This study introduces the PocketCFDM generative diffusion model, aimed at improving the prediction of small molecule poses in the protein binding pockets. The model utilizes a novel data augmentation technique, involving the creation of numerous artificial binding pockets that mimic the statistical patterns of non-bond interactions found in actual protein-ligand complexes. An algorithmic method was developed to assess and replicate these interaction patterns in the artificial binding pockets built around small molecule conformers.
View Article and Find Full Text PDFAccurate prediction of the drug-target affinity (DTA) is of critical importance for modern drug discovery. Computational methods of DTA prediction, applied in the early stages of drug development, are able to speed it up and cut its cost significantly. A wide range of approaches based on machine learning were recently proposed for DTA assessment.
View Article and Find Full Text PDFDuring alcohol fermentation, the carbon isotope composition of ethyl alcohol produced depended on the substrate used and was characterized by the value of delta 13C equal to -24.7 +/- 0.8/1000 (wheat grain), -22 +/- 0.
View Article and Find Full Text PDFFluorescence yield of Rhodopseudomonas sphaeroides cells whose primary acceptor is chemically reduced depends on the magnetic field tension. The maximal value of relative magnetic effect and the field value, at which the effect amounts to a half of the maximal value for R. sphaeroides wild strain and R-26, equal 3.
View Article and Find Full Text PDFRedox titration of chromatophores through the region +300 +570 mV at room temperature results in generation of two dark ESR signals, a well-known reaction center signal and a new narrow line. This line is characterized by deltaH pp = 4.2 Oe, g-factor about that of RC and a Lorentzian shape.
View Article and Find Full Text PDF