“
“One common and challenging problem faced by many bioinformatics applications, such as promoter recognition, splice site prediction, RNA gene prediction, drug discovery and protein classification, is the imbalance

of the available datasets. In most of these applications, the positive data examples are largely outnumbered by the negative data examples, which often leads to the development of sub-optimal prediction models having high negative recognition rate (Specificity = SP) and low positive recognition rate (Sensitivity AZD9291 SE). When class imbalance learning methods are applied, usually, the SE is increased at the expense of reducing some amount of the SP. In this paper, we point out that in these data-imbalanced bioinformatics applications, the goal of applying class imbalance learning methods would be to increase the SE as high as possible by keeping the reduction of SP as low as possible. We explain that the existing performance measures used in class imbalance learning can still produce sub-optimal models with respect to this classification this website goal. In order to overcome these problems, we introduce a new performance measure called Adjusted Geometric-mean

(AGm). The experimental results obtained on ten real-world imbalanced bioinformatics datasets demonstrates that the AGm metric can achieve a lower rate of reduction of SP than the existing performance metrics, when increasing the SE through class imbalance learning methods. This characteristic of AGm metric makes it more suitable for achieving the proposed classification LCL161 goal in imbalanced bioinformatics datasets learning.”
“Background: Neocortical lesions (NLs) are an important pathological component of multiple sclerosis (MS), but their visualization by magnetic resonance imaging (MRI) remains challenging. Objectives: We aimed at assessing the sensitivity of multi echo gradient echo (ME-GRE) T-2*-weighted MRI at 7.0 Tesla in depicting NLs compared to myelin and iron staining. Methods: Samples from two MS patients were imaged post mortem using a whole body 7T MRI scanner with a 24-channel receive-only array. Isotropic 200 micron resolution images with varying T-2* weighting were reconstructed from the ME-GRE data and converted

into R-2* maps. Immunohistochemical staining for myelin (proteolipid protein, PLP) and diaminobenzidine-enhanced Turnbull blue staining for iron were performed. Results: Prospective and retrospective sensitivities of MRI for the detection of NLs were 48% and 67% respectively. We observed MRI maps detecting only a small portion of 20 subpial NLs extending over large cortical areas on PLP stainings. No MRI signal changes suggestive of iron accumulation in NLs were observed. Conversely, R-2* maps indicated iron loss in NLs, which was confirmed by histological quantification. Conclusions: High-resolution post mortem imaging using R-2* and magnitude maps permits detection of focal NLs. However, disclosing extensive subpial demyelination with MRI remains challenging.