#1

As many are familliar with, AI is being developed at a rapid, exponential rate, doubling capabilities about every 7 months, soon we might have longevity drugs available for use in e.g worms (see previous thread Super longevity drugs coming soon 2027-2028) by using models for custom synthesis, but maybe there are models available today or soon, to develop new drugs or to check already approved ones.

For example has anyone tried this, released yesterday? Does it look promising? Model is open weights (available for download), and allows you to ask questions based on a compound’s chemical structure, like if it can pass the BBB, and Google offers an agent (Agentic-Tx) with lots of tools to figure if maybe a compound is good for further development.

Feel free to post here what you discover or any new models or websites related to this, or how you might use these models for longevity.

Introducing TxGemma: Open models to improve therapeutics development

MAR 25, 2025

Developing a new therapeutic is risky, notoriously slow, and can cost billions of dollars. 90% of drug candidates fail beyond phase 1 trials. Today, we’re excited to release TxGemma, a collection of open models designed to improve the efficiency of therapeutic development by leveraging the power of large language models.

Building on Google DeepMind’s Gemma, a family of lightweight, state-of-the-art open models, TxGemma is specifically trained to understand and predict the properties of therapeutic entities throughout the entire discovery process, from identifying promising targets to helping predict clinical trial outcomes. This can potentially shorten the time from lab to bedside, and reduce the costs associated with traditional methods.
…
TxGemma models, fine-tuned from Gemma 2 using 7 million training examples, are open models designed for prediction and conversational therapeutic data analysis. These models are available in three sizes: 2B, 9B and 27B. Each size includes a ‘predict’ version, specifically tailored for narrow tasks drawn from Therapeutic Data Commons, for example predicting if a molecule is toxic.

These tasks encompass:

  • classification (e.g., will this molecule cross the blood-brain barrier?)

  • regression (e.g., predicting a drug’s binding affinity)

  • and generation (e.g., given the product of some reaction, generate the reactant set)

…

Orchestrating workflows for advanced therapeutic discovery with Agentic-Tx

Beyond single-step predictions, we’re demonstrating how TxGemma can be integrated into agentic systems to tackle more complex research problems. Standard language models often struggle with tasks requiring up-to-date external knowledge or multi-step reasoning. To address this, we’ve developed Agentic-Tx, a therapeutics-focused agentic system powered by Gemini 2.0 Pro. Agentic-Tx is equipped with 18 tools, including:

  • TxGemma as a tool for multi-step reasoning

  • General search tools from PubMed, Wikipedia and the web

  • Specific molecular tools

  • Gene and protein tools

Agentic-Tx achieves state-of-the-art results on reasoning-intensive chemistry and biology tasks from benchmarks including Humanity’s Last Exam and ChemBench. We are including a Colab notebook with our release to demonstrate how Agentic-Tx can be used to orchestrate complex workflows and answer multi-step research questions.

image
image791×542 67.9 KB

2 Likes
#2

I asked the model about the BBB permeability of rapamycin, it suggested that it does not cross the BBB.

Instructions: Answer the following question about drug properties.
Context: As a membrane separating circulating blood and brain extracellular fluid, the blood-brain barrier (BBB) is the protection layer that blocks most foreign drugs. Thus the ability of a drug to penetrate the barrier to deliver to the site of action forms a crucial challenge in development of drugs for central nervous system.
Question: Given a drug SMILES string, predict whether it
(A) does not cross the BBB (B) crosses the BBB
Drug SMILES: O[C@@H]1CCC@HCC@@H[C@@H]4CC(=O)C@H/C=C(\C)C@@HC@@HC(=O)C@HCC@H\C=C\C=C\C=C(/C)C@@HC[C@@H]2CCC@@HC@@(O2)C(=O)C(=O)N3CCCC[C@H]3C(=O)O4
Answer:

(A)

Explain your reasoning based on the molecule structure.

The provided SMILES string describes a very large and complex molecule with multiple chiral centers and several functional groups including amides, esters, and ethers. Here’s why this molecule is likely to have poor blood-brain barrier permeability:

  • Size and Complexity: The molecule is extremely large. Large molecules generally have difficulty crossing the BBB due to the tight junctions between endothelial cells lining the blood vessels in the brain.
  • Polarity: The presence of multiple polar functional groups like amides, esters, and ethers increases the molecule’s overall polarity. Highly polar molecules tend to be less permeable across lipid membranes, such as the BBB.
  • Lack of Lipophilicity: There are limited hydrophobic regions in the molecule. Lipophilicity (fat solubility) is a crucial factor for crossing the BBB, as the cell membranes within the barrier are primarily composed of lipids.

In summary: The combination of large size, high polarity, and lack of lipophilicity strongly suggests that this molecule will have difficulty crossing the blood-brain barrier.

1 Like