Investigating the Role of Obesity in Prostate Cancer and Identifying Biomarkers for Drug Discovery: Systems Biology and Deep Learning Approaches

Abstract

Prostate cancer (PCa) is the second most frequently diagnosed cancer for men and is viewed as the fifth leading cause of death worldwide. The body mass index (BMI) is taken as a vital criterion to elucidate the association between obesity and PCa. In this study, systematic methods are employed to investigate how obesity influences the noncutaneous malignancies of PCa. By comparing the core signaling pathways of lean and obese patients with PCa, we are able to investigate the relationships between obesity and pathogenic mechanisms and identify significant biomarkers as drug targets for drug discovery. Regarding drug design specifications, we take drug–target interaction, drug regulation ability, and drug toxicity into account. One deep neural network (DNN)-based drug–target interaction (DTI) model is trained in advance for predicting drug candidates based on the identified biomarkers. In terms of the application of the DNN-based DTI model and the consideration of drug design specifications, we suggest two potential multiple-molecule drugs to prevent PCa (covering lean and obese PCa) and obesity-specific PCa, respectively. The proposed multiple-molecule drugs (apigenin, digoxin, and orlistat) not only help to prevent PCa, suppressing malignant metastasis, but also result in lower production of fatty acids and cholesterol, especially for obesity-specific PCa.

In-silico evaluation of natural alkaloids against the main protease and spike glycoprotein as potential therapeutic agents for SARS-CoV-2

“…The highest and lowest chronic toxicity values were shown by isoliensinine (3.668 log mg/kg bw/day) and emetine (0.674 log mg/kg_bw/day), respectively. According to the results of acute LD50 toxicity analysis, emetine causes the lowest toxicity as compared to other selected alkaloids because the higher the value of LD50, lesser the toxicity, or vice versa [ 83 , 84 ]. Similarly, according to LOAEL value, emetine is a safer alkaloid as a drug as compared to other lead alkaloids as it haa a higher LOAEL value ( Table 5 ).…”

“…LD50 toxicity analysis, emetine causes the lowest toxicity as compared to other selected alkaloids because the higher the value of LD50, lesser the toxicity, or vice versa [83,84]. Similarly, according to LOAEL value, emetine is a safer alkaloid as a drug as compared to other lead alkaloids as it haa a higher LOAEL value (Table 5).…”

Drug Target Identification and Drug Repurposing in Psoriasis through Systems Biology Approach, DNN-Based DTI Model and Genome-Wide Microarray Data

“…and ρ c is the estimated residual error of the c-th lncRNA, which was calculated from the least square estimated parameter Θc in the constrained estimation parameter problem Equation (19). H c , I c, and J c are the number of regulations of genes, lncRNAs, and miRNAs on the c-th gene, respectively.…”

“…Traditional DTI prediction methods mainly include ligand-based methods and docking-based methods, which are used to predict interactions based on the similarity between proteins and ligands. In recent years, DTI prediction methods based on machine learning have developed rapidly [ 17 , 18 , 19 , 20 ]. Drug repurposing, which refers to the use of a drug for an indication other than its original approval, can yield a wealth of data for research and can also reduce the need for additional studies of pharmacokinetic properties and toxicity.…”

“…The goal of this study is to investigate core signaling pathways through the systems biology method, identify significant biomarkers for the pathogenic mechanism of psoriasis as drug targets, and employ a DNN-based DTI model to predict and design a multi-molecule drug for the treatment of psoriasis as shown in Figure 1 . First, the genome-wide genetic and epigenetic networks (GWGENs) of psoriasis and non-psoriasis are constructed [ 19 ]. For the annotation of KEGG pathways, GWGENs of psoriasis and non-psoriasis are extracted by the principal network projection (PNP) method into two core GWGENs with 6000 significant nodes, as shown in Figure 2 and Figure 3 , respectively.…”