Multi-Scale Input Strategies for Medulloblastoma Tumor Classification using Deep Transfer Learning

Medulloblastoma (MB) is a primary central nervous system tumor and the most common malignant brain cancer among children. Neuropathologists perform microscopic inspection of histopathological tissue slides under a microscope to assess the severity of the tumor. This is a timeconsuming task and often infused with observer variability. Recently, pre-trained convolutional neural networks (CNN) have shown promising results for MB subtype classification. Typically, high-resolution images are divided into smaller tiles for classification, while the size of the tiles has not been systematically evaluated. We study the impact of tile size and input strategy and classify the two major histopathological subtypes-Classic and Desmoplastic/Nodular. To this end, we use recently proposed EfficientNets and evaluate tiles with increasing size combined with various downsampling scales. Our results demonstrate using large input tiles pixels followed by intermediate downsampling and patch cropping significantly improves MB classification performance. Our top-performing method achieves the AUC-ROC value of 90.90% compared to 84.53% using the previous approach with smaller input tiles.

Machine learning for detection of stenoses and aneurysms: application in a physiologically realistic virtual patient database

This study presents an application of machine learning (ML) methods for detecting the presence of stenoses and aneurysms in the human arterial system. Four major forms of arterial disease-carotid artery stenosis (CAS), subclavian artery stenosis (SAS), peripheral arterial disease (PAD), and abdominal aortic aneurysms (AAA)-are considered. The ML methods are trained and tested on a physiologically realistic virtual patient database (VPD) containing 28,868 healthy subjects, adapted from the authors previous work and augmented to include disease. It is found that the tree-based methods of Random Forest and Gradient Boosting outperform other approaches. The performance of ML methods is quantified through the [Formula: see text] score and computation of sensitivities and specificities. When using six haemodynamic measurements (pressure in the common carotid, brachial, and radial arteries; and flow-rate in the common carotid, brachial, and femoral arteries), it is found that maximum [Formula: see text] scores larger than 0.9 are achieved for CAS and PAD, larger than 0.85 for SAS, and larger than 0.98 for both low- and high-severity AAAs. Corresponding sensitivities and specificities are larger than 90% for CAS and PAD, larger than 85% for SAS, and larger than 98% for both low- and high-severity AAAs. When reducing the number of measurements, performance is degraded by less than 5% when three measurements are used, and less than 10% when only two measurements are used for classification. For AAA, it is shown that [Formula: see text] scores larger than 0.85 and corresponding sensitivities and specificities larger than 85% are achievable when using only a single measurement. The results are encouraging to pursue AAA monitoring and screening through wearable devices which can reliably measure pressure or flow-rates.

Active participation of membrane lipids in inhibition of multidrug transporter P-glycoprotein

P-glycoprotein (Pgp) is a major efflux pump in humans, overexpressed in a variety of cancers and associated with the development of multi-drug resistance. Allosteric modulation by various ligands (e.g., transport substrates, inhibitors, and ATP) has been biochemically shown to directly influence structural dynamics, and thereby, the function of Pgp. However, the molecular details of such effects, particularly with respect to the role and involvement of the surrounding lipids, are not well established. Here, we employ all-atom molecular dynamics (MD) simulations to study the conformational landscape of Pgp in the presence of a high-affinity, third-generation inhibitor, tariquidar, in comparison to the nucleotide-free (APO) and the ATP-bound states, in order to characterize the mechanical effects of the inhibitor that might be of relevance to its blocking mechanism of Pgp. Simulations in a multi-component lipid bilayer show a dynamic equilibrium between open(er) and more closed inward-facing (IF) conformations in the APO state, with binding of ATP shifting the equilibrium towards conformations more prone to ATP hydrolysis and subsequent events in the transport cycle. In the presence of the inhibitor bound to the drug-binding pocket within the transmembrane domain (TMD), Pgp samples more open IF conformations, and the nucleotide binding domains (NBDs) become highly dynamic. Interestingly, and reproduced in multiple independent simulations, the inhibitor is observed to facilitate recruitment of lipid molecules into the Pgp lumen through the two proposed drug-entry portals, where the lipid head groups from the cytoplasmic leaflet penetrate into and, in some cases, translocate inside the TMD, while the lipid tails remain extended into the bulk lipid environment. These "wedge" lipids likely enhance the inhibitor-induced conformational restriction of the TMD leading to the differential modulation of coupling pathways observed with the NBDs downstream. We suggest a novel inhibitory mechanism for tariquidar, and potentially for related third-generation Pgp inhibitors, where lipids are seen to enhance the inhibitory role in the catalytic cycle of membrane transporters.

Glutamate transporters have a chloride channel with two hydrophobic gates

Glutamate is the most abundant excitatory neurotransmitter in the central nervous system, and its precise control is vital to maintain normal brain function and to prevent excitotoxicity¹. The removal of extracellular glutamate is achieved by plasma-membrane-bound transporters, which couple glutamate transport to sodium, potassium and pH gradients using an elevator mechanism^2-5. Glutamate transporters also conduct chloride ions by means of a channel-like process that is thermodynamically uncoupled from transport^6-8. However, the molecular mechanisms that enable these dual-function transporters to carry out two seemingly contradictory roles are unknown. Here we report the cryo-electron microscopy structure of a glutamate transporter homologue in an open-channel state, which reveals an aqueous cavity that is formed during the glutamate transport cycle. The functional properties of this cavity, combined with molecular dynamics simulations, reveal it to be an aqueous-accessible chloride permeation pathway that is gated by two hydrophobic regions and is conserved across mammalian and archaeal glutamate transporters. Our findings provide insight into the mechanism by which glutamate transporters support their dual function, and add information that will assist in mapping the complete transport cycle shared by the solute carrier 1A transporter family.

Evaluation and Selection of Video Stabilization Techniques for UAV-Based Active Infrared Thermography Application

Unmanned Aerial Vehicles (UAVs) that can fly around an aircraft carrying several sensors, e.g., thermal and optical cameras, to inspect the parts of interest without removing them can have significant impact in reducing inspection time and cost. One of the main challenges in the UAV based active InfraRed Thermography (IRT) inspection is the UAV’s unexpected motions. Since active thermography is mainly concerned with the analysis of thermal sequences, unexpected motions can disturb the thermal profiling and cause data misinterpretation especially for providing an automated process pipeline of such inspections. Additionally, in the scenarios where post-analysis is intended to be applied by an inspector, the UAV’s unexpected motions can increase the risk of human error, data misinterpretation, and incorrect characterization of possible defects. Therefore, post-processing is required to minimize/eliminate such undesired motions using digital video stabilization techniques. There are number of video stabilization algorithms that are readily available; however, selecting the best suited one is also challenging. Therefore, this paper evaluates video stabilization algorithms to minimize/mitigate undesired UAV motion and proposes a simple method to find the best suited stabilization algorithm as a fundamental first step towards a fully operational UAV-IRT inspection system.

Sensitivity and Specificity of Lateral Flow Antigen Test Kits for COVID-19 in Asymptomatic Population of Quarantine Centre of Province 3

Background Nearly after 6 months of the spread of Corona Virus Disease 19, along with the world Nepal is still trying to control the spread and prevent general population from acquiring it. With limited resources in manpower, technology and evidence it has been a difficult battle. But with time and more understanding of the virus new technology to detect the virus are coming up. It is a major breakthrough in the diagnostic field as this helps us in not only detecting the virus but also helps us to mobilize our human resources. This comes in a time where the cases are increasing at an alarming rate. Although numbers of Polymerase Chain Reaction testing have increased but due to the time consuming and the cost wise, we need a faster and equally reliable alternative. Antigen test approved by different countries can be used for point of care, screening and surveillance depending upon the requirements after calculating its sensitivity, specificity and accuracy. Objective To find out sensitivity and specificity of the Antigen test kit for COVID-19. Method Antigen tests were compared with Reverse Transcription Polymerase Chain Reaction as a reference standard in calculated sample size of 113 subjects in a high risk population. Both Reverse Transcription Polymerase Chain Reaction and antigen test were performed in a same subject with in maximum of 2 days' interval. Convenience sampling technique was used to select the subjects. Ethical approval was taken from Nepal Health Research Council before data collection. Study was done from August to September 2020 from Quarantine center of Province 3. Result There were total of 113 test carried out, among those 47 were positive and 66 were negative in Reverse Transcription Polymerase Chain Reaction. After preparing two by two table, Sensitivity and specificity of the tested was calculated which came out to be 85% and 100% respectively, with accuracy of 93.80%. Conclusion Even though the sensitivity and specificity came to be higher, this test should be interpreted cautiously depending upon the prevalence of Corona Virus Disease 19 in that particular community and the clinical and epidemiological context of the person who has been tested. When in doubt by clinical correlation should be confirmed with Reverse Transcription Polymerase Chain Reaction.

Confronting pitfalls of AI-augmented molecular dynamics using statistical physics

Artificial intelligence (AI)-based approaches have had indubitable impact across the sciences through the ability to extract relevant information from raw data. Recently, AI has also found use in enhancing the efficiency of molecular simulations, wherein AI derived slow modes are used to accelerate the simulation in targeted ways. However, while typical fields where AI is used are characterized by a plethora of data, molecular simulations, per construction, suffer from limited sampling and thus limited data. As such, the use of AI in molecular simulations can suffer from a dangerous situation where the AI-optimization could get stuck in spurious regimes, leading to incorrect characterization of the reaction coordinate (RC) for the problem at hand. When such an incorrect RC is then used to perform additional simulations, one could start to deviate progressively from the ground truth. To deal with this problem of spurious AI-solutions, here, we report a novel and automated algorithm using ideas from statistical mechanics. It is based on the notion that a more reliable AI-solution will be one that maximizes the timescale separation between slow and fast processes. To learn this timescale separation even from limited data, we use a maximum caliber-based framework. We show the applicability of this automatic protocol for three classic benchmark problems, namely, the conformational dynamics of a model peptide, ligand-unbinding from a protein, and folding/unfolding energy landscape of the C-terminal domain of protein G. We believe that our work will lead to increased and robust use of trustworthy AI in molecular simulations of complex systems.

An Investigation of Rotary Drone HERM Line Spectrum under Manoeuvering Conditions

Detecting and identifying drones is of great interest due to the proliferation of highly manoeuverable drones with on-board sensors of increasing sensing capabilities. In this paper, we investigate the use of radars for tackling this problem. In particular, we focus on the problem of detecting rotary drones and distinguishing between single-propeller and multi-propeller drones using a micro-Doppler analysis. Two different radars were used, an ultra wideband (UWB) continuous wave (CW) C-band radar and an automotive frequency modulated continuous wave (FMCW) W-band radar, to collect micro-Doppler signatures of the drones. By taking a closer look at HElicopter Rotor Modulation (HERM) lines, the spool and chopping lines are identified for the first time in the context of drones to determine the number of propeller blades. Furthermore, a new multi-frequency analysis method using HERM lines is developed, which allows the detection of propeller rotation rates (spool and chopping frequencies) of single and multi-propeller drones. Therefore, the presented method is a promising technique to aid in the classification of drones.

Membrane surface recognition by the ASAP1 PH domain and consequences for interactions with the small GTPase Arf1

Adenosine diphosphate-ribosylation factor (Arf) guanosine triphosphatase-activating proteins (GAPs) are enzymes that need to bind to membranes to catalyze the hydrolysis of guanosine triphosphate (GTP) bound to the small GTP-binding protein Arf. Binding of the pleckstrin homology (PH) domain of the ArfGAP With SH3 domain, ankyrin repeat and PH domain 1 (ASAP1) to membranes containing phosphatidylinositol 4,5-bisphosphate [PI(4,5)P₂] is key for maximum GTP hydrolysis but not fully understood. By combining nuclear magnetic resonance, neutron reflectometry, and molecular dynamics simulation, we show that binding of multiple PI(4,5)P₂ molecules to the ASAP1 PH domain (i) triggers a functionally relevant allosteric conformational switch and (ii) maintains the PH domain in a well-defined orientation, allowing critical contacts with an Arf1 mimic to occur. Our model provides a framework to understand how binding of the ASAP1 PH domain to PI(4,5)P₂ at the membrane may play a role in the regulation of ASAP1.