Comparative Analysis of miRNA and EMT Markers in Metastatic Colorectal Cancer.

Colorectal cancer (CRC) is the fourth most commonly diagnosed malignant condition in the world. Micro RNAs (miRNAs) as well as epithelial to mesenchymal transition (EMT) play an important role in the pathogenesis of CRC. We performed a comparative analysis of the expression of selected miRNA genes and EMT markers in bioptic samples from patients (n = 45) with primary CRC or metastatic (m)CRC to the regional lymph node using reverse transcription-quantitative PCR and IHC staining. Results: Out of all miRNA analyzed, the miR-17 expression was most significantly different and associated with lower risk of CRC spread to the lymph node. In addition, significant relationships were found between the tumor side localization and several miRNAs expressions (miR-9, miR-29b, miR-19a, miR-19b, miR-21, miR-106a, miR-20a and miR-17). In addition, of the examined EMT markers, only VEGFA expression correlated with tumor progression (tumor grade G2). In the examined set of patient samples and their matched healthy tissue, several specific molecular markers (miRNAs associated with EMT and tumor progression) were identified with a promising prognostic potential. Their further examination in larger patient cohorts is planned to validate the present data.

Image recognition based on deep learning in Haemonchus contortus motility assays.

Poor efficacy of some anthelmintics and rising concerns about the widespread drug resistance have highlighted the need for new drug discovery. The parasitic nematode Haemonchus contortus is an important model organism widely used for studies of drug resistance and drug screening with the current gold standard being the motility assay. We applied a deep learning approach Mask R-CNN for analysing motility videos containing varying rates of motile worms and compared it to other commonly used algorithms with different levels of complexity, namely the Wiggle Index and the Wide Field-of-View Nematode Tracking Platform. Mask R-CNN consistently outperformed the other algorithms in terms of the detection of worms as well as the precision of motility forecasts, having a mean absolute percentage error of 7.6% and a mean absolute error of 5.6% for the detection and motility forecasts, respectively. Using Mask R-CNN for motility assays confirmed the common problem with algorithms that use non-maximum suppression in detecting overlapping objects, which negatively impacts the overall precision. The use of intersect over union as a measure of the classification of motile / non-motile instances had an overall accuracy of 89%, indicating that it is a viable alternative to previously used methods based on movement characteristics, such as body bends. In comparison to the existing methods evaluated here, Mask R-CNN performed better and we anticipate that this method will broaden the number of possible approaches to video analysis of worm motility.