and classify their associated genotypes from sparse and noisy experimental data. With a 2-step training process consisting of a learning stage and an inference stage with an ensemble, G2Φnet could effectively learn the constitutive models from biaxial testing data for 28 mice with 4 different genotypes with an L2 error of less than 5%.…”

On the Geometry Transferability of the Hybrid Iterative Numerical Solver for Differential Equations

“…Numerical simulations play a crucial role in scientific and engineering applications such as mechanics of materials and structures [1,2,3,4,5,6,7], bio-mechanics [8,9], fluid dynamics [10,11,12], etc. The simulation approach is based on solving linear/nonlinear partial differential equations (PDEs).…”