Research Insights

In the rapidly evolving landscape of structural biology and AI-native drug discovery, the frontier is moving faster than ever. Almost weekly, new computational models are released, each claiming to outperform previous benchmarks on critical macromolecular structure prediction tasks. For a lean, mission-driven startup like AlgorithmicRx, this explosion of open-science tools is a massive equalizer. But it also introduces a critical scientific question: How do we separate model-

One of the quieter shifts happening in drug discovery right now isn’t a new drug class — it’s a change in where the design work happens. Increasingly, the first draft of a therapeutic molecule is built not on a lab bench, but inside a cloud computing job, using a protein language model to propose a structure before a single reagent is touched. At AlgorithmicRx, we spend a lot of time evaluating tools like this, because the computational front-end of drug discovery is exactly

At AlgorithmicRx, our mission has always been clear: accelerate the discovery of transformative therapies for rare diseases by combining deep biology with artificial intelligence. As our platform advances into the MVP stage, we are continuing to refine not only how we identify therapeutic targets, but also how we build biological confidence around them before moving into downstream drug design. Beyond Target Discovery Our AI platform integrates diverse biological data—includi

The AlgorithmicRx team participated virtually in July 29's U.S. Food and Drug Administration (FDA) Cellular, Tissue, and Gene Therapies Advisory Committee (CTGTAC) meeting reviewing Capricor Therapeutics' Biologics License Application (BLA) for Deramiocel as a potential treatment for Duchenne muscular dystrophy (DMD). Following presentations from FDA reviewers, Capricor Therapeutics, scientific experts, physicians, patients, caregivers, and advocacy organizations, the Advisor

We're building a computational proof-of-concept (POC) that uses AlphaFold 3 to discover compensatory proteins capable of restoring a critical structural link broken in DMD: from disease hypothesis to in silico validation The Problem Duchenne Muscular Dystrophy (DMD) is caused by mutations in the dystrophin gene , that leave the protein truncated or missing entirely. Dystrophin normally acts as a molecular shock absorber, anchoring the cell's internal actin skeleton to the...

A recent breakthrough from researchers at Biohub and UC Berkeley demonstrates exactly that. Their development of a laser phase plate significantly enhances the contrast of cryo-electron microscopy (cryo-EM), allowing scientists to visualize proteins and cellular structures that were previously difficult—or even impossible—to observe. Why does this matter beyond microscopy? Because every advancement in biological measurement improves the quality of the data we generate. And in

With the introduction of Claude Science, Anthropic has signaled something profound: frontier AI companies increasingly see biology—not just software—as the next frontier for innovation. Beyond launching an AI workbench tailored for scientific research, Anthropic has also announced plans to pursue drug discovery for neglected diseases, marking a shift from building AI tools to actively participating in therapeutic discovery. This reflects a broader transformation in our indust

The U.S. Food and Drug Administration (FDA) has released a draft guidance recommending the use of Quantitative Systems Pharmacology (QSP) modeling to inform first-in-human dose selection. This represents another important step toward modernizing drug development by integrating computational science into regulatory decision-making and reducing unnecessary reliance on animal studies. For the rare disease community, this development is particularly significant. Traditional drug