We present El Agente Estructural, a multimodal, natural-language-driven geometry-generation and manipulation agent for autonomous chemistry and molecular modelling. Unlike molecular generation or edit...

Computational tools for searching molecular databases accelerate lead identification in drug discovery. In this work, we introduce qMol, an online platform designed to enable the search for accessible...

With the rapid growth of structural data in the Protein Data Bank, efficient mining and utilization of protein–ligand interaction pattern information from these structures can advance rational drug de...

Registering and working with a 3D data set using lwreg

EU-OPENSCREEN and the Society for Laboratory Automation and Screening (SLAS) are pleased to announce the second EU-OPENSCREEN/SLAS Joint Machine Learning Challenge, inviting scientists worldwide to pa...

In this work, we introduce TorchANI 2.0, a significantly improved version of the free and open source TorchANI software package for training and evaluation of ANI (ANAKIN-ME) deep learning models. Tor...

This editorial presents an analysis of the articles published in the Journal of Cheminformatics Special Issue “AI in Drug Discovery”. We review how novel machine learning developments are enhancing st...

The open-source tool goes beyond AlphaFold by finding proteins’ multiple equilibrium states and free energies

Posted 12:44:22 PM. At Roche you can show up as yourself, embraced for the unique qualities you bring. Our culture…See this and similar jobs on LinkedIn.

Protein engineering is a critical area within biotechnology, with enhancing protein thermal stability posing a significant challenge. Proteins from organisms adapted to extreme temperatures, such as t...

Including an exploration of charge variability across conformers

Transthyretin (TTR) plays a vital role in thyroid hormone transport and homeostasis in both the blood and target tissues. Interactions between exogenous compounds and TTR can disrupt the function of t...

Borrowing an idea from Randall Munroe

Generative models have emerged as potentially powerful methods for molecular design, yet challenges persist in generating molecules that effectively bind to the intended target. The ability to control the design process and incorporate prior knowledge would be highly beneficial for better tailoring molecules to fit specific binding sites. In this paper, we introduce MolSnapper, a novel tool that is able to condition diffusion models for structure-based drug design by seamlessly integrating expert knowledge in the form of 3D pharmacophores. We demonstrate through comprehensive testing on both the CrossDocked and Binding MOAD data sets that our method generates molecules better tailored to fit a given binding site, achieving high structural and chemical similarity to the original molecules. Additionally, MolSnapper yields approximately twice as many valid molecules as alternative methods.

Among the smaller substituents in the medicinal chemist’s toolbox, the hydroxy (OH) group can bestow one of the largest impacts in the drug-like properties of a molecule. A previous study showed that an H-to-OH structural modification effectively decreases lipophilicity, increases solubility, and decreases hERG inhibition. Despite these benefits, an OH group is not always recommended in drug molecules because it presents a metabolic “soft spot” for oxidation and glucuronidation in primary and secondary alcohols. Furthermore, the OH group presents challenges in permeability. In contrast, tertiary alcohols (3° ROH) often display an improved metabolic profile because oxidation at the 3° ROH is not possible, and the geminal alkyl groups could sterically shield the OH group from glucuronidation and permeability challenges. Through a series of matched molecular pairs, this Perspective highlights the 3° ROH as a motif that can reap the benefits but minimize the drawbacks of hydroxy groups in drug discovery.