Abstract

Parkinson’s Disease (PD) is a chronic and progressive neurological disorder that results in rigidity, tremors and postural instability. There is no definite medical test to diagnose PD and diagnosis is mostly a clinical exercise. Although guidelines exist, about 10-30% of the patients are wrongly diagnosed with PD. Hence, there is a need for an accurate, unbiased and fast method for diagnosis. In this study, we propose LPGNet, a fast and accurate method to diagnose PD from gait. LPGNet uses Linear Prediction Residuals (LPR) to extract discriminating patterns from gait recordings and then uses a 1D convolution neural network with depth-wise separable convolutions to perform diagnosis. LPGNet achieves an AUC of 0.91 with a 21 times speedup and about 99% lesser parameters in the model compared to the state of the art. We also undertake an analysis of various cross-validation strategies used in literature in PD diagnosis from gait and find that most methods are affected by some form of data leakage between various folds which leads to unnecessarily large models and inflated performance due to overfitting. The analysis clears the path for future works in correctly evaluating their methods.

Abstract

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) manifests a broad spectrum of clinical presentations, varying in severity from asymptomatic to mortality. As the viral infection spread, it evolved and developed into many variants of concern. Understanding the impact of mutations in the SARS-CoV-2 genome on the clinical phenotype and associated co-morbidities is important for treatment and preventionas the pandemic progresses. Based on the mild, moderate, and severe clinical phenotypes, we analyzed the possible association between both, the clinical sub-phenotypes and genomic mutations with respect to the severity and outcome of the patients. We found a significant association between the requirement of respiratory support and co-morbidities. We also identified six SARS-CoV-2 genome mutations that were significantly correlated with severity and mortality in our cohort. We examined structural alterations at the RNA and protein levels as a result of three of these mutations: A26194T, T28854T, and C25611A, present in the Orf3a and N protein. The RNA secondary structure change due to the above mutations can be one of the modulators of the disease outcome. Our findings highlight the importance of integrative analysis in which clinical and genetic components of the disease are co-analyzed. In combination with genomic surveillance, the clinical outcome-associated mutations could help identify individuals for priority medical support.

Abstract

Understanding the pathogenesis of SARS-CoV-2 is essential for developing effective treatment strategies. Viruses hijack the host metabolism to redirect the resources for their replication and survival. The influence of SARSCoV-2 on host metabolism is yet to be fully understood. In this study, we analyzed the transcriptomic data obtained from different human respiratory cell lines and patient samples (nasopharyngeal swab, peripheral blood mononuclear cells, lung biopsy, bronchoalveolar lavage fluid) to understand metabolic alterations in response to SARS-CoV-2 infection. We explored the expression pattern of metabolic genes in the comprehensive genomescale network model of human metabolism, Recon3D, to extract key metabolic genes, pathways, and reporter metabolites under each SARS-CoV-2-infected condition. A SARS-CoV-2 core metabolic interactome was constructed for network-based drug repurposing. Our analysis revealed the host-dependent dysregulation of glycolysis, mitochondrial metabolism, amino acid metabolism, nucleotide metabolism, glutathione metabolism, polyamine synthesis, and lipid metabolism. We observed different pro- and antiviral metabolic changes and generated hypotheses on how the host metabolism can be targeted for reducing viral titers and immunomodulation. These findings warrant further exploration with more samples and in vitro studies to test predictions.

Abstract

Protein-ligand complex structures have been utilised to design benchmark machine learning methods that perform important tasks related to drug design such as receptor binding site detection, small molecule docking and binding affinity prediction. However, these methods are usually trained on only ligand bound (or holo) conformations of the protein and therefore are not guaranteed to perform well when the protein structure is in its native unbound conformation (or apo), which is usually the conformation available for a newly identified receptor. A primary reason for this is that the local structure of the binding site usually changes upon ligand binding. To facilitate solutions for this problem, we propose a dataset called APObind that aims to provide apo conformations of proteins present in the PDBbind dataset, a popular dataset used in drug design. Furthermore, we explore the performance of methods specific to three use cases on this dataset, through which, the importance of validating them on the APObind dataset is demonstrated.

Abstract

Images in the medical domain are fundamentally different from the general domain images. Consequently, it is infeasible to directly employ general domain Visual Question Answering (VQA) models for the medical domain. Additionally, medical image annotation is a costly and time-consuming process. To overcome these limitations, we propose a solution inspired by self-supervised pretraining of Transformer-style architectures for NLP, Vision, and Language tasks. Our method involves learning richer medical image and text semantic representations using Masked Vision-Language Modeling as the pretext task on a large medical image+caption dataset. The proposed solution achieves new state-of-the-art performance on two VQA datasets for radiology images – VQA-Med 2019 and VQA-RAD, outperforming even the ensemble models of previous best solutions. Moreover, our solution provides attention maps which help in model interpretability.

Abstract

We present CCO-VOXEL: the very first chance-constrained optimization (CCO) algorithm that can compute trajectory plans with probabilistic safety guarantees in real-time directly on the voxel-grid representation of the world. CCO-VOXEL maps the distribution over the distance to the closest obstacle to a distribution over collision-constraint violation and computes an optimal trajectory that minimizes the violation probability. Importantly, unlike existing works, we never assume the nature of the sensor uncertainty or the probability distribution of the resulting collision-constraint violations. We leverage the notion of Hilbert Space embedding of distributions and Maximum Mean Discrepancy (MMD) to compute a tractable surrogate for the original chance-constrained optimization problem and employ a combination of A* based graph-search and Cross-Entropy Method for obtaining its minimum. We show tangible performance gain in terms of collision avoidance and trajectory smoothness as a consequence of our probabilistic formulation vis a vis state-of-the-art planning methods that do not account for such nonparametric noise. Finally, we also show how a combination of low-dimensional feature embedding and pre-caching of Kernel Matrices of MMD allows us to achieve real-time performance in simulations as well as in implementations on on-board commodity hardware that controls the quadrotor flight

Abstract

We embark on a hitherto unreported problem of an autonomous robot (self-driving car) navigating in dynamic scenes in a manner that reduces its localization error and eventual cumulative drift or Absolute Trajectory Error, which is pronounced in such dynamic scenes. With the hugely popular Velodyne-16 3D LIDAR as the main sensing modality, and the accurate LIDAR-based Localization and Mapping algorithm, LOAM, as the state estimation framework, we show that in the absence of a navigation policy, drift rapidly accumulates in the presence of moving objects. To overcome this, we learn actions that lead to drift-minimized navigation through a suitable set of reward and penalty functions. We use Proximal Policy Optimization, a class of Deep Reinforcement Learning methods, to learn the actions that result in drift-minimized trajectories. We show by extensive comparisons on a variety of synthetic, yet photo-realistic scenes made available through the CARLA Simulator the superior performance of the proposed framework vis-a-vis methods that do not adopt such policies.

Abstract

Synaptic integration is a prominent aspect of neuronal information processing. The detailed mechanisms that modulate synaptic inputs determine the computational properties of any given neuron. We study a simple model for the summation of excitatory inputs from synapses and illustrate its use by characterizing some functional properties of postsynaptic neurons. In this regard, we study the response of postsynaptic neurons as defined by the model to two well known noise driven processes: stochastic and coherence resonance. The model requires a small number of parameters and is especially useful to isolate the role of integration mechanisms that rely on summation of inputs with little dendritic processing.

Abstract

Surface codes are quantum error correcting codes normally defined on 2D arrays of qubits. In this paper, we introduce a surface code design based on the fact that the severity of bit flip and phase flip errors in the physical quantum systems is asymmetric. For our proposed surface code design for asymmetric error channels, we present pseudo-threshold and threshold values in the presence of various degrees of asymmetry of Pauli Xˆ, Yˆ , and Zˆ errors in a depolarization channel. We show that, compared to symmetric surface codes, our asymmetric surface codes can provide almost double the pseudo-threshold rates while requiring less than half the number of physical qubits in the presence of increasing asymmetry in the error channel. We also demonstrate that as the asymmetry of the surface code increases, the advantage in the pseudo-threshold rates begins to saturate for any degree of asymmetry in the channel. Keywords: Surface Codes, Quantum Error Correction, Quantum Computing

Abstract

In this paper, we develop a Kinetic Monte Carlo (KMC) based model to simulate the atomistic growth behavior of metallic nanoparticle in the solution of its ions and understand the growth pattern. KMC is used as it can model the growth of nanoparticle to the timescale comparable with that actual experiments. Energy minimas where metal atom can adsorb or surface diffuse have been found using Shrake–Rupley algorithm and conjugate gradient energy minimization algorithm. The rate of adsorption, desorption, and surface diffusion was artificially accelerated, and decelerated to observe different shapes. We demonstrate the model by a case study on growth of gold nanoparticles and find that shapes like the truncated octahedron, cuboctahedron, truncated cube, cube, rhombic dodecahedron, and sphere are seen to form by the model during the growth of NP. This KMC model provides a simplistic understanding of the mechanism and progression of shapes that may be seen during the growth of nanoparticle; these in turn may provide clues to synthesize NP of specific shapes.