Recludix succeeded in drugging SH2 domains, a target class abandoned in the 90s, by integrating five modern technologies. This platform includes proprietary DNA-encoded libraries, machine learning, a selectivity tool, novel crystallography methods, and a pro-drug approach to ensure cell permeability, demonstrating the complex approach needed for modern drug discovery breakthroughs.

Unlike traditional small molecules that need a pocket on a target protein, molecular glues work by changing the surface of an E3 ligase. This modified surface then perfectly matches and binds the target protein, enabling its degradation without requiring a direct drug-to-target binding site.

Instead of targeting the final protein, Remix develops small molecules that intervene during pre-mRNA processing. This novel approach allows them to inhibit historically difficult drug targets like MYB, a transcription factor with no obvious binding sites, by preventing the disease-driving protein from ever being made.

The concept of an "undruggable" target is a misnomer, according to Pacesa. Any failure to create a binder for a specific protein site is a limitation of the current design method or modality, not an intrinsic property of the target. He posits that, with the right approach, a binder can be designed for any site.

To target MYC, Dewpoint uses phenotypic screens that monitor the entire MYC condensate. This approach is mechanism-agnostic, capable of identifying compounds that work via previously attempted methods (e.g., disrupting binding) as well as novel ones like dissolving the condensate itself.

By focusing on the phenotypic outcome (cellular stress) rather than a predefined target, Soleil's platform can identify small molecules that modulate proteins considered undruggable by conventional means. Their lead oncology candidate, for example, modulates CCAP2, demonstrating the platform's ability to find novel biology and expand the druggable space.

ProPhet's strategy is to focus on 'hard-to-drug' proteins, which are often avoided because they lack the structural data required for traditional discovery. Because ProPhet's AI model needs very little protein information to predict interactions, this data scarcity becomes a competitive advantage.

Targeting the MYC cancer protein presents a dual challenge. Biologically, it's vital for healthy cells, creating a high risk of toxicity. Biophysically, its disordered, 'floppy' structure lacks the defined pockets that traditional drugs need to bind to, making it a 'holy grail' target.

Instead of designing synthetic small molecules to block cancer-driving CDK kinases, which often cause toxic side effects, Concarlo uses a 'molecular glue' to lock the naturally selective p27 protein in its inhibitory state. This novel approach lets 'nature be selective for us,' increasing specificity and reducing toxicity.