Enumerating protonation states and calculating microstate pKa values of small molecules is an important yet challenging task for lead optimization and molecular modeling. Commercial and non-commercial solutions have notable limitations such as restrictive and expensive licenses, high CPU/GPU hour requirements, or the need for expert knowledge to set up and use. We present a graph neural network model that is trained on 714,906 calculated microstate pKa predictions from molecules obtained from the ChEMBL database. The model is fine-tuned on a set of 5,994 experimental pKa values significantly improving its performance on two challenging test sets. Combining the graph neural network model with Dimorphite-DL, an open-source program for enumerating ionization states, we have developed the open-source Python package pkasolver, which is able to generate and enumerate protonation states and calculate pKa values with high accuracy.

Oxidative stress monitoring in the neonatal period supports early outcome prediction and treatment. Glutathione (GSH) is the most abundant antioxidant in most cells and tissues, including whole blood, and its usefulness as a biomarker has been known for decades. To date, the available methods for GSH determination require laborious sample processing and the use of sophisticated laboratory equipment. To the best of our knowledge, no tools suitable for point-of-care (POC) sensing have been reported. Surface-enhanced Raman spectroscopy (SERS), performed in a microvolume capillary measurement cell, is proposed in this study as a robust approach for the quantification of GSH in human whole blood samples. The use of a silver colloid allowed a highly selective signal enhancement for GSH providing analytical enhancement factors of 3 to 4 orders of magnitude. A highly accurate determination of GSH in whole blood samples with recoveries ranging from 99 to 107% and relative standard deviations less than or equal to 18% were achieved by signal normalization with the intensity of an isotopically labeled internal standard. GSH concentrations were retrieved within 4 min using small-volume blood samples (2 μL). The developed procedure was applied to the analysis of blood of 20 healthy adults and 36 newborns, obtaining comparable results between literature and those found by SERS and a reference method. The characteristics of this novel tool are suitable for its implementation in a portable optical sensor device enabling POC testing of oxidative stress levels in newborns.

Enumerating protonation states and calculating micro-state pKa values of small molecules is an important yet challenging task for lead optimization and molecular modeling. Commercial and non-commercial solutions have notable limitations such as restrictive and expensive licenses, high CPU/GPU hour requirements or the need for expert knowledge to setup and use. We present a graph neural network model that is trained on 714,906 calculated mico-state pKa predictions from molecules obtained from the ChEMBL database. The model is fine-tuned on a set of 5,994 experimental pKa values significantly improving its performance on two challenging test sets. Combining the graph neural network model with Dimorphite-DL, an open-source program for enumerating ionization states, we have developed the open-source Python package pkasolver, which is able to generate and enumerate protonation states and calculate micro-state pKa values with high accuracy.

No abstract