Integration of graph network with kernel SVM and logistic regression for identification of biomarkers in SCA12 and its diagnosis.

Spinocerebellar ataxia type 12 is a hereditary and neurodegenerative illness commonly found in India. However, there is no established noninvasive automatic diagnostic system for its diagnosis and identification of imaging biomarkers. This work proposes a novel four-phase machine learning-based diagnostic framework to find spinocerebellar ataxia type 12 disease-specific atrophic-brain regions and distinguish spinocerebellar ataxia type 12 from healthy using a real structural magnetic resonance imaging dataset. Firstly, each brain region is represented in terms of statistics of coefficients obtained using 3D-discrete wavelet transform. Secondly, a set of relevant regions are selected using a graph network-based method. Thirdly, a kernel support vector machine is used to capture nonlinear relationships among the voxels of a brain region. Finally, the linear relationship among the brain regions is captured to build a decision model to distinguish spinocerebellar ataxia type 12 from healthy by using the regularized logistic regression method. A classification accuracy of 95% and a harmonic mean of precision and recall, i.e. F1-score of 94.92%, is achieved. The proposed framework provides relevant regions responsible for the atrophy. The importance of each region is captured using Shapley Additive exPlanations values. We also performed a statistical analysis to find volumetric changes in spinocerebellar ataxia type 12 group compared to healthy. The promising result of the proposed framework shows that clinicians can use it for early and timely diagnosis of spinocerebellar ataxia type 12.

Metal-Organic Framework-Supported Mono Bipyridyl-Iron Hydroxyl Catalyst for Selective Benzene Hydroxylation into Phenol.

Direct hydroxylation of benzene to phenol is more appealing in the industry for the economic and environmentally friendly phenol synthesis than the conventional cumene process. We have developed a UiO-metal-organic framework (MOF)-supported mono bipyridyl-Iron(II) hydroxyl catalyst [bpy-UiO-Fe(OH)2] for the selective benzene hydroxylation into phenol using H2O2 as the oxidant. The heterogeneous bpy-UiO-Fe(OH)2 catalyst showed high activity and remarkable phenol selectivity of 99%, giving the phenol mass-specific activity up to 1261 mmolPhOHgFe-1 h-1 at 60 °C. Bpy-UiO-Fe(OH)2 is significantly more active and selective than its homogeneous counterpart, bipyridine-Fe(OH)2. This enhanced catalytic activity of bpy-UiO-Fe(OH)2 over its homogeneous control is attributed to the active site isolation of the bpy-Fe(OH)2 moiety by the solid MOF that prevents intermolecular decomposition. Moreover, the exceptional selectivity of bpy-UiO-Fe(OH)2 in benzene to phenol conversion is originated via shape-selective catalysis, where the confined reaction space within the porous UiO-MOF prevents the formation of larger overoxidized products such as hydroquinone or benzoquinone, leading to the formation of only smaller-sized phenol after monohydroxylation of benzene. Spectroscopic and controlled experiments and theoretical calculations elucidated the reaction pathway, in which the in situ generated •OH radical mediated by bpy-UiO-FeII(OH)2 is the key species for benzene hydroxylation. This work underscores the significance of MOF-supported earth-abundant metal catalysts for sustainable production of fine chemicals.

Selective Reduction of Nitro Compounds by Organosilanes Catalyzed by a Zirconium Metal-Organic Framework Supported Salicylaldimine-Cobalt(II) Complex.

Reducing nitro compounds to amines is a fundamental reaction in producing valuable chemicals in industry. Herein, the synthesis and characterization of a zirconium metal-organic framework-supported salicylaldimine-cobalt(II) chloride (salim-UiO-CoCl) and its application in catalytic reduction of nitro compounds are reported. Salim-UiO-Co displayed excellent catalytic activity in chemoselective reduction of aromatic and aliphatic nitro compounds to the corresponding amines in the presence of phenylsilane as a reducing agent under mild reaction conditions. Salim-UiO-Co catalyzed nitro reduction had a broad substrate scope with excellent tolerance to diverse functional groups, including easily reducible ones such as aldehyde, keto, nitrile, and alkene. Salim-UiO-Co MOF catalyst could be recycled and reused at least 14 times without noticeable losing activity and selectivity. Density functional theory (DFT) studies along with spectroscopic analysis were employed to get into a comprehensive investigation of the reaction mechanism. This work underscores the significance of MOF-supported single-site base-metal catalysts for the sustainable and cost-effective synthesis of chemical feedstocks and fine chemicals.

Gray Matter Atrophy in a 6-OHDA-induced Model of Parkinson's Disease.

INTRODUCTION: Magnetic resonance imaging (MRI) based brain morphometric changes in unilateral 6-hydroxydopamine (6-OHDA) induced Parkinson's disease (PD) model can be elucidated using voxel-based morphometry (VBM), study of alterations in gray matter volume and Machine Learning (ML) based analyses. METHODS: We investigated gray matter atrophy in 6-OHDA induced PD model as compared to sham control using statistical and ML based analysis. VBM and atlas-based volumetric analysis was carried out at regional level. Support vector machine (SVM)-based algorithms wherein features (volume) extracted from (a) each of the 150 brain regions (b) statistically significant features (only) and (c) volumes of each cluster identified after application of VBM (VBM_Vol) were used for training the decision model. The lesion of the 6-OHDA model was validated by estimating the net contralateral rotational behaviour by the injection of apomorphine drug and motor impairment was assessed by rotarod and open field test. RESULTS AND DISCUSSION: In PD, gray matter volume (GMV) atrophy was noted in bilateral cortical and subcortical brain regions, especially in the internal capsule, substantia nigra, midbrain, primary motor cortex and basal ganglia-thalamocortical circuits in comparison with sham control. Behavioural results revealed an impairment in motor performance. SVM analysis showed 100% classification accuracy, sensitivity and specificity at both 3 and 7 weeks using VBM_Vol. CONCLUSION: Unilateral 6-OHDA induced GMV changes in both hemispheres at 7th week may be associated with progression of the disease in the PD model. SVM based approaches provide an increased classification accuracy to elucidate GMV atrophy.

ADHD diagnosis using structural brain MRI and personal characteristic data with machine learning framework.

An essential yet challenging task is an automatic diagnosis of attention-deficit/hyperactivity disorder (ADHD) without manual intervention. The present study emphasises utilizing structural MRI and personal characteristic (PC) data for developing an automated diagnostic system for ADHD classification. Here, an age-balanced dataset of 316 ADHD and 316 Typically Developing Children (TDC) was prepared from the publicly available dataset. We extracted volumetric features from gray matter (GM) volumes from brain regions defined by Automated Anatomical Labelling (AAL3) atlas and cortical thickness-based (CT) features using the Destrieux atlas. A set of salient features were selected independently using minimum redundancy and maximum relevance (mRMR) and ensemble feature selection (EFS) methods. Decision models were trained using five well-known classifiers: K-nearest neighbours, logistic regression, linear Support Vector Machine (SVM), radial-based SVM (RBSVM), and Random Forest. The performance of the proposed system was evaluated using accuracy, recall, and specificity with ten runs of a ten-fold cross-validation scheme. We run seven experiments by considering different combinations of features. The maximum classification accuracy of 75% was obtained with CT and PC features with RBSVM and SVM with the EFS. An increase in GM volume in fifteen brain regions and loss of cortical thickness in twenty-seven brain regions were observed.

Isoreticular Metal-Organic Frameworks Confined Mononuclear Ru-Hydrides Enable Highly Efficient Shape-Selective Hydrogenolysis of Polyolefins.

Upcycling nonbiodegradable plastics such as polyolefins is paramount due to their ever-increasing demand and landfills after usage. Catalytic hydrogenolysis is highly appealing to convert polyolefins into targeted value-added products under mild reaction conditions compared with other methods, such as high-temperature incineration and pyrolysis. We have developed three isoreticular zirconium UiO-metal-organic frameworks (UiO-MOFs) node-supported ruthenium dihydrides (UiO-RuH2), which are efficient heterogeneous catalysts for hydrogenolysis of polyethylene at 200 °C, affording liquid hydrocarbons with a narrow distribution and excellent selectivity via shape-selective catalysis. UiO-66-RuH2 catalyzed hydrogenolysis of single-use low-density polyethylene (LDPE) produced a C12 centered narrow bell-shaped distribution of C8-C16 alkanes in >80% yield and 90% selectivity in the liquid phase. By tuning the pore sizes of the isoreticular UiO-RuH2 MOF catalysts, the distribution of the products could be systematically altered, affording different fuel-grade liquid hydrocarbons from LDPE in high yields. Our spectroscopic and theoretical studies and control experiments reveal that UiO-RuH2 catalysts enable highly efficient upcycling of plastic wastes under mild conditions owing to their unique combination of coordinatively unsaturated single-site Ru-active sites, uniform and tunable pores, well-defined porous structure, and superior stability. The kinetics and theoretical calculations also identify the C-C bond scission involving ß-alkyl transfer as the turnover-limiting step.

Identification of brain regions associated with working memory deficit in schizophrenia.

Background: Schizophrenia, a severe psychological disorder, shows symptoms such as hallucinations and delusions. In addition, patients with schizophrenia often exhibit a deficit in working memory which adversely impacts the attentiveness and the behavioral characteristics of a person. Although several clinical efforts have already been made to study working memory deficit in schizophrenia, in this paper, we investigate the applicability of a machine learning approach for identification of the brain regions that get affected by schizophrenia leading to the dysfunction of the working memory. Methods: We propose a novel scheme for identification of the affected brain regions from functional magnetic resonance imaging data by deploying group independent component analysis in conjunction with feature extraction based on statistical measures, followed by sequential forward feature selection. The features that show highest accuracy during the classification between healthy and schizophrenia subjects are selected. Results: This study reveals several brain regions like cerebellum, inferior temporal gyrus, superior temporal gyrus, superior frontal gyrus, insula, and amygdala that have been reported in the existing literature, thus validating the proposed approach. We are also able to identify some functional changes in the brain regions, such as Heschl gyrus and the vermian area, which have not been reported in the literature involving working memory studies amongst schizophrenia patients. Conclusions: As our study confirms the results obtained in earlier studies, in addition to pointing out some brain regions not reported in earlier studies, the findings are likely to serve as a cue for clinical investigation, leading to better medical intervention.

A novel fuzzy rough selection of non-linearly extracted features for schizophrenia diagnosis using fMRI.

BACKGROUND AND OBJECTIVES: Schizophrenia is a severe brain disorder primarily diagnosed through externally observed behavioural symptoms due to the dearth of established clinical tests. Functional magnetic resonance imaging (fMRI) can capture the distortions caused by schizophrenia in the brain activation. Hence, it can be useful for developing a decision model that performs computer-aided diagnosis of schizophrenia. But, fMRI data is huge in dimension. Therefore dimension reduction is indispensable. It is additionally required to identify the discriminative brain regions. Hence, we aim to build an effective decision model that incorporates suitable dimension reduction and also identifies discriminative brain regions. METHODS: We propose a three-phase dimension reduction. First phase involves spatially-constrained fuzzy clustering of 3-dimensional spatial maps (obtained from general linear model and independent component analysis). In the second phase, non-linear features are extracted from each cluster using a generalized discriminant analysis. In the third phase, a novel fuzzy rough feature selection is proposed. The features obtained after the third phase are used for learning a decision model by the help of support vector machine classifier. This complete method is implemented within leave-one-out cross-validation on two balanced datasets (respectively acquired on 1.5Tesla and 3Tesla scanners). Both these datasets are created using Function Biomedical Informatics Research Network multisite data and contain fMRI data acquired during auditory oddball task performed by age-matched schizophrenia patients and healthy subjects. A permutation test is also carried out to ensure that no bias is involved in the learning. RESULTS: The results indicate that the proposed method achieves maximum classification accuracy of 97.1% and 98.0% for the two datasets respectively. The proposed method outperforms the state-of-the-art methods. The results of the permutation test show that p-values are lesser than the significance level i.e. 0.05. Therefore, the classifier has found a significant class structure and does not involve any bias. Further, discriminative brain regions are identified and are in agreement with the findings in related literature. CONCLUSION: The proposed method is able to derive suitable non-linear features and the related brain regions for effective computer-aided diagnosis. The fuzzy and rough set based approaches help in handling uncertainty and ambiguity in real data.

A combination of dual-tree discrete wavelet transform and minimum redundancy maximum relevance method for diagnosis of Alzheimer's disease.

In this paper, we propose a three-phased method for diagnosis of Alzheimer's disease using the structural magnetic resonance imaging (MRI). In first phase, gray matter tissue probability map is obtained from every brain MRI volume. Further, five regions of interest (ROIs) are extracted as per prior knowledge. In second phase, features are extracted from each ROI using 3D dual-tree discrete wavelet transform. In third phase, relevant features are selected using minimum redundancy maximum relevance features selection technique. The decision model is built with features so obtained, using a classifier. To evaluate the effectiveness of the proposed method, experiments are performed with four well-known classifiers on four data sets, built from a publicly available OASIS database. The performance is evaluated in terms of sensitivity, specificity and classification accuracy. It was observed that the proposed method outperforms existing methods in terms of all three performance measures. This is further validated with statistical tests.