New research published in Nature Communications shows how generative AI can be used to design complex dual-action cancer drug candidates. Insilico Medicine has developed a PKMYT1 degrader that both eliminates the target protein and blocks its activity, demonstrating the growing role of AI in advanced drug discovery.
AI is accelerating drug discovery at an unprecedented pace. Thousands of antibody candidates can now be designed in silico within hours. The challenge now is keeping experimental workflows fast enough to keep up. High-throughput expression and integrated developability assessment are making it possible to move from sequence to data in days.
Promatix Biosciences is developing a new generation of bispecific antibody–drug conjugates using proprietary membrane proteomics data to identify highly selective target pairings. CEO Dr Michael Hunter explains how the company’s TXPro database enables discovery of previously unexplored tumour biology to improve therapeutic index and reduce on-target/off-tumour toxicities in solid tumours.
The key to faster, smarter drug discovery lies in data that’s often overlooked. By exposing hidden delays and inefficiencies, this data enables teams to shorten discovery cycles and progress promising candidates faster.
Designing gene control from scratch is becoming possible. SynGenSys is using computational design to create synthetic promoters for advanced therapies.