Combined segmentation and classification-based approach to automated analysis of biomedical signals obtained from calcium imaging.

Automated screening systems in conjunction with machine learning-based methods are becoming an essential part of the healthcare systems for assisting in disease diagnosis. Moreover, manually annotating data and hand-crafting features for training purposes are impractical and time-consuming. We propose a segmentation and classification-based approach for assembling an automated screening system for the analysis of calcium imaging. The method was developed and verified using the effects of disease IgGs (from Amyotrophic Lateral Sclerosis patients) on calcium (Ca2+) homeostasis. From 33 imaging videos we analyzed, 21 belonged to the disease and 12 to the control experimental groups. The method consists of three main steps: projection, segmentation, and classification. The entire Ca2+ time-lapse image recordings (videos) were projected into a single image using different projection methods. Segmentation was performed by using a multi-level thresholding (MLT) step and the Regions of Interest (ROIs) that encompassed cell somas were detected. A mean value of the pixels within these boundaries was collected at each time point to obtain the Ca2+ traces (time-series). Finally, a new matrix called feature image was generated from those traces and used for assessing the classification accuracy of various classifiers (control vs. disease). The mean value of the segmentation F-score for all the data was above 0.80 throughout the tested threshold levels for all projection methods, namely maximum intensity, standard deviation, and standard deviation with linear scaling projection. Although the classification accuracy reached up to 90.14%, interestingly, we observed that achieving better scores in segmentation results did not necessarily correspond to an increase in classification performance. Our method takes the advantage of the multi-level thresholding and of a classification procedure based on the feature images, thus it does not have to rely on hand-crafted training parameters of each event. It thus provides a semi-autonomous tool for assessing segmentation parameters which allows for the best classification accuracy.

Two phases of macrophages: Inducing maturation and death of oligodendrocytes in vitro co-culture.

BACKGROUND: The plasticity of macrophages in the immune response is a dynamic situation dependent on external stimuli. The activation of macrophages both has beneficial and detrimental effects on mature oligodendrocytes (OLs) and myelin. The activation towards inflammatory macrophages has a critical role in the immune-mediated oligodendrocytes death in multiple sclerosis (MS) lesions. NEW METHOD: We established an in vitro co-culture method to study the function of macrophages in the survival and maturation of OLs. RESULTS: We revealed that M1 macrophages decreased the number of mature OLs and phagocytosed the myelin. Interestingly, non-activated as well as M2 macrophages contributed to an increase in the number of mature OLs in our in vitro co-culture platform. COMPARISON WITH EXISTING METHODS: We added an antibody against an OL surface antigen in our in vitro co-cultures. The antibody presents the OLs to the macrophages enabling the investigation of direct interactions between macrophages and OLs. CONCLUSION: Our co-culture system is a feasible method for the investigation of the direct cell-to-cell interactions between OLs and macrophages. We utilized it to show that M2 and non-activated macrophages may be employed to enhance remyelination.

Multiple Sclerosis Biomarker Candidates Revealed by Cell-Type-Specific Interactome Analysis.

Multiple sclerosis (MS) is a demyelinating disorder that affects multiple regions of the central nervous system such as the brain, spinal cord, and optic nerves. Susceptibility to MS, as well as disease progression rates, displays marked patient-to-patient variability. To date, biomarkers that forecast differences in clinical phenotypes and outcomes have been limited. In this context, cell-type-specific interactome analyses offer important prospects and hope for novel diagnostics and therapeutics. We report here an original study using bioinformatic analysis of MS data sets that revealed interaction profiles as well as specific hub proteins in white matter (WM) and gray matter (GM) that appear critical for disease mechanisms. First, cell-type-specific interactome analyses suggested that while interactions within the WM were focused on oligodendrocytes, interactions within the GM were mostly neuron centric. Second, hub proteins such as APP, EGLN3, PTEN, and LRRK2 were identified to be differentially regulated in MS data sets. Lastly, a comparison of the brain and peripheral blood samples identified biomarker candidates such as NRGN, CRTC1, CDC42, and IFITM3 to be differentially expressed in different types of MS. These findings offer a unique cell-type-specific cell-to-cell interaction network in MS and identify potential biomarkers by comparative analysis of the brain and the blood transcriptomics. From a study design and methodology perspective, we suggest that the cell-type-specific interactome analysis is an important systems science frontier that might offer new insights on other neurodegenerative and brain disorders as well.

Motoneuron expression profiling identifies an association between an axonal splice variant of HDGF-related protein 3 and peripheral myelination.

Disorders that disrupt myelin formation during development or in adulthood, such as multiple sclerosis and peripheral neuropathies, lead to severe pathologies, illustrating myelin's crucial role in normal neural functioning. However, although our understanding of glial biology is increasing, the signals that emanate from axons and regulate myelination remain largely unknown. To identify the core components of the myelination process, here we adopted a microarray analysis approach combined with laser-capture microdissection of spinal motoneurons during the myelinogenic phase of development. We identified neuronal genes whose expression was enriched during myelination and further investigated hepatoma-derived growth factor-related protein 3 (HRP3 or HDGFRP3). HRP3 was strongly expressed in the white matter fiber tracts of the peripheral (PNS) and central (CNS) nervous systems during myelination and remyelination in a cuprizone-induced demyelination model. The dynamic localization of HPR3 between axons and nuclei during myelination was consistent with its axonal localization during neuritogenesis. To study this phenomenon, we identified two splice variants encoded by the HRP3 gene: the canonical isoform HRP3-I and a newly recognized isoform, HRP3-II. HRP3-I remained solely in the nucleus, whereas HRP3-II displayed distinct axonal localization both before and during myelination. Interestingly, HRP3-II remained in the nuclei of unmyelinated neurons and glial cells, suggesting the existence of a molecular machinery that transfers it to and retains it in the axons of neurons fated for myelination. Overexpression of HRP3-II, but not of HRP3-I, increased Schwann cell numbers and myelination in PNS neuron-glia co-cultures. However, HRP3-II overexpression in CNS co-cultures did not alter myelination.

A multi-spectral myelin annotation tool for machine learning based myelin quantification.

Myelin is an essential component of the nervous system and myelin damage causes demyelination diseases. Myelin is a sheet of oligodendrocyte membrane wrapped around the neuronal axon. In the fluorescent images, experts manually identify myelin by co-localization of oligodendrocyte and axonal membranes that fit certain shape and size criteria. Because myelin wriggles along x-y-z axes, machine learning is ideal for its segmentation. However, machine-learning methods, especially convolutional neural networks (CNNs), require a high number of annotated images, which necessitate expert labor. To facilitate myelin annotation, we developed a workflow and software for myelin ground truth extraction from multi-spectral fluorescent images. Additionally, to the best of our knowledge, for the first time, a set of annotated myelin ground truths for machine learning applications were shared with the community.

Particular phosphorylation of PI3K/Akt on Thr308 via PDK-1 and PTEN mediates melatonin's neuroprotective activity after focal cerebral ischemia in mice.

Apart from its potent antioxidant property, recent studies have revealed that melatonin promotes PI3K/Akt phosphorylation following focal cerebral ischemia (FCI) in mice. However, it is not clear (i) whether increased PI3K/Akt phosphorylation is a concomitant event or it directly contributes to melatonin's neuroprotective effect, and (ii) how melatonin regulates PI3K/Akt signaling pathway after FCI. In this study, we showed that Akt was intensively phosphorylated at the Thr308 activation loop as compared with Ser473 by melatonin after FCI. Melatonin treatment reduced infarct volume, which was reversed by PI3K/Akt inhibition. However, PI3K/Akt inhibition did not inhibit melatonin's positive effect on brain swelling and IgG extravasation. Additionally, phosphorylation of mTOR, PTEN, AMPKα, PDK1 and RSK1 were increased, while phosphorylation of 4E-BP1, GSK-3α/ß, S6 ribosomal protein were decreased in melatonin treated animals. In addition, melatonin decreased apoptosis through reduced p53 phosphorylation by the PI3K/Akt pathway. In conclusion, we demonstrated the activation profiles of PI3K/Akt signaling pathway components in the pathophysiological aspect of ischemic stroke and melatonin's neuroprotective activity. Our data suggest that Akt phosphorylation, preferably at the Thr308 site of the activation loop via PDK1 and PTEN, mediates melatonin's neuroprotective activity and increased Akt phosphorylation leads to reduced apoptosis.