Détails

Source

TAO Daily

Publication

26 août à 19h20

Lien direct

https://taodaily.io/nova-takes-ai-drug-discovery-from-competition-to-the-lab/

Contenu source (brut)

<p class="wp-block-paragraph">NOVA has reached a new stage in its attempt to turn <a href="https://taodaily.io/metanova-sn68-turns-miner-submissions-into-testable-drugs/">drug discovery</a> into a continuous, open competition. Its first <strong>small molecules and nanobodies have entered the laboratory for experimental testing</strong>.</p> <p class="wp-block-paragraph">This development marks an important milestone for the subnet. Until now, NOVA&#8217;s competitions have primarily operated in the computational domain, with participants submitting molecules, nanobodies, and discovery algorithms and competing based on measurable performance.</p> <p class="wp-block-paragraph">With physical experiments now underway, the network can begin bringing real-world experimental results back into the system.</p> <h2 class="wp-block-heading">212,000+ Submissions</h2> <p class="wp-block-paragraph">The scale of the competition is already substantiated.&nbsp;NOVA reported that it has received <strong>212,561 submissions</strong>, enriching its discovery libraries with:</p> <ul class="wp-block-list"> <li><strong>11,130,975 small molecules</strong></li> <li><strong>82,575 nanobodies</strong></li> <li><strong>6,397 discovery algorithms</strong></li> </ul> <p class="wp-block-paragraph">These submissions come from three parallel competitions covering small-molecule design, nanobody design, and chemical search algorithms.</p> <p class="wp-block-paragraph">This is significant because the competition creates a mechanism for continuously selecting among different approaches without relying on a single model, research team, or predetermined methodology.</p> <p class="wp-block-paragraph">Now, some of those computationally generated candidates are being subjected to experimental validation.</p> <h2 class="wp-block-heading">From Benchmark Performance to Physical Ground Truth</h2> <p class="wp-block-paragraph">One of the persistent problems in AI-driven drug discovery is the gap between performance on computational benchmarks and performance against novel, real-world chemistry.</p> <p class="wp-block-paragraph">NOVA&#8217;s approach is designed to address that gap by introducing experimental results into the competitive loop.</p> <p class="wp-block-paragraph">The subnet&#8217;s development builds on a broader history of scientific competitions, from Kaggle&#8217;s Merck Molecular Activity Challenge and Tox21 to Leash Bio&#8217;s BELKA challenge and more recent blind and prospective drug-discovery benchmarks.</p> <p class="wp-block-paragraph">These competitions have demonstrated the value of exposing difficult scientific problems to large numbers of competing approaches. But NOVA is attempting to make the process <strong>persistent</strong>, while extending the evaluation process toward physical experimentation.</p> <h2 class="wp-block-heading">A Continuous Discovery Loop</h2> <p class="wp-block-paragraph">This is where NOVA&#8217;s model becomes particularly interesting.</p> <p class="wp-block-paragraph">Instead of a competition ending when a leaderboard is finalized, successful computational candidates can move toward laboratory testing. The resulting experimental data can then provide new ground truth for the network.</p> <p class="wp-block-paragraph">That creates the possibility of a continuously improving discovery system and, in turn, determines which ideas deserve further resources.</p> <p class="wp-block-paragraph">The platform is effectively trying to turn drug discovery into an ongoing selection process.&nbsp;If that loop works at scale, the value of NOVA may extend well beyond the individual competitions they&#8217;re currently running.</p> <p class="wp-block-paragraph">The objective is no longer simply to find the best-performing model on a benchmark. It is to build an infrastructure where <strong>the best-performing scientific ideas can continuously move from computation toward experimentally validated discoveries.</strong></p> <p class="wp-block-paragraph">And with the first small molecules and nanobodies now in the lab, NOVA is beginning to test that objective against physical reality.</p> <p class="wp-block-paragraph">More on Metanova (SN68):</p> <figure class="wp-block-embed is-type-wp-embed is-provider-the-tao-daily wp-block-embed-the-tao-daily"><div class="wp-block-embed__wrapper"> <blockquote class="wp-embedded-content" data-secret="lTXt5dJ6UK"><a href="https://taodaily.io/hash-rate-ep-165-metanova-expands-into-nanobodies-wet-lab-pipeline-and-ai-co-scientist-vision/">Hash Rate Ep. 165: Metanova Expands Into Nanobodies, Wet Lab Pipeline, and AI Co-Scientist Vision</a></blockquote><iframe class="wp-embedded-content" sandbox="allow-scripts" security="restricted" style="position: absolute; visibility: hidden;" title="“Hash Rate Ep. 165: Metanova Expands Into Nanobodies, Wet Lab Pipeline, and AI Co-Scientist Vision” — The TAO Daily" src="https://taodaily.io/hash-rate-ep-165-metanova-expands-into-nanobodies-wet-lab-pipeline-and-ai-co-scientist-vision/embed/#?secret=xYkhrqpojL#?secret=lTXt5dJ6UK" data-secret="lTXt5dJ6UK" width="500" height="282" frameborder="0" marginwidth="0" marginheight="0" scrolling="no"></iframe> </div></figure>