High-Throughput Cryo-EM Enabled by User-Free Preprocessing Routines

Single-particle cryoelectron microscopy (cryo-EM) continues to grow into a mainstream structural biology technique. Recent developments in data collection strategies alongside new sample preparation devices herald a future where users will collect multiple datasets per microscope session. To make cryo-EM data processing more automatic and user-friendly, we have developed an automatic pipeline for cryo-EM data preprocessing and assessment using a combination of deep-learning and image-analysis tools. We have verified the performance of this pipeline on a number of datasets and extended its scope to include sample screening by the user-free assessment of the qualities of a series of datasets under different conditions. We propose that our workflow provides a decision-free solution for cryo-EM, making data preprocessing more generalized and robust in the high-throughput era as well as more convenient for users from a range of backgrounds.

Approaching neural net feature interpretation using stacked autoencoders: gene expression profiling of systemic lupus erythematosus patients

Systemic lupus erythematosus (SLE) is a rare, autoimmune disorder known to affect most organ sites. Complicating clinical management is a poorly differentiated, heterogenous SLE disease state. While some small molecule drugs and biologics are available for treatment, additional therapeutic options are needed. Parsing complex biological signatures using powerful, yet human interpretable approaches is critical to advancing our understanding of SLE etiology and identifying therapeutic repositioning opportunities. To approach this goal, we developed a semi-supervised deep neural network pipeline for gene expression profiling of SLE patients and subsequent characterization of individual gene features. Our pipeline performed exemplar multinomial classification of SLE patients in independent balanced validation (F₁=0.956) and unbalanced, under-powered testing (F₁=0.944) cohorts. A stacked autoencoder disambiguated individual feature representativeness by regenerating an input-like(A ') feature matrix. A to A' comparisons suggest the top associated features to be key features in gene expression profiling using neural nets.