A Strong Contender for the Next Nobel Prize

The startup Iambic has made a breakthrough that surpasses Google DeepMind’s AlphaFold. While AlphaFold, the AI system developed by Google DeepMind, recently earned a Nobel Prize in Chemistry for predicting the 3D structure of how molecules bind to target proteins, this is just the beginning. It’s impressive but not enough to drastically reduce the time (10-15 years) and costs ($1-2.6 billion per drug) required to bring new medicines to market.

Iambic has taken it a step further by developing an AI model that predicts, with remarkable accuracy, how well a human body will absorb a specific drug candidate. The predictions are validated against real-world data, making it a promising tool for pharmaceutical development.

The success of a drug candidate depends on several key properties—pharmacokinetics, efficacy, and toxicity. These are exactly the factors predicted by Iambic’s AI-powered drug discovery platform called Enchant, which boasts a predictive accuracy of 0.74, compared to just 0.58 achieved by previous models.

The Enchant model could potentially cut the costs of drug development in half, allowing pharmaceutical companies to assess a drug’s potential success at the earliest stages of research.

To understand the significance of Iambic’s breakthrough, consider the vast competition in the “AI in Biomedicine” sector, where more than 8,600 companies are racing to unlock the next major innovation (as shown in the chart above). In the sub-segment of “AI-based Analytics Platforms for Drug Development” alone, the number of companies has grown fourfold in the last three years, now standing at 950 competitors (see the chart below).

#AI #DeepPharma #DrugDiscovery #Biotech #Pharmacology #AlphaFold
#science

🧬
DeepMind has released AlphaFold 4, pushing protein structure prediction into a new era.

The updated model handles:
• ~20,000 human proteins
• multi-chain complexes
• protein–protein interactions
• selected post-translational modifications

Reported accuracy reaches ~98% on benchmark datasets — approaching experimental resolution in many cases.

📄 Preprint (updated Feb 18, 2026):
https://arxiv.org/abs/2402.18567

⸻

🧪 Why this matters

This is no longer just about predicting isolated protein folds.

AlphaFold 4 moves toward modeling biological systems — complexes, assemblies, interaction interfaces — the level where real drug discovery happens.

Targets long considered “undruggable,” such as:

• KRAS
• MYC

may become structurally tractable thanks to improved interface prediction.

Pharma companies are already integrating AI-generated structures into drug pipelines, potentially shortening early-stage discovery timelines dramatically. (Not “10 years → 2 years” overnight — but the structural bottleneck is shrinking fast.)

⸻

🔬 Bigger picture

If AlphaFold 2 solved the protein folding problem,
AlphaFold 4 begins solving the interaction problem.

Structural biology is shifting from slow, expensive crystallography toward AI-assisted molecular design.

We are watching the transition from “map the molecule” to “engineer the molecule.”

The question now isn’t can we predict structure?
It’s how fast can we turn structure into therapy?

#AlphaFold #AI #DrugDiscovery #Biotech #ComputationalBiology

🧠 Scientists Discover the Hidden Molecular Switch That Keeps Alzheimer's Inflammation Stuck in Overdrive

Researchers at Scripps Research Institute have identified a precise molecular mechanism that explains why the brain's immune system becomes trapped in a state of chronic, destructive inflammation in Alzheimer's disease. The discovery, published in Cell Chemical Biology, reveals that a single chemical modification to a protein called STING — at a specific building block known as cysteine 148 — acts as an "on switch" that cannot turn itself off.

The brain has its own built-in immune defenses, and STING normally serves as an early-warning system against infections. But in Alzheimer's patients, the team found that STING undergoes a process called S-nitrosylation (SNO), where a nitric oxide-related molecule latches onto cysteine 148. This transforms STING into a hyperactive form — dubbed "SNO-STING" — that clusters into large complexes and continuously pumps out inflammatory signals. The researchers confirmed elevated levels of this rogue protein in postmortem human brain tissue, in human stem cell-derived brain immune cells, and in mouse models of the disease.

What makes this cycle particularly vicious is that the very protein clumps associated with Alzheimer's — amyloid-beta and alpha-synuclein — can themselves trigger the S-nitrosylation of STING. Aging, air pollution, and even wildfire smoke further fuel the process by increasing nitric oxide in the brain. The result is a self-perpetuating "SNO-STORM": inflammation generates more NO, which modifies more STING, which drives even more inflammation, gradually destroying the synapses neurons use to communicate.

— A single amino acid (cysteine 148) on the STING protein is the exact site of the damaging modification
— Blocking SNO-STING formation in mice significantly reduced neuroinflammation
— Crucially, synaptic connections between neurons were protected from degradation — the same connections whose loss correlates with cognitive decline
— Unlike broad anti-inflammatory drugs, targeting cysteine 148 quiets only the pathological overactivation while leaving normal immune function intact
— The same pathway was confirmed active in human Alzheimer's brain tissue and stem-cell models

"This is a new and important therapeutic target for Alzheimer's disease," said senior author Stuart Lipton, the Step Family Foundation Endowed Chair at Scripps Research and a clinical neurologist. "It's exciting to see that blocking this switch in mice reduces inflammation and protects the very brain cell connections that are lost in Alzheimer's."

Why it matters: Alzheimer's affects over 55 million people worldwide, yet nearly all clinical trials targeting amyloid plaques have failed or shown marginal benefit. This discovery shifts the focus to neuroinflammation as a driver — not just a bystander — of the disease. The fact that the target is a single, well-defined amino acid means drug developers have an unusually clean bullseye. Lipton's team is already working on small-molecule drugs designed to sit on cysteine 148 and prevent the SNO modification, potentially offering the first therapy that breaks the inflammation cycle without crippling the immune system.

📄 Original paper (Cell Chemical Biology): https://www.cell.com/cell-chemical-biology/fulltext/S2451-9456(26)00109-1
📖 Readable summary (ScienceDaily): https://www.sciencedaily.com/releases/2026/05/260530053424.htm

#Alzheimers #Neuroscience #Neuroinflammation #STING #DrugDiscovery

🧠 A Copper-Based Compound May Help the Brain Clear Alzheimer’s Proteins — by Repairing Its “Waste Pumps”

Most Alzheimer’s drug research has focused on attacking amyloid plaques directly. A new study from Monash University suggests a different route: what if the brain’s waste-clearance system could be repaired instead?

The compound is called Cu(ATSM) — a copper-delivering molecule already studied in human safety trials for Parkinson’s disease and ALS. In a mouse model of Alzheimer’s, researchers found that Cu(ATSM) restored levels of P-glycoprotein, or P-gp — a transporter at the blood-brain barrier that helps move amyloid-beta out of the brain.

Think of P-gp as part of the brain’s drainage system. When these pumps weaken, toxic proteins can accumulate. When the researchers boosted them with Cu(ATSM), the results were striking:

• 42% reduction in toxic amyloid-beta over 56 days
• nearly 44% improvement in spatial learning
• 24.1% increase in P-gp clearance pumps at the blood-brain barrier
• evidence that repairing the blood-brain barrier may help lower amyloid burden and improve cognition

The important caveat: this was not a human Alzheimer’s trial. The results come from APP/PS1 mice — a widely used model of the disease — so the next question is whether the same mechanism works in people.

Still, the idea is powerful. Instead of only trying to destroy plaques after they form, future therapies might also help the brain restore its own clearance infrastructure.

If Alzheimer’s is partly a “drainage failure,” could repairing the brain’s plumbing become one of the next big strategies in neurodegeneration?

📄 Source: https://doi.org/10.1021/acschemneuro.6c00252

#Alzheimers #Neuroscience #DrugDiscovery #BloodBrainBarrier #CopperTherapy #science