Deep learning reduces data requirements and allows real-time measurements in imaging FCS.

Imaging fluorescence correlation spectroscopy (FCS) is a powerful tool to extract information on molecular mobilities, actions, and interactions in live cells, tissues, and organisms. Nevertheless, several limitations restrict its applicability. First, FCS is data hungry, requiring 50,000 frames at 1-ms time resolution to obtain accurate parameter estimates. Second, the data size makes evaluation slow. Third, as FCS evaluation is model dependent, data evaluation is significantly slowed unless analytic models are available. Here, we introduce two convolutional neural networks-FCSNet and ImFCSNet-for correlation and intensity trace analysis, respectively. FCSNet robustly predicts parameters in 2D and 3D live samples. ImFCSNet reduces the amount of data required for accurate parameter retrieval by at least one order of magnitude and makes correct estimates even in moderately defocused samples. Both convolutional neural networks are trained on simulated data, are model agnostic, and allow autonomous, real-time evaluation of imaging FCS measurements.

Wnt3 Is Lipidated at Conserved Cysteine and Serine Residues in Zebrafish Neural Tissue.

Wnt proteins are a family of hydrophobic cysteine-rich secreted glycoproteins that regulate a gamut of physiological processes involved in embryonic development and tissue homeostasis. Wnt ligands are post-translationally lipidated in the endoplasmic reticulum (ER), a step essential for its membrane targeting, association with lipid domains, secretion and interaction with receptors. However, at which residue(s) Wnts are lipidated remains an open question. Initially it was proposed that Wnts are lipid-modified at their conserved cysteine and serine residues (C77 and S209 in mWnt3a), and mutations in either residue impedes its secretion and activity. Conversely, some studies suggested that serine is the only lipidated residue in Wnts, and substitution of serine with alanine leads to retention of Wnts in the ER. In this work, we investigate whether in zebrafish neural tissues Wnt3 is lipidated at one or both conserved residues. To this end, we substitute the homologous cysteine and serine residues of zebrafish Wnt3 with alanine (C80A and S212A) and investigate their influence on Wnt3 membrane organization, secretion, interaction and signaling activity. Collectively, our results indicate that Wnt3 is lipid modified at its C80 and S212 residues. Further, we find that lipid addition at either C80 or S212 is sufficient for its secretion and membrane organization, while the lipid modification at S212 is indispensable for receptor interaction and signaling.