SiteRadar: Utilizing Graph Machine Learning for Precise Mapping of Protein-Ligand-Binding Sites.

Identifying ligand-binding sites on the protein surface is a crucial step in the structure-based drug design. Although multiple techniques have been proposed, including those using machine learning algorithms, the existing solutions do not provide significant advantages over nonmachine learning approaches and there is still a big room for improvement. The low ability to identify protein-ligand-binding sites makes available approaches inapplicable to automated drug design. Here, we present SiteRadar, a new algorithm for mapping cavities that are likely to bind a small-molecule ligand. SiteRadar shows higher accuracy in binding site identification compared with FPocket and PUResNet. SiteRadar demonstrates an ability to detect up to 74% of true ligand-binding sites according to the top N + 2 metric and usually covers approximately 80% of ligand atoms. Therefore, SiteRadar can be regarded as a promising solution for implementation into algorithms for automated drug design.

Synthesis and initial in vitro evaluation of PSMA-targeting ligands with a modified aromatic moiety at the lysine ε-nitrogen atom.

We report an improved series of ligands targeting prostate specific membrane antigen (PSMA). The new compounds were designed by the introduction of changes in the structure of the aromatic fragment at ε-nitrogen atom of lysine that resulted in improved biological parameters. Some of them demonstrated high selectivity and nanomolar IC50 values. We synthesized and tested two conjugates with a fluorescent label Sulfo-Cy5 as an example of the use of the obtained PSMA inhibitors as a basis for the creation of diagnostic preparations.

Discovery of Bivalent GalNAc-Conjugated Betulin as a Potent ASGPR-Directed Agent against Hepatocellular Carcinoma.

Herein, we describe the design, synthesis, and biological evaluation of novel betulin and N-acetyl-d-galactosamine (GalNAc) glycoconjugates and suggest them as targeted agents against hepatocellular carcinoma. We prepared six conjugates derived via the C-3 and C-28 positions of betulin with one or two saccharide ligands. These molecules demonstrate high affinity to the asialoglycoprotein receptor (ASGPR) of hepatocytes assessed by in silico modeling and surface plasmon resonance tests. Cytotoxicity studies in vitro revealed a bivalent conjugate with moderate activity, selectivity of action, and cytostatic properties against hepatocellular carcinoma cells HepG2. An additional investigation confirmed the specific engagement with HepG2 cells by the enhanced generation of reactive oxygen species. Stability tests demonstrated its lability to acidic media and to intracellular enzymes. Therefore, the selected bivalent conjugate represents a new potential agent targeted against hepatocellular carcinoma. Further extensive studies of the cellular uptake in vitro and the real-time microdistribution in the murine liver in vivo for fluorescent dye-labeled analogue showed its selective internalization into hepatocytes due to the presence of GalNAc ligand in comparison with reference compounds. The betulin and GalNAc glycoconjugates can therefore be considered as a new strategy for developing therapeutic agents based on natural triterpenoids.

New Small-Molecule Glycoconjugates of Docetaxel and GalNAc for Targeted Delivery to Hepatocellular Carcinoma.

In this work, we have developed covalent and low molecular weight docetaxel delivery systems based on conjugation with N-acetyl-d-galactosamine and studied their properties related to hepatocellular carcinoma cells. The resulting glycoconjugates have an excellent affinity to the asialoglycoprotein receptor (ASGPR) in the nanomolar range of concentrations and a high cytotoxicity level comparable to docetaxel. Likewise, we observed the 21-75-fold increase in water solubility in comparison with parent docetaxel and prodrug lability to intracellular conditions with half-life values from 25.5 to 42 h. We also found that the trivalent conjugate possessed selective toxicity against hepatoma cells vs control cell lines (20-35 times). The absence of such selectivity in the case of monovalent conjugates indicates the effect of ligand valency. Specific ASGPR-mediated cellular uptake of conjugates was proved in vitro using fluorescent-labeled analogues. In addition, we showed an enhanced generation of reactive oxygen species in the HepG2 cells, which could be inhibited by the natural ligand of ASGPR. Overall, the obtained results highlight the potential of ASGPR-directed cytostatic taxane drugs for selective therapy of hepatocellular carcinoma.

Bifunctional Inhibitors of Influenza Virus Neuraminidase: Molecular Design of a Sulfonamide Linker.

The growing resistance of the influenza virus to widely used competitive neuraminidase inhibitors occupying the active site of the enzyme requires the development of bifunctional compounds that can simultaneously interact with other regulatory sites on the protein surface. When developing such an inhibitor and combining structural fragments that could be located in the sialic acid cavity of the active site and the adjacent 430-cavity, it is necessary to select a suitable linker not only for connecting the fragments, but also to ensure effective interactions with the unique arginine triad Arg118-Arg292-Arg371 of neuraminidase. Using molecular modeling, we have demonstrated the usefulness of the sulfonamide group in the linker design and the potential advantage of this functional group over other isosteric analogues.

Synthesis and Evaluation of New Trivalent Ligands for Hepatocyte Targeting via the Asialoglycoprotein Receptor.

Since the asialoglycoprotein receptor (also known as the "Ashwell-Morell receptor" or ASGPR) was discovered as the first cellular mammalian lectin, numerous drug delivery systems have been developed and several gene delivery systems associated with multivalent ligands for liver disease targeting are undergoing clinical trials. The success of these systems has facilitated the further study of new ligands with comparable or higher affinity and less synthetic complexity. Herein, we designed two novel trivalent ligands based on the esterification of tris(hydroxymethyl) aminomethane (TRIS) followed by the azide-alkyne Huisgen cycloaddition with azido N-acetyl-d-galactosamine. The presented triazolyl glycoconjugates exhibited good binding to ASGPR, which was predicted using in silico molecular docking and assessed by a surface plasmon resonance (SPR) technique. Moreover, we demonstrated the low level of in vitro cytotoxicity, as well as the optimal spatial geometry and the required amphiphilic balance, for new, easily accessible ligands. The conjugate of a new ligand with Cy5 dye exhibited selective penetration into HepG2 cells in contrast to the ASGPR-negative PC3 cell line.

Quantum-assisted fragment-based automated structure generator (QFASG) for small molecule design: an in vitro study.

Introduction: The significance of automated drug design using virtual generative models has steadily grown in recent years. While deep learning-driven solutions have received growing attention, only a few modern AI-assisted generative chemistry platforms have demonstrated the ability to produce valuable structures. At the same time, virtual fragment-based drug design, which was previously less popular due to the high computational costs, has become more attractive with the development of new chemoinformatic techniques and powerful computing technologies. Methods: We developed Quantum-assisted Fragment-based Automated Structure Generator (QFASG), a fully automated algorithm designed to construct ligands for a target protein using a library of molecular fragments. QFASG was applied to generating new structures of CAMKK2 and ATM inhibitors. Results: New low-micromolar inhibitors of CAMKK2 and ATM were designed using the algorithm. Discussion: These findings highlight the algorithm's potential in designing primary hits for further optimization and showcase the capabilities of QFASG as an effective tool in this field.

The Hitchhiker's Guide to Deep Learning Driven Generative Chemistry.

This microperspective covers the most recent research outcomes of artificial intelligence (AI) generated molecular structures from the point of view of the medicinal chemist. The main focus is on studies that include synthesis and experimental in vitro validation in biochemical assays of the generated molecular structures, where we analyze the reported structures' relevance in modern medicinal chemistry and their novelty. The authors believe that this review would be appreciated by medicinal chemistry and AI-driven drug design (AIDD) communities and can be adopted as a comprehensive approach for qualifying different research outcomes in AIDD.