Utilizing Deep Learning Models and Transfer Learning for COVID-19 Detection from X-Ray Images.

COVID-19 has been a global pandemic. Flattening the curve requires intensive testing, and the world has been facing a shortage of testing equipment and medical personnel with expertise. There is a need to automate and aid the detection process. Several diagnostic tools are currently being used for COVID-19, including X-Rays and CT-scans. This study focuses on detecting COVID-19 from X-Rays. We pursue two types of problems: binary classification (COVID-19 and No COVID-19) and multi-class classification (COVID-19, No COVID-19 and Pneumonia). We examine and evaluate several classic models, namely VGG19, ResNet50, MobileNetV2, InceptionV3, Xception, DenseNet121, and specialized models such as DarkCOVIDNet and COVID-Net and prove that ResNet50 models perform best. We also propose a simple modification to the ResNet50 model, which gives a binary classification accuracy of 99.20% and a multi-class classification accuracy of 86.13%, hence cementing the ResNet50's abilities for COVID-19 detection and ability to differentiate pneumonia and COVID-19. The proposed model's explanations were interpreted via LIME which provides contours, and Grad-CAM, which provides heat-maps over the area(s) of interest of the classifier, i.e., COVID-19 concentrated regions in the lungs, and realize that LIME explains the results better. These explanations support our model's ability to generalize. The proposed model is intended to be deployed for free use.

Gaussian Blurring Technique for Detecting and Classifying Acute Lymphoblastic Leukemia Cancer Cells from Microscopic Biopsy Images.

Visual inspection of peripheral blood samples is a critical step in the leukemia diagnostic process. Automated solutions based on artificial vision approaches can accelerate this procedure, while also improving accuracy and uniformity of response in telemedicine applications. In this study, we propose a novel GBHSV-Leuk method to segment and classify Acute Lymphoblastic Leukemia (ALL) cancer cells. GBHSV-Leuk is a two staged process. The first stage involves pre-processing, which uses the Gaussian Blurring (GB) technique to blur the noise and reflections in the image. The second stage involves segmentation using the Hue Saturation Value (HSV) technique and morphological operations to differentiate between the foreground and background colors, which improve the accuracy of prediction. The proposed method attains 96.30% accuracy when applied on the private dataset, and 95.41% accuracy when applied on the ALL-IDB1 public dataset. This work would facilitate early detection of ALL cancer.

An Effective Multi-Label Protein Sub-Chloroplast Localization Prediction by Skipped-Grams of Evolutionary Profiles Using Deep Neural Network.

Chloroplast is one of the most classic organelles in algae and plant cells. Identifying the locations of chloroplast proteins in the chloroplast organelle is an important as well as a challenging task in deciphering their functions. Biological-based experiments to identify the Protein Sub-Chloroplast Localization (PSCL) is time-consuming and cost-intensive. Over the last decade, a few computational methods have been developed to predict PSCL in which earlier works assumed to predict only single-location; whereas, recent works are able to predict multiple-locations of chloroplast organelle. However, the performances of all the state-of-the-art predictors are poor. This article proposes a novel skip-gram technique to extract highly discriminating patterns from evolutionary profiles and a multi-label deep neural network to predict the PSCL. The proposed model is assessed on two publicly available datasets, i.e., Benchmark and Novel. Experimental results demonstrate that the proposed work outperforms significantly when compared to the state-of-the-art multi-label PSCL predictors. A multi-label prediction accuracy (i.e., Overall Actual Accuracy) of the proposed model is enhanced by an absolute minimum margin of 6.7 percent on Benchmark dataset and 7.9 percent on Novel dataset when compared to the best PSCL predictor from the literature. Further, result of statistical t-test concludes that the performance of the proposed work is significantly improved and thus, the proposed work is an effective computational model to solve multi-label PSCL prediction. The proposed prediction model is hosted on web-server and available at https://nitkit-vgst727-nppsa.nitk.ac.in/deeplocpred/.

Enhanced Protein Structural Class Prediction Using Effective Feature Modeling and Ensemble of Classifiers.

Protein Secondary Structural Class (PSSC) information is important in investigating further challenges of protein sequences like protein fold recognition, protein tertiary structure prediction, and analysis of protein functions for drug discovery. Identification of PSSC using biological methods is time-consuming and cost-intensive. Several computational models have been developed to predict the structural class; however, they lack in generalization of the model. Hence, predicting PSSC based on protein sequences is still proving to be an uphill task. In this article, we proposed an effective, novel and generalized prediction model consisting of a feature modeling and an ensemble of classifiers. The proposed feature modeling extracts discriminating information (features) by leveraging three techniques: (i) Embedding - features are extracted on the basis of spatial residue arrangements of the sequences using word embedding approaches; (ii) SkipXGram Bi-gram - various sets of skipped bi-gram features are extracted from the sequences; and (iii) General Statistical (GS) based features are extracted which covers the global information of structural sequences. The combined effective sets of features are trained and classified using an ensemble of three classifiers: Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting Machines (GBM). The proposed model when assessed on five benchmark datasets (high and low sequence similarity), viz. z277, z498, 25PDB, 1189, and FC699, reported an overall accuracy of 93.55, 97.58, 81.82, 81.11, and 93.93 percent respectively. The proposed model is further validated on a large-scale updated low similarity ( ≤ 25%) dataset, where it achieved an overall accuracy of 81.11 percent. The proposed generalized model is robust and consistently outperformed several state-of-the-art models on all the five benchmark datasets.

An Enhanced Protein Fold Recognition for Low Similarity Datasets Using Convolutional and Skip-Gram Features With Deep Neural Network.

The protein fold recognition is one of the important tasks of structural biology, which helps in addressing further challenges like predicting the protein tertiary structures and its functions. Many machine learning works are published to identify the protein folds effectively. However, very few works have reported the fold recognition accuracy above 80% on benchmark datasets. In this study, an effective set of global and local features are extracted from the proposed Convolutional (Conv) and SkipXGram bi-gram (SXGbg) techniques, and the fold recognition is performed using the proposed deep neural network. The performance of the proposed model reported 91.4% fold accuracy on one of the derived low similarity (< 25%) datasets of latest extended version of SCOPe_2.07. The proposed model is further evaluated on three popular and publicly available benchmark datasets such as DD, EDD, and TG and obtained 85.9%, 95.8%, and 88.8% fold accuracies, respectively. This work is first to report fold recognition accuracy above 85% on all the benchmark datasets. The performance of the proposed model has outperformed the best state-of-the-art models by 5% to 23% on DD, 2% to 19% on EDD, and 3% to 30% on TG dataset.

ProgSIO-MSA: Progressive-based single iterative optimization framework for multiple sequence alignment using an effective scoring system.

Aligning more than two biological sequences is termed multiple sequence alignment (MSA). To analyze biological sequences, MSA is one of the primary activities with potential applications in phylogenetics, homology markers, protein structure prediction, gene regulation, and drug discovery. MSA problem is considered as NP-complete. Moreover, with the advancement of Next-Generation Sequencing techniques, all the gene and protein databases are consistently loaded with a vast amount of raw sequence data which are neither analyzed nor annotated. To analyze these growing volumes of raw sequences, the need of computationally-efficient (polynomial time) models with accurate alignment is high. In this study, a progressive-based alignment model is proposed, named ProgSIO-MSA, which consists of an effective scoring system and an optimization framework. The proposed scoring system aligns sequences effectively using the combination of two scoring strategies, i.e. Look Back Ahead, that scores a residue pair dynamically based on the status information of the previous position to improve the sum-of-pair score, and Position-Residue-Specific Dynamic Gap Penalty, that dynamically penalizes a gap using mutation matrix on the basis of residue and its position information. The proposed single iterative optimization (SIO) framework identifies and optimizes the local optima trap to improve the alignment quality. The proposed model is evaluated against progressive-based state-of-the-art models on two benchmark datasets, i.e. BAliBASE and SABmark. The alignment quality (biological accuracy) of the proposed model is increased by a factor of 17.7% on BAliBASE dataset. The proposed model's efficiency is compared with state-of-the-art models using time complexity as well as runtime analysis. Wilcoxon signed-rank statistical test results concluded that the quality of the proposed model significantly outperformed progressive-based state-of-the-art models.