Is it time to retire druglikeness?

⚡ I was struck by a statement I read today about a Techbio company that "uses large language models to create billions of druglike molecules". I have nothing against this company and I think they do very interesting work, no need to name them. But I found myself suddenly and surprisingly critical of the expression "druglike molecules", a somewhat anachronistic concept in 2025. I mentioned Lipinski's Rule of Five (focusing on molecular weight, lipophilicity, hydrogen bond donors/acceptors) in yesterday's post (link in comments) about the drug-unlike compound that looks too much like a detergent but might be acceptable by modern criteria.

Traditional druglikeness criteria provided useful guidelines for oral bioavailability at a time of little data and less powerful model (compared to now). However, modern drug discovery has shown these rules have significant limitations:

1️⃣ Many successful drugs violate these rules, particularly biologics, peptides, and natural products.

2️⃣ The pharmaceutical landscape has expanded beyond small molecule oral drugs to include antibodies, oligonucleotides, and other modalities.

3️⃣ Target-specific considerations often override general druglikeness rules.

Today, the concept is more nuanced—druglikeness is increasingly viewed as a spectrum rather than binary. We can now use more sophisticated computational models that consider:

▶️ Specific delivery routes and target tissues

▶️ Pharmacokinetic properties

▶️ Safety profiles

▶️ Target engagement

Rather than asking "is this molecule druglike?" developers now ask "does this molecule have the right properties for its intended therapeutic use?" This shift reflects the growing complexity and sophistication of modern drug discovery, with its rapidly increasing arsenal of models, AI algorithms and datasets.

👏 The super short and catchy title

"Validation of L-type calcium channel blocker amlodipine as a novel ADHD treatment through cross-species analysis, drug target Mendelian randomization, and clinical evidence from

medical records" (link) hides a gem of a clever study. Or perhaps the title does not hide anything 💡. In any event, Marco Schmidt does a great job of summarizing and simplifying the findings, distilling a 3-step process so clearly that I thought I had missed something 😵‍💫 .

So, for those who enjoy more convoluted expressions of awe, here is my take on an epic highly multidisciplinary study led by 3Z Pharmaceuticals and biotx.ai:

1️⃣ Cross-species Validation: They confirmed effects across different animal models before moving to human genetic data. Just in passing, they demonstrated amlodipine can cross the blood-brain barrier, contradicting previous assumptions

2️⃣ Drug-target Mendelian Randomization: They developed a new approach to analyze data from multiple drug-target genes simultaneously, providing stronger evidence for repurposing

3️⃣ Reverse Translation: Instead of the typical drug development pathway (starting with basic science and moving to clinical trials), they started with a drug screen, validated in animal models, then confirmed with human genetic evidence

4️⃣ Repurposing Potential: They identified a well-established, safe medication that could potentially be developed into a new ADHD treatment with fewer side effects than current stimulant medications

The beauty of this research lies in how it combines multiple lines of evidence (behavioral, pharmacological, genetic, and clinical data) to build a compelling case for amlodipine as a potential ADHD treatment.

This approach will have many more applications!