We present 3dpredict/Ab which calculates ensemble-based predictions of antibody developability descriptors and putative liabilities. 3dpredict/Ab allows for out-of-the-box SaaS automation and integration of such complex simulations of hundreds or thousands of sequences.

¹ Wang et al. Scientific Reports, 2022

The results show that pharmacophore queries can be used to efficiently search and pose 3D antibody structures and that pharmacophore searching represents a high-throughput virtual screening (HTVS) alternative to protein-protein docking.

While cheminformatics and molecular modeling techniques have matured significantly for small molecules, peptide modelers frequently encounter substantial limitations when attempting to adapt these methodologies to peptides. This challenge is exacerbated by the higher synthetic throughput, which necessitates the generation of numerous proposals.

In this discussion, we outline the typical challenges faced by molecular peptide modelers, including issues related to 2D depictions, sequence handling, peptide ADME predictions, structure-activity relationship (SAR) analysis, and 3D modeling. We also present innovative solutions, ideas, and strategies aimed at overcoming combinatorial hurdles and advancing peptide-based projects.

We will delve into cutting-edge methodologies that leverage generative models, such as deep learning frameworks, to predict protein-protein interactions, streamline molecular design, and accelerate the drug discovery pipeline. Alongside technical advancements, we will discuss the challenges of integrating AI-driven models with existing computational frameworks and experimental techniques for structure determination and validation. Through real-world case studies we will highlight successful implementations of structure-based design and ongoing research.