Machine Learning-Assisted Prediction of the Biological Activity of Aromatase Inhibitors and Data Mining to Explore Similar Compounds

Designing molecules for drugs has been a hot topic for many decades. However, it is hard and expensive to find a new molecule. Thus, the cost of the final drug is also increased. Machine learning can provide the fastest way to predict the biological activity of druglike molecules. In the present work, machine learning models are trained for the prediction of the biological activity of aromatase inhibitors. Data was collected from the literature. Molecular descriptors are calculated to be used as independent features for model training. The results showed that the R ² values for linear regression, random forest regression, gradient boosting regression, and bagging regression are 0.58, 0.84, 0.77, and 0.80, respectively. Using these models, it is possible to predict the activity of new molecules in a short period of time and at a reasonable cost. Furthermore, Tanimoto similarity is used for similarity analysis, as well as a chemical database is mined to search for similar molecules. Nonetheless, this study provides a framework for repurposing other effective drug molecules to prevent cancer.

A Highly Fluorescent Pyrene-Based Sensor for Selective Detection Of Fe3+ Ion in Aqueous Medium: Computational Investigations

In this work, we introduce a highly selective and sensitive fluorescent sensor based on pyrene derivative for Fe(III) ion sensing in DMSO/water media. 2-(pyrene-2-yl)-1-(pyrene-2-ylmethyl)-1H-benzo[d]imidazole (PEBD) receptor was synthesized via simple condensation reaction and confirmed by spectroscopic techniques. The receptor exhibits fluorescence quenching in the presence of Fe(III) ions at 440 nm. ESI-MS and Job's method were used to confirm the 1:1 molar binding ratio of the receptor PEBD to Fe(III) ions. Using the Benesi-Hildebrand equation the binding constant value was determined as 8.485 × 10³ M^-1. Furthermore, the limit of detection (LOD, 3σ/K) value was found to be 1.81 µM in DMSO/water (95/5, v/v) media. According to the Environmental Protection Agency (EPA) of the United States, it is lower than the acceptable value of Fe³⁺ in drinking water (0.3 mg/L). The presence of 14 other metal ions such Co²⁺, Cr³⁺, Cu²⁺, Fe²⁺, Hg²⁺, Pb²⁺, K⁺, Ni²⁺, Mg²⁺, Cd²⁺, Ca²⁺, Mn²⁺, Al³⁺, and Zn²⁺ did not interfere with the detection of Fe(III) ions. The fluorescence life-time of the receptor PEBD with and without Fe³⁺ ion was found to be 1.097 × 10^-9 s and 0.9202 × 10^-9 s respectively. Similarly, the quantum yield of the receptor PEBD with Fe³⁺ and without Fe³⁺ ion was calculated, and found as 0.05 and 0.25 respectively. Computational studies of the receptor PEBD were carried out with density functional theory (DFT) using B3LYP/ 6-311G (d, p), LANL2DZ level of theory.

Synthesis of steroidal imidazolidinthiones as potential apoptotic agents: Investigation by theoretical and experimental studies

New steroidal imidazolidinthione derivatives (4-6) were synthesized from steroidal thiosemicarbazones and dichloroethane. The synthesized compounds were characterized using spectral data analysis. Theoretical DFT involving B3LYP/6-31G∗∗ level of theory was employed to gain insights into the molecular structure of the target compounds. MEPS and FMO analysis were carried out. HOMO-LUMO energy gap was determined which helped to evaluate various global descriptors like hardness, chemical potential, electronegativity, nucleophilicity and electrophilicity index, etc. The calculated properties established that the synthesized products are more or less similar in their reactivity behaviour. To explore their biological potential, interaction studies of compounds (4-6) with DNA were carried out using various biophysical techniques. The compounds bind DNA preferentially through electrostatic and hydrophobic interactions with K_b of 3.21 × 10³ M^-1, 2.79 × 10³ M^-1 and 2.26 × 10³ M^-1, respectively indicating the higher binding affinity of compound 4 towards DNA. Gel electrophoresis of compound 4 demonstrated strong interaction during the concentration dependent cleavage activity with pBR322 DNA. It was observed that these steroidal imidazolidinthiones are minor groove binders of DNA which was validated using molecular docking studies. An in vitro cytotoxicity screening using MTT assay revealed that the compounds (4-6) exhibit potential toxicity against different human cancer cells. Highest antiproliferative effect was observed on HeLa cells by compound 4. The results suggested that compounds 4-6 cause apoptotic cell death by cleaving apoptotic protein caspase-3 and suppress anti-apoptotic protein Bcl-2 in HeLa cancer cells.