Chemical databases store information in text representations, and the SMILES format is a universal standard used in many cheminformatics software. Encoded in each SMILES string is structural information that can be used to predict complex chemical properties. In this work, we develop SMILES2vec, a deep RNN that automatically learns features from SMILES strings to predict a broad range of chemic...

A rapidly growing area of modern pharmaceutical research is the prediction of aqueous solubility of drug-sized compounds from their molecular structures. There exist many different reasons for considering this physico-chemical property as a key parameter: the design of novel entities with adequate aqueous solubility brings many advantages to preclinical and clinical research and development, al...

Solubility is a very important parameter in pharmaceutical research, especially for the early phase of drug discovery in fully automatized high throughput screening, compound pool extension and SAR and ADME-Tox parameter measurement. In recent years a multitude of models has been published concerned with the exact prediction of aqueous solubility. Still, almost all in the meantime commercially ...

Classical Barbiturates are formed by substituting one or both hydrogen atoms at the 5-position with alkyl, aryl, and/or alicyclic groups. In this study, a previously developed UPPER (Unified Physicochemical Property Estimation Relationships) approach is applied to predict the melting points and aqueous solubilities of a series of barbiturates. The descriptors from a previously developed UPPER m...

Although extensive theoretical and experimental research has been conducted on fluorinated fullerenes, little detailed information exists on their solubility in different solvents. However, this solubility is crucial for their processability and possible application. In this work, we predict the solubility of fluorinated C(60) in various polar and non-polar solvents, based on a correlation betw...

Dense Phase Carbon Dioxide (DPCD) is a non-thermal process that pasteurizes mostly liquid foods. It inactivates vegetative bacterial cells, some spores, yeasts and molds, some viruses, and some enzymes. The traditional approach to develop a DPCD process for a new product involves a complex experimental plan to investigate microbial and safety effects. Recent studies show the importance of the s...

The descriptors computed by HyperChem® software were employed to represent the solubility of 40 drug molecules in supercritical carbon dioxide using an artificial neural network with the architecture of 15-4-1. The accuracy of the proposed method was evaluated by computing average of absolute error (AE) of calculated and experimental logarithm of solubilities. The AE (±SD) of data sets was 0.4 ...

QSAR modeling is a method for predicting properties, e.g. the solubility or toxicity, of chemical compounds using statistical learning techniques. QSAR is in widespread use within the pharmaceutical industry to prioritize compounds for experimental testing or to alert for potential toxicity. However, predictions from a QSAR model are difficult to assess if their prediction intervals are unknown...

The objective of this contribution was to explore the effect of thermodynamic model selection on predicting the solubility of hydrogen in Pyrolysis Gasoline (PYGAS). In order to do this, different combinations of cubic equations of state (EOS), cohesion functions and mixing rules were compared, using both own algorithms and those implemented in the PRO/II 8.0 process simulation software. The mo...