Will we ever be able to accurately predict solubility?

Accurate prediction of thermodynamic solubility by machine learning remains a challenge. Recent models often display good performances, but their reliability may be deceiving when used prospectively. This study investigates the origins of these discrepancies, following three directions: a historical perspective, an analysis of the aqueous solubility dataverse and data quality. We investigated over 20 years of published solubility datasets and models, highlighting overlooked datasets and the overlaps between popular sets. We benchmarked recently published models on a novel curated solubility dataset and report poor performances. We also propose a workflow to cure aqueous solubility data aiming at producing useful models for bench chemist. Our results demonstrate that some state-of-the-art models are not ready for public usage because they lack a well-defined applicability domain and overlook historical data sources. We report the impact of factors influencing the utility of the models: interlaboratory standard deviation, ionic state of the solute and data sources. The herein obtained models, and quality-assessed datasets are publicly available.

In silico prediction of polyethylene-aqueous and air partition coefficients of organic contaminants using linear and nonlinear approaches

Low-density polyethylene (LDPE) passive sampling is very attractive for use in determining chemicals concentrations. Crucial to the measurement is the coefficient (K_PE) describing partitioning between LDPE and environmental matrices. 255, 117 and 190 compounds were collected for the development of datasets in three different matrices, i.e., water, air and seawater, respectively. Further, 3 pp-LFER models and 9 QSPR models based on classical multiple linear regression (MLR) coupled with prevalent nonlinear algorithms (artificial neural network, ANN and support vector machine, SVM) were performed to predict LDPE-water (K_PE-W), LDPE-air (K_PE-A) and LDPE-seawater (K_PE-SW) partition coefficients. These developed models have satisfying predictability (R²_adj: 0.805-0.966, 0.963-0.991 and 0.817-0.941; RMSE_tra: 0.233-0.565, 0.200-0.406 and 0.260-0.459) and robustness (Q²_ext: 0.840-0.943, 0.968-0.984 and 0.797-0.842; RMSE_ext: 0.308-0.514, 0.299-0.426 and 0.407-0.462) in three datasets (water, air and seawater), respectively. In particular, the reasonable mechanism interpretations revealed that the molecular size, hydrophobicity, polarizability, ionization potential, and molecular stability were the most relevant properties, for governing chemicals partitioning between LDPE and environmental matrices. The application domains (ADs) assessed here exhibited the satisfactory applicability. As such, the derived models can act as intelligent tools to predict unknown K_PE values and fill the experimental gaps, which was further beneficial for the construction of enormous and reliable database to facilitate a distinct understanding of the distribution for organic contaminants in total environment.

Study on the interaction of anti-inflammatory drugs with human serum albumin using molecular docking, quantitative structure-activity relationship, and fluorescence spectroscopy

The interaction of 14 anti-inflammatory drugs with human serum albumin (HSA) was investigated using fluorescence quenching, molecular docking studies, and quantitative structure-activity relationship (QSAR) methodology. Binding of anti-inflammatory drugs to HSA plays a fundamental role in their transport, distribution, delivery, and elimination. Binding constants of these drugs to HSA, obtained using the fluorescence quenching method, were within the range 0.01 × 10⁴  M^-1 (acetaminophen) to 1881.05 × 10⁴  M^-1 (meloxicam). Binding sites and binding constants of these anti-inflammatory drugs were estimated using molecular docking. Inspection of the obtained values for docking score, logK_b and K_b , showed that the drugs in this data set have a relatively strong binding constant for HSA. QSAR modelling was applied for binding constants obtained from fluorescence quenching and theoretical molecular descriptors. This modelling led to a linear two-parameter model with a correlation coefficient of 0.95 and adequate robustness. The descriptor results showed the importance of a bonding network and electronegativity as the discriminative structural factors in binding affinity for the HSA molecule.