HBCVTr: an end-to-end transformer with a deep neural network hybrid model for anti-HBV and HCV activity predictor from SMILES.

Hepatitis B and C viruses (HBV and HCV) are significant causes of chronic liver diseases, with approximately 350 million infections globally. To accelerate the finding of effective treatment options, we introduce HBCVTr, a novel ligand-based drug design (LBDD) method for predicting the inhibitory activity of small molecules against HBV and HCV. HBCVTr employs a hybrid model consisting of double encoders of transformers and a deep neural network to learn the relationship between small molecules' simplified molecular-input line-entry system (SMILES) and their antiviral activity against HBV or HCV. The prediction accuracy of HBCVTr has surpassed baseline machine learning models and existing methods, with R-squared values of 0.641 and 0.721 for the HBV and HCV test sets, respectively. The trained models were successfully applied to virtual screening against 10 million compounds within 240 h, leading to the discovery of the top novel inhibitor candidates, including IJN04 for HBV and IJN12 and IJN19 for HCV. Molecular docking and dynamics simulations identified IJN04, IJN12, and IJN19 target proteins as the HBV core antigen, HCV NS5B RNA-dependent RNA polymerase, and HCV NS3/4A serine protease, respectively. Overall, HBCVTr offers a new and rapid drug discovery and development screening method targeting HBV and HCV.

Crystal structure of the flavin reductase of Acinetobacter baumannii p-hydroxyphenylacetate 3-hydroxylase (HPAH) and identification of amino acid residues underlying its regulation by aromatic ligands.

The first step in the degradation of p-hydroxyphenylacetic acid (HPA) is catalyzed by the two-component enzyme p-hydroxyphenylacetate 3-hydroxylase (HPAH). The two components of Acinetobacter baumannii HPAH are known as C1 and C2, respectively. C1 is a flavin reductase that uses NADH to generate reduced flavin mononucleotide (FMNH-), which is used by C2 in the hydroxylation of HPA. Interestingly, although HPA is not directly involved in the reaction catalyzed by C1, the presence of HPA dramatically increases the FMN reduction rate. Amino acid sequence analysis revealed that C1 contains two domains: an N-terminal flavin reductase domain, and a C-terminal MarR domain. Although MarR proteins typically function as transcription regulators, the MarR domain of C1 was found to play an auto-inhibitory role. Here, we report a crystal structure of C1 and small-angle X-ray scattering (SAXS) studies that revealed that C1 undergoes a substantial conformational change in the presence of HPA, concomitant with the increase in the rate of flavin reduction. Amino acid residues that are important for HPA binding and regulation of C1 activity were identified by site-directed mutagenesis. Amino acid sequence similarity analysis revealed several as yet uncharacterized flavin reductases with N- or C-terminal fusions.