Classical and Deep Learning Paradigms for Detection and Validation of Key Genes of Risky Outcomes of HCV

Abstract

Hepatitis C virus (HCV) is one of the most dangerous viruses worldwide. It is the foremost cause of the hepatic cirrhosis, and hepatocellular carcinoma, HCC. Detecting new key genes that play a role in the growth of HCC in HCV patients using machine learning techniques paves the way for producing accurate antivirals. In this work, there are two phases: detecting the up/downregulated genes using classical univariate and multivariate feature selection methods, and validating the retrieved list of genes using Insilico classifiers. However, the classification algorithms in the medical domain frequently suffer from a deficiency of training cases. Therefore, a deep neural network approach is proposed here to validate the significance of the retrieved genes in classifying the HCV-infected samples from the disinfected ones. The validation model is based on the artificial generation of new examples from the retrieved genes’ expressions using sparse autoencoders. Subsequently, the generated genes’ expressions data are used to train conventional classifiers. Our results in the first phase yielded a better retrieval of significant genes using Principal Component Analysis (PCA), a multivariate approach. The retrieved list of genes using PCA had a higher number of HCC biomarkers compared to the ones retrieved from the univariate methods. In the second phase, the classification accuracy can reveal the relevance of the extracted key genes in classifying the HCV-infected and disinfected samples.

Combining docking, molecular dynamics simulations, AD-MET pharmacokinetics properties, and MMGBSA calculations to create specialized protocols for running effective virtual screening campaigns on the autoimmune disorder and SARS-CoV-2 main protease

“…Then, a variety of variable selection techniques, such as Fractional Factorial Design (FFDSEL) and Uninformative Variable Elimination-Partial Least Square (UVE-PLS) variable selection ( Baroni et al, 1992 ; Centner et al, 1996 ), were used to develop the best PLS models. Cross-validated LOO (Leave-One-Out), LTO (Leave-Two-Out), or LMO (Leave-Many-Out) paradigms were used to compute PLS models ( Tosco and Balle, 2011 ; Abdel Samee et al, 2012 ; Abdel Samee, 2020 ; Nawaz et al, 2022 ). Last but not least, the Maestro graphics package was used to visualize PLS coefficient grid maps or the activity-correlating molecular regions in the form of iso-contour maps.…”

Detection and Classification of Histopathological Breast Images Using a Fusion of CNN Frameworks

“…Consequently, employing traditional ML approaches is severely limited when it comes to the classification of BC. Finally, DL algorithms [17,48] achieved impressive success of wide range of biomedical applications [11][12][13][14].…”

“…The use of machine learning (ML) [17][18][19][20] and deep learning (DL) [21,22] methodologies for the automatic categorization of BC has assisted in decreasing the risk of getting cancer and recurrence, and survival prediction might increase the accuracy by 20% to 25% more than it did in the previous year [23]. In the identification of invasive breast cancer, ML/DL is a technique that sees widespread application [8][9][10][11][12][13][14]24].…”

Using deep DenseNet with cyclical learning rate to classify leukocytes for leukemia identification

“…Numerous scientists have argued for employing machine learning (ML) and AI to automatically detect and diagnose abnormalities in microscopic images of leukocytes. CAD of leukocytes can be broken down into two categories: those that use ML ( 18 ) and those that use DL ( 19 ). Both ML and DL are described and summarized here.…”