Interpretable neural architecture search and transfer learning for understanding CRISPR/Cas9 off-target enzymatic reactions.

Finely-tuned enzymatic pathways control cellular processes, and their dysregulation can lead to disease. Creating predictive and interpretable models for these pathways is challenging because of the complexity of the pathways and of the cellular and genomic contexts. Here we introduce , a deep learning framework which addresses these challenges with data-driven and biophysically interpretable models for determining the kinetics of biochemical systems. First, it uses kinetic assays to rapidly hypothesize an ensemble of high-quality Kinetically Interpretable Neural Networks (KINNs) that predict reaction rates. It then employs a novel transfer learning step, where the KINNs are inserted as intermediary layers into deeper convolutional neural networks, fine-tuning the predictions for reaction-dependent outcomes. makes effective use of the limited, but clean data and the complex, yet plentiful data that captures cellular context. We apply to predict CRISPR-Cas9 off-target editing probabilities and demonstrate that achieves state-of-the-art performance, regularizes neural network architectures, and maintains physical interpretability.