Deep Learning-Based Objective and Reproducible Osteosarcoma Chemotherapy Response Assessment and Outcome Prediction.

Osteosarcoma is the most common primary bone cancer, whose standard treatment includes pre-operative chemotherapy followed by resection. Chemotherapy response is used for prognosis and management of patients. Necrosis is routinely assessed after chemotherapy from histology slides on resection specimens, where necrosis ratio is defined as the ratio of necrotic tumor/overall tumor. Patients with necrosis ratio ≥90% are known to have a better outcome. Manual microscopic review of necrosis ratio from multiple glass slides is semiquantitative and can have intraobserver and interobserver variability. In this study, an objective and reproducible deep learning-based approach was proposed to estimate necrosis ratio with outcome prediction from scanned hematoxylin and eosin whole slide images (WSIs). To conduct the study, 103 osteosarcoma cases with 3134 WSIs were collected. Deep Multi-Magnification Network was trained to segment multiple tissue subtypes, including viable tumor and necrotic tumor at a pixel level and to calculate case-level necrosis ratio from multiple WSIs. Necrosis ratio estimated by the segmentation model highly correlates with necrosis ratio from pathology reports manually assessed by experts. Furthermore, patients were successfully stratified to predict overall survival with P = 2.4 × 10-6 and progression-free survival with P = 0.016. This study indicates that deep learning can support pathologists as an objective tool to analyze osteosarcoma from histology for assessing treatment response and predicting patient outcome.

Discovery and Characterization of Native Deinococcus radiodurans Promoters for Tunable Gene Expression.

The potential utilization of extremophiles as a robust chassis for metabolic engineering applications has prompted interest in the use of Deinococcus radiodurans for bioremediation efforts, but current applications are limited by the lack of availability of genetic tools, such as promoters. In this study, we used a combined computational and experimental approach to identify and screen 30 predicted promoters for expression in D. radiodurans using a fluorescent reporter assay. The top eight candidates were further characterized, compared to currently available promoters, and optimized for engineering through minimization for use in D. radiodurans Of these top eight, two promoter regions, PDR_1261 and PrpmB, were stronger and more consistent than the most widely used promoter sequence in D. radiodurans, PgroES Furthermore, half of the top eight promoters could be minimized by at least 20% (to obtain final sequences that are approximately 24 to 177 bp), and several of the putative promoters either showed activity in Escherichia coli or were D. radiodurans specific, broadening the use of the promoters for various applications. Overall, this work introduces a suite of novel, well-characterized promoters for protein production and metabolic engineering in D. radioduransIMPORTANCE The tolerance of the extremophile, Deinococcus radiodurans, to numerous oxidative stresses makes it ideal for bioremediation applications, but many of the tools necessary for metabolic engineering are lacking in this organism compared to model bacteria. Although native and engineered promoters have been used to drive gene expression for protein production in D. radiodurans, very few have been well characterized. Informed by bioinformatics, this study expands the repertoire of well-characterized promoters for D. radiodurans via thorough characterization of eight putative promoters with various strengths. These results will help facilitate tunable gene expression, since these promoters demonstrate strong and consistent performance compared to the current standard, PgroES This study also provides a methodology for high-throughput promoter identification and characterization using fluorescence in D. radiodurans The promoters identified in this study will facilitate metabolic engineering of D. radiodurans and enable its use in biotechnological applications ranging from bioremediation to synthesis of commodity chemicals.

A diagnostic host response biosignature for COVID-19 from RNA profiling of nasal swabs and blood.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which causes coronavirus disease-19 (COVID-19), has emerged as the cause of a global pandemic. We used RNA sequencing to analyze 286 nasopharyngeal (NP) swab and 53 whole-blood (WB) samples from 333 patients with COVID-19 and controls. Overall, a muted immune response was observed in COVID-19 relative to other infections (influenza, other seasonal coronaviruses, and bacterial sepsis), with paradoxical down-regulation of several key differentially expressed genes. Hospitalized patients and outpatients exhibited up-regulation of interferon-associated pathways, although heightened and more robust inflammatory responses were observed in hospitalized patients with more clinically severe illness. Two-layer machine learning-based host classifiers consisting of complete (>1000 genes), medium (<100), and small (<20) gene biomarker panels identified COVID-19 disease with 85.1-86.5% accuracy when benchmarked using an independent test set. SARS-CoV-2 infection has a distinct biosignature that differs between NP swabs and WB and can be leveraged for COVID-19 diagnosis.