Borrelia-specific antibody profiles and complement deposition in joint fluid distinguish antibiotic-refractory from -responsive Lyme arthritis.

Lyme arthritis, caused by the spirochete Borrelia burgdorferi, is the most common feature of late disseminated Lyme disease in the United States. While most Lyme arthritis resolves with antibiotics, termed "antibiotic-responsive", some individuals develop progressive synovitis despite antibiotic therapy, called "antibiotic-refractory" Lyme arthritis (LA). The primary drivers behind antibiotic-refractory arthritis remain incompletely understood. We performed a matched, cross-compartmental comparison of antibody profiles from blood and joint fluid of individuals with antibiotic-responsive (n = 11) or antibiotic-refractory LA (n = 31). While serum antibody profiles poorly discriminated responsive from refractory patients, a discrete profile of B.burgdorferi-specific antibodies in joint fluid discriminated antibiotic-responsive from refractory LA. Cross-compartmental comparison of antibody glycosylation, IgA1, and antibody-dependent complement deposition (ADCD) revealed more poorly coordinated humoral responses and increased ADCD in refractory disease. These data reveal B.burgdorferi-specific serological markers that may support early stratification and clinical management, and point to antibody-dependent complement activation as a key mechanism underlying persistent disease.

ResidualBind: Uncovering Sequence-Structure Preferences of RNA-Binding Proteins with Deep Neural Networks.

Deep neural networks have demonstrated improved performance at predicting sequence specificities of DNA- and RNA-binding proteins. However, it remains unclear why they perform better than previous methods that rely on k-mers and position weight matrices. Here, we highlight a recent deep learning-based software package, called ResidualBind, that analyzes RNA-protein interactions using only RNA sequence as an input feature and performs global importance analysis for model interpretability. We discuss practical considerations for model interpretability to uncover learned sequence motifs and their secondary structure preferences.

Global importance analysis: An interpretability method to quantify importance of genomic features in deep neural networks.

Deep neural networks have demonstrated improved performance at predicting the sequence specificities of DNA- and RNA-binding proteins compared to previous methods that rely on k-mers and position weight matrices. To gain insights into why a DNN makes a given prediction, model interpretability methods, such as attribution methods, can be employed to identify motif-like representations along a given sequence. Because explanations are given on an individual sequence basis and can vary substantially across sequences, deducing generalizable trends across the dataset and quantifying their effect size remains a challenge. Here we introduce global importance analysis (GIA), a model interpretability method that quantifies the population-level effect size that putative patterns have on model predictions. GIA provides an avenue to quantitatively test hypotheses of putative patterns and their interactions with other patterns, as well as map out specific functions the network has learned. As a case study, we demonstrate the utility of GIA on the computational task of predicting RNA-protein interactions from sequence. We first introduce a convolutional network, we call ResidualBind, and benchmark its performance against previous methods on RNAcompete data. Using GIA, we then demonstrate that in addition to sequence motifs, ResidualBind learns a model that considers the number of motifs, their spacing, and sequence context, such as RNA secondary structure and GC-bias.