Identifying disease targets, understanding complex biology, and developing effective technologies for target engagement.

Discussing the challenges and strategies in targeted protein degradation (TPD), a promising therapeutic modality with the potential to drug difficult or "undruggable" protein targets.

The complexities of developing cell models and testing novel therapies: considering throughput, consistency, and reproducibility.

The significance of reproducibility, fidelity, and translatability in models, as well as the importance of using multiple models to cross-validate therapeutic targets.

The panel at Drug Discovery US discussed hit finding technologies, protein availability for screening, and hit-to-lead transition.

How quantum annealers, which use quantum mechanics to solve optimisation problems by finding the lowest energy state of a system, are being used for drug discovery.

Our Discussion Group featured expert conversation on automation and synthesis from software to hardware, key challenges, and end goals.

Our expert panel discuss the implementation of AI and ML tools for drug design: predictive models, computational chemistry, and AlphaFold.

The panel discussion from Discovery US 2022, investigates into new technologies for target engagement and expanding the chemical space.

Benedict Cross, Chief Technology Officer at PhoreMost, leads our Discussion Group on Target-Based Drug Discovery using Genomic and CRISPR techniques.

Target deconvolution is crucial to the phenotypic discovery process. Jenny Mattsson of BioInvent International explains how using CRISPR/Cas9 screening is a more efficient target deconvolution approach.

Target identification and validation forms the backbone of efforts to discover new drugs. Our expert panel discussed challenges and solutions in this field to drive safety and efficacy.

Japanese-UK biotech Sosei Heptares are tackling the problem of stabilising GPCR structures with a view toward novel drug discovery endpoints.

AlphaFold, using AI/ML to predict the structures of proteins, has jumped off the pages of sci-fi and landed into the labs of researchers… but is it any good?

Making the most of big data and AI to achieve compound suggestions for drug discovery chemistry.

September's discussion group takes us through AI applied to drug design. Where it has been useful, and where it has been not so useful.

As computer processing capabilities have risen to new heights, scientists have been learning to take advantage for molecular dynamic simulation.

RAS mutations are the most common subfamily of oncogenes, so finding inhibitors could be extremely valuable to oncology research. However, they also make for particularly difficult targets. Andreas Mantoulidis explains how BI have been attempting to ‘drug the undruggable.’