GraphEGFR: Multi-task and transfer learning based on molecular graph attention mechanism and fingerprints improving inhibitor bioactivity prediction for EGFR family proteins on data scarcity.

The proteins within the human epidermal growth factor receptor (EGFR) family, members of the tyrosine kinase receptor family, play a pivotal role in the molecular mechanisms driving the development of various tumors. Tyrosine kinase inhibitors, key compounds in targeted therapy, encounter challenges in cancer treatment due to emerging drug resistance mutations. Consequently, machine learning has undergone significant evolution to address the challenges of cancer drug discovery related to EGFR family proteins. However, the application of deep learning in this area is hindered by inherent difficulties associated with small-scale data, particularly the risk of overfitting. Moreover, the design of a model architecture that facilitates learning through multi-task and transfer learning, coupled with appropriate molecular representation, poses substantial challenges. In this study, we introduce GraphEGFR, a deep learning regression model designed to enhance molecular representation and model architecture for predicting the bioactivity of inhibitors against both wild-type and mutant EGFR family proteins. GraphEGFR integrates a graph attention mechanism for molecular graphs with deep and convolutional neural networks for molecular fingerprints. We observed that GraphEGFR models employing multi-task and transfer learning strategies generally achieve predictive performance comparable to existing competitive methods. The integration of molecular graphs and fingerprints adeptly captures relationships between atoms and enables both global and local pattern recognition. We further validated potential multi-targeted inhibitors for wild-type and mutant HER1 kinases, exploring key amino acid residues through molecular dynamics simulations to understand molecular interactions. This predictive model offers a robust strategy that could significantly contribute to overcoming the challenges of developing deep learning models for drug discovery with limited data and exploring new frontiers in multi-targeted kinase drug discovery for EGFR family proteins.

Structure-based virtual screening for potent inhibitors of GH-20 ß-N-acetylglucosaminidase: Classical and machine learning scoring functions, and molecular dynamics simulations.

GH-20 ß-N-acetylglucosaminidases (GlcNAcases) are promising targets in the development of antimicrobial agents against Vibrio infections in humans and aquatic animals. In this study, we set up structure-based virtual screening to identify potential GH-20 GlcNAcase inhibitors from the Reaxys commercial database, using VhGlcNAcase from V. campbellii type strain ATCC® BAA 1116 as the protein target and Redoxal as the reference ligand. Using ChemPLP and RF-Score-VS machine learning scoring functions, eight lead compounds were identified and further evaluated for protein interaction preference and pharmacological properties. Protein-ligand analysis demonstrated that all selected compounds interacted exclusively at subsite - 1 with five hydrophobic residues W487, W505, W546, W582 and V544 at site S1, and with two polar residues, D437 and E438, at site 3. For subsite + 1, the most common residues were R274 and E584 at site 2 and I397 and Q398 at site 4. Based on the data obtained from binding free energy changes (ΔG°binding), pharmacological property analysis and molecular dynamic simulations, two ChemPLP compounds, 338175 and 1146525, and one RF-Score-VS compound, 337447, were considered as the likely lead compounds. The most promising compound, 1146525, could serve as a scaffold for the future design of novel antimicrobial agents against Vibrio infections.

Potential tripeptides against the tyrosine kinase domain of human epidermal growth factor receptor (HER) 2 through computational and kinase assay approaches.

An abnormal activation of human epidermal growth factor receptor (HER) 2 has been found to associate with several types of human cancer, and thus the protein is a prominent target for cancer therapy. Although several small chemical molecules targeting the tyrosine kinase (TK) of HER family have been identified, the development of a new class of inhibitors, i.e., small peptides inhibiting the function of tyrosine kinase is still promising. Here, we screened 8000 tripeptides for candidate potential inhibitors against HER2-TK using molecular docking. Our in vitro kinase assays showed that the candidate tripeptides had more than 50% relative inhibition to HER2-TK. Even though these tripeptides had much lower inhibitory activity than that of the drug Lapatinib, the tripeptides WWW exhibited high inhibitory activity with the IC50 of ≈283 µM, while FYW showed lower activity with the IC50 of ≈1723 µM. The relative binding free energies calculated by MM/PBSA method were comparable to the inhibition experiment in that Lapatinib binding was ≈-139 kJ/mol whereas the binding of WWW and FYW was ≈-112 kJ/mol and ≈-81 kJ/mol, respectively. Energy calculation also indicated that the HER2-TK/inhibitor interactions were dominated by van der Waals over electrostatic contributions. In addition, molecular interaction analyses revealed that several interacting residues with more negative binding free energy could mostly contribute the hydrophobic interaction. Therefore, we suggested preferable interactions for further development of potential tripeptides as a new anticancer peptide targeting HER2-TK.