RESUMO
Here we used machine learning to engineer genetically encoded fluorescent indicators, protein-based sensors critical for real-time monitoring of biological activity. We used machine learning to predict the outcomes of sensor mutagenesis by analyzing established libraries that link sensor sequences to functions. Using the GCaMP calcium indicator as a scaffold, we developed an ensemble of three regression models trained on experimentally derived GCaMP mutation libraries. The trained ensemble performed an in silico functional screen on 1,423 novel, uncharacterized GCaMP variants. As a result, we identified the ensemble-derived GCaMP (eGCaMP) variants, eGCaMP and eGCaMP+, which achieve both faster kinetics and larger ∆F/F0 responses upon stimulation than previously published fast variants. Furthermore, we identified a combinatorial mutation with extraordinary dynamic range, eGCaMP2+, which outperforms the tested sixth-, seventh- and eighth-generation GCaMPs. These findings demonstrate the value of machine learning as a tool to facilitate the efficient engineering of proteins for desired biophysical characteristics.
Assuntos
Sinalização do Cálcio , Cálcio , Cálcio/metabolismo , Corantes , Indicadores e Reagentes , Aprendizado de MáquinaRESUMO
Vanishing white matter disease (VWM) is a severe leukodystrophy of the central nervous system caused by mutations in subunits of the eukaryotic initiation factor 2B complex (eIF2B). Current models only partially recapitulate key disease features, and pathophysiology is poorly understood. Through development and validation of zebrafish (Danio rerio) models of VWM, we demonstrate that zebrafish eif2b mutants phenocopy VWM, including impaired somatic growth, early lethality, effects on myelination, loss of oligodendrocyte precursor cells, increased apoptosis in the CNS, and impaired motor swimming behavior. Expression of human EIF2B2 in the zebrafish eif2b2 mutant rescues lethality and CNS apoptosis, demonstrating conservation of function between zebrafish and human. In the mutants, intron 12 retention leads to expression of a truncated eif2b5 transcript. Expression of the truncated eif2b5 in wild-type larva impairs motor behavior and activates the ISR, suggesting that a feed-forward mechanism in VWM is a significant component of disease pathophysiology.