Model Diagnostics and Forecast Evaluation for Quantiles

Model diagnostics and forecast evaluation are closely related tasks, with the former concerning in-sample goodness (or lack) of fit and the latter addressing predictive performance out-of-sample. We review the ubiquitous setting in which forecasts are cast in the form of quantiles or quantile-bounded prediction intervals. We distinguish unconditional calibration, which corresponds to classical coverage criteria, from the stronger notion of conditional calibration, as can be visualized in quantile reliability diagrams. Consistent scoring functions-including, but not limited to, the widely used asymmetric piecewise linear score or pinball loss-provide for comparative assessment and ranking, and link to the coefficient of determination and skill scores.We illustrate the use of these tools on Engel's food expenditure data, the Global Energy Forecasting Competition 2014, and the US COVID-19 Forecast Hub.

From oncoproteins to spike proteins: the evaluation of intramolecular stability using hydropathic force field.

Evaluation of the intramolecular stability of proteins plays a key role in the comprehension of their biological behavior and mechanism of action. Small structural alterations such as mutations induced by single nucleotide polymorphism can impact biological activity and pharmacological modulation. Covid-19 mutations, that affect viral replication and the susceptibility to antibody neutralization, and the action of antiviral drugs, are just one example. In this work, the intramolecular stability of mutated proteins, like Spike glycoprotein and its complexes with the human target, is evaluated through hydropathic intramolecular energy scoring originally conceived by Abraham and Kellogg based on the "Extension of the fragment method to calculate amino acid zwitterion and side-chain partition coefficients" by Abraham and Leo in Proteins: Struct. Funct. Genet. 1987, 2:130 - 52. HINT is proposed as a fast and reliable tool for the stability evaluation of any mutated system. This work has been written in honor of Prof. Donald J. Abraham (1936-2021).

Target-Specific Machine Learning Scoring Function Improved Structure-Based Virtual Screening Performance for SARS-CoV-2 Drugs Development.

Leveraging machine learning has been shown to improve the accuracy of structure-based virtual screening. Furthermore, a tremendous amount of empirical data is publicly available, which further enhances the performance of the machine learning approach. In this proof-of-concept study, the 3CLpro enzyme of SARS-CoV-2 was used. Structure-based virtual screening relies heavily on scoring functions. It is widely accepted that target-specific scoring functions may perform more effectively than universal scoring functions in real-world drug research and development processes. It would be beneficial to drug discovery to develop a method that can effectively build target-specific scoring functions. In the current study, the bindingDB database was used to retrieve experimental data. Smina was utilized to generate protein-ligand complexes for the extraction of InteractionFingerPrint (IFP) and SimpleInteractionFingerPrint SIFP fingerprints via the open drug discovery tool (oddt). The present study found that randomforestClassifier and randomforestRegressor performed well when used with the above fingerprints along the Molecular ACCess System (MACCS), Extended Connectivity Fingerprint (ECFP4), and ECFP6. It was found that the area under the precision-recall curve was 0.80, which is considered a satisfactory level of accuracy. In addition, our enrichment factor analysis indicated that our trained scoring function ranked molecules correctly compared to smina's generic scoring function. Further molecular dynamics simulations indicated that the top-ranked molecules identified by our developed scoring function were highly stable in the active site, supporting the validity of our developed process. This research may provide a template for developing target-specific scoring functions against specific enzyme targets.

An intuitionistic fuzzy decision support system for COVID-19 lockdown relaxation protocols in India.

In January 2020, the World Health Organization (WHO) identified a world-threatening virus, SARS-CoV-2. To diminish the virus spread rate, India implemented a six-month-long lockdown. During this period, the Indian government lifted certain restrictions. Therefore, this study investigates the efficacy of India's lockdown relaxation protocols using fuzzy decision-making. The decision-making trial and evaluation laboratory (DEMATEL) is one of the fuzzy MCDM methods. When it is associated with intuitionistic fuzzy circumstances, it is known as the intuitionistic fuzzy DEMATEL (IF-DEMATEL) method. Moreover, converting intuitionistic fuzzy into a crisp score (CIFCS) algorithm is an aggregation technique utilized for the intuitionistic fuzzy set. By using IF-DEMATEL and CIFCS, the most efficient lockdown relaxation protocols for COVID-19 are determined. It also provides the cause and effect relationship of the lockdown relaxation protocols. Additionally, the comparative study is carried out through various DEMATEL methods to see the effectiveness of the result. The findings would be helpful to the government's decision-making process in the fight against the pandemic.

Methods and applications of machine learning in structure-based drug discovery

Structure-based drug discovery (SBDD) utilizes the three-dimensional (3D) structure of a target protein to identify the lead compounds. This medium is then considered a viable solution based on its availability and correlation with a particular disease. In the case of pandemics like COVID 19, shortening drug development time can save millions of people worldwide;for such a task, classical drug discovery methods will take a long time. Hence, researchers worldwide actively incorporated machine learning (ML) into the drug discovery process, particularly in SBDD, to minimize the lead optimization time. ML uses statistical methods to make a computer perform tasks, take a critical decision, and automate this entire process without being explicitly programmed. With this, the computer can discover new insights about data and unknown patterns crucial to decide the therapeutic use of lead compounds as drugs. The use of ML in the drug discovery field is not new, and it spans an ample research space. By integrating artificial intelligence with ML techniques, viable targets can be found using data clustering, regression, and classification from vast omics databases and sources. In this chapter, we will discuss the methods and applications of ML in SBDD. © 2022 Elsevier Inc. All rights reserved.

Anti-metal Deteriorating and Antiviral Potency of a Novel Polynuclear Schiff base, Derived from Anthrone

The versatile behavior of many Schiff bases is due to the presence of the azomethine group. In this work, we synthesized a novel polynuclear Schiff base [ANHIS] derived from anthrone and histidine, characterized using spectroscopic tools, and evaluated its anti-corrosion and anti-viral potencies. Conventional weight-loss method, electrochemical impedance spectroscopic investigation (EIS), potentiodynamic polarization studies (Tafel), adsorption studies, and quantum chemical calculations were used to investigate the anticorrosion behavior. The result showed that the Schiff base interacted with the surface metal atoms and provides good protection to the carbon steel surface against corrosion in an acid medium. A mixed-type inhibitor action of ANHIS was determined by Tafel plot analysis. A plausible mechanism of inhibition action is also anticipated. SEM analyses were carried out to explore the surface characteristics of the metal in the absence and presence of ANHIS. Drug likeness and ADMET properties of ANHIS were screened using online web servers. The preliminary IN SILICO pharmacokinetics and medicinal chemistry studies revealed that the molecule shows a very good drug-like property. The toxicity studies predict that it has less or no toxic behavior (carcinogenic in mice and non-carcinogenic in rats). The antiviral activity of the molecule was investigated on SARS-CoV-2(COVID-19 virus) using Autodock software. Docking studies showed that the polynuclear molecule ANHIS possessed hydrogen bonding, aromatic and hydrophobic interactions with the binding site of the main receptor of the COVID-19 virus. The docking score is comparable with the score value of anti-HIV drugs such as lopinavir and indinavir.

In Silico Study of Phenolic Compounds from Honey as Mpro SARS-CoV-2 Inhibitor Candidates

SARS-CoV-2 has caused a global COVID-19 pandemic since late 2019 and the reported cases have not ended until now. One way to overcome the Covid-19 pandemic is to find the main viral protease inhibitor (Mpro) SARS-CoV-2 which is a key enzyme of virus replication. Honey is a bee-derived product that contains various phenolic compounds and has antiviral activity. This study aimed to find candidate Mpro SARS-CoV-2 inhibitors from honey phenolic compounds using molecular docking simulations in a directed manner. A total of 27 test ligands (from honey's phenolic compounds), 4 comparison ligands (from synthetic antiviral compounds), and reference ligands (N3 compound) were screened for their character as drug compounds by Lipinski's rules and for their toxicity by admetSAR. All ligands were docked to the Mpro SARS-CoV-2 receptor code 7BQY using AutoDock Tools 1.5.6 and Autodock Vina with center of coordinates: X = 10,398;Y = -1,254;Z = 23.473 and grid size: X = 40;Y = 46;Z = 40. Molecular docking simulation produces affinity energy and molecular interactions data. The results showed that the best candidate for Mpro SARS-CoV-2 inhibitor from honey's phenolic compounds was genistein because it complied with all Lipinski rules, was non-toxigenic, not a carcinogen, had an affinity energy of -7.6 kCal/mol, 80% similarity to the reference ligand N3, and occupies 63,64% of the tether coverage area. The results of this study are expected to be used in further research, both in vitro and in vivo.