RIMD: A novel method for clinical prediction.

Electronic health records (EHR) are sparse, noisy, and private, with variable vital measurements and stay lengths. Deep learning models are the current state of the art in many machine learning domain; however, the EHR data is not a suitable training input for most of them. In this paper, we introduce RIMD, a novel deep learning model that consists of a decay mechanism, modular recurrent networks, and a custom loss function that learns minor classes. The decay mechanism learns from patterns in sparse data. The modular network allows multiple recurrent networks to pick only relevant input based on the attention score at a given timestamp. Finally, the custom class balance loss function is responsible for learning minor classes based on samples provided in training. This novel model is used to evaluate predictions for early mortality identification, length of stay, and acute respiratory failure on MIMIC-III dataset. Experiment results indicate that the proposed models outperform similar models in F1-Score, AUROC, and PRAUC scores.

In Vitro and In Silico Studies for the Identification of Potent Metabolites of Some High-Altitude Medicinal Plants from Nepal Inhibiting SARS-CoV-2 Spike Protein.

Despite ongoing vaccination programs against COVID-19 around the world, cases of infection are still rising with new variants. This infers that an effective antiviral drug against COVID-19 is crucial along with vaccinations to decrease cases. A potential target of such antivirals could be the membrane components of the causative pathogen, SARS-CoV-2, for instance spike (S) protein. In our research, we have deployed in vitro screening of crude extracts of seven ethnomedicinal plants against the spike receptor-binding domain (S1-RBD) of SARS-CoV-2 using an enzyme-linked immunosorbent assay (ELISA). Following encouraging in vitro results for Tinospora cordifolia, in silico studies were conducted for the 14 reported antiviral secondary metabolites isolated from T. cordifolia-a species widely cultivated and used as an antiviral drug in the Himalayan country of Nepal-using Genetic Optimization for Ligand Docking (GOLD), Molecular Operating Environment (MOE), and BIOVIA Discovery Studio. The molecular docking and binding energy study revealed that cordifolioside-A had a higher binding affinity and was the most effective in binding to the competitive site of the spike protein. Molecular dynamics (MD) simulation studies using GROMACS 5.4.1 further assayed the interaction between the potent compound and binding sites of the spike protein. It revealed that cordifolioside-A demonstrated better binding affinity and stability, and resulted in a conformational change in S1-RBD, hence hindering the activities of the protein. In addition, ADMET analysis of the secondary metabolites from T. cordifolia revealed promising pharmacokinetic properties. Our study thus recommends that certain secondary metabolites of T. cordifolia are possible medicinal candidates against SARS-CoV-2.

Molecular Docking and Dynamics Simulation of Several Flavonoids Predict Cyanidin as an Effective Drug Candidate against SARS-CoV-2 Spike Protein.

The in silico method has provided a versatile process of developing lead compounds from a large database in a short duration. Therefore, it is imperative to look for vaccinations and medications that can stop the havoc caused by SARS-CoV-2. The spike protein of SARS-CoV-2 is required for the viral entry into the host cells, hence inhibiting the virus from fusing and infecting the host. This study determined the binding interactions of 36 flavonoids along with two FDA-approved drugs against the spike protein receptor-binding domain of SARS-CoV-2 through molecular docking and molecular dynamics (MD) simulations. In addition, the molecular mechanics generalized Born surface area (MM/GBSA) approach was used to calculate the binding-free energy (BFE). Flavonoids were selected based on their in vitro assays on SARS-CoV and SARS-CoV-2. Our pharmacokinetics study revealed that cyanidin showed good drug-likeness, fulfilled Lipinski's rule of five, and conferred favorable toxicity parameters. Furthermore, MD simulations showed that cyanidin interacts with spike protein and alters the conformation and binding-free energy suited. Finally, an in vitro assay indicated that about 50% reduction in the binding of hACE2 with S1-RBD in the presence of cyanidin-containing red grapes crude extract was achieved at approximately 1.25 mg/mL. Hence, cyanidin may be a promising adjuvant medication for the SARS-CoV-2 spike protein based on in silico and in vitro research.

Potential natural inhibitors of xanthine oxidase and HMG-CoA reductase in cholesterol regulation: in silico analysis.

BACKGROUND: Hypercholesterolemia has posed a serious threat of heart diseases and stroke worldwide. Xanthine oxidase (XO), the rate-limiting enzyme in uric acid biosynthesis, is regarded as the root of reactive oxygen species (ROS) that generate atherosclerosis and cholesterol crystals. ß-Hydroxy ß-methylglutaryl-coenzyme A reductase (HMGR) is a rate-limiting enzyme in cholesterol biosynthesis. Although some commercially available enzyme inhibiting drugs have effectively reduced cholesterol levels, most of them have failed to meet potential drug candidates' requirements. Here, we have carried out an in-silico analysis of secondary metabolites that have already shown good inhibitory activity against XO and HMGR in a wet lab setup. METHODS: Out of 118 secondary metabolites reviewed, sixteen molecules inhibiting XO and HMGR were selected based on the IC50 values reported in in vitro assays. Further, receptor-based virtual screening was carried out against secondary metabolites using GOLD Protein-Ligand Docking Software, combined with subsequent post-docking, to study the binding affinities of ligands to the enzymes. In-silico ADMET analysis was carried out to explore their pharmacokinetic properties, followed by toxicity prediction through ProTox-II. RESULTS: The molecular docking of amentoflavone (GOLD score 70.54, ∆G calc. = - 10.4 Kcal/mol) and ganomycin I (GOLD score 59.61, ∆G calc. = - 6.8 Kcal/mol) displayed that the drug has effectively bound at the competitive site of XO and HMGR, respectively. Besides, 6-paradol and selgin could be potential drug candidates inhibiting XO. Likewise, n-octadecanyl-O-α-D-glucopyranosyl (6' → 1″)-O-α-D-glucopyranoside could be potential drug candidates to maintain serum cholesterol. In-silico ADMET analysis has shown that these sixteen metabolites were optimal within the categorical range compared to commercially available XO and HMGR inhibitors, respectively. Toxicity analysis through ProTox-II revealed that 6-gingerol, ganoleucoin K, and ganoleucoin Z are toxic for human use. CONCLUSION: This computational analysis supports earlier experimental evidence towards the inhibition of XO and HMGR by natural products. Further study is necessary to explore the clinical efficacy of these secondary molecules, which might be alternatives for the treatment of hypercholesterolemia.