Yamamoto, Y. — Page 4 | Search bioRxiv

bioRxiv2019

Effects of a rifampicin pre-treatment on linezolid pharmacokinetics

Linezolid is an oxazolidinone antibiotic that effectively treats methicillin-resistant Staphylococcus aureus (MRSA) and vancomycin-resistant Enterococci (VRE). Since rifampicin induces other antibiotic effects, it is combined with linezolid in therapeutic regimes. However, linezolid blood concentrations are reduced by this combination, which increases the risk of the emergence of antibiotic-resistant bacteria. We herein demonstrated that the combination of linezolid with rifampicin inhibited its absorption and promoted its elimination, but not through microsomal enzymes. Our results indicate that the combination of linezolid with rifampicin reduces linezolid blood concentrations via metabolic enzymes.

molecular biology↗

bioRxiv2019

Automated acquisition of knowledge beyond pathologists

Deep learning algorithms have been successfully used in medical image classification and cancer detection. In the next stage, the technology of acquiring explainable knowledge from medical images is highly desired. Herein, fully automated acquisition of explainable features from annotation-free histopathological images is achieved via revealing statistical distortions in datasets by introducing the way of pathologists examination into a set of deep neural networks. As validation, we compared the prediction accuracy of prostate cancer recurrence using our algorithm-generated features with that of diagnosis by an expert pathologist using established criteria on 13,188 whole-mount pathology images. Our method found not only the findings established by humans but also features that have not been recognized so far, and showed higher accuracy than human in prognostic prediction. This study provides a new field to the deep learning approach as a novel tool for discovering uncharted knowledge, leading to effective treatments and drug discovery.

bioinformatics↗