We are excited to announce that the powerful IBM MAMMAL (Molecular Aligned Multi-Modal Architecture and Language) model is now available for free through the Cure Cancer With AI public API. Developed by IBM Research, MAMMAL is a cutting-edge multi-modal biomedical foundation model designed to enhance cancer research and drug discovery.

But what exactly does "multi-modal" mean? In essence, MAMMAL integrates information from various biological sources, including proteins, small molecules, and single-cell gene and omics data. This unification allows researchers to analyze complex relationships across different biological entities, making it a vital tool for advancing our understanding of cancer and improving drug discovery processes.

The Science Behind MAMMAL

The capabilities of MAMMAL are detailed in the research paper titled "MAMMAL — Molecular Aligned Multi-Modal Architecture and Language for biomedical discovery", published in npj Drug Discovery (Nature). This impressive model has been trained on approximately 2 billion biological samples and evaluated across 11 diverse drug-discovery tasks, achieving state-of-the-art results on 9 of these tasks, while performing comparably on the remaining two.

With MAMMAL's structured prompt syntax, it can handle a variety of tasks including classification, regression, and generation. This versatility makes it an invaluable asset for researchers aiming to uncover new insights in the complex world of biomedical data.

MAMMAL in the Cure Cancer With AI API

Now that you understand the significance of the MAMMAL model, let’s explore how you can leverage its capabilities through our API. At Cure Cancer With AI, we are providing three key MAMMAL endpoints, each designed for specific predictions:

• Protein–Protein Interaction Prediction (/api/v1/mammal/ppi)
  This endpoint allows you to input two amino-acid sequences (protein_a and protein_b). The model will then return a binding-affinity class label of "1" if the proteins are predicted to interact, or "0" if they are not interacting. This can help researchers understand potential interactions between proteins, which is crucial for various biological processes.
• Drug–Target Interaction Prediction (/api/v1/mammal/dti)
  Using this endpoint, you can provide a target protein amino-acid sequence (target_seq) and a drug represented in SMILES notation (drug_seq). The model returns a predicted pKd value (−log₁₀ Kd), where a higher score indicates a stronger predicted binding affinity between the drug and the target protein. This information is essential for drug development and optimization.
• ClinTox Clinical-Trial Toxicity Prediction (/api/v1/mammal/clintox)
  This endpoint accepts a compound in SMILES notation (smiles) and returns a toxicity prediction. The prediction output includes a binary value (pred 1 = toxic/likely to fail trials, 0 = not toxic) and a raw score reflecting the confidence of the prediction. This can guide researchers in identifying compounds with potential safety concerns before entering clinical trials.

Each of these endpoints is designed to be simple to use, making it easier for researchers to integrate MAMMAL predictions into their workflows. Remember that these predictions are research signals and are not intended as medical or clinical advice.

Start Using It for Free

We invite you to take advantage of this groundbreaking opportunity! You can create a free API key at /api-keys. This key will allow you to make up to 100 requests per hour, providing you with valuable insights from the MAMMAL model. For all the details on how to use the API, including parameters and code samples, please visit /developers.

Conclusion

MAMMAL's inference capabilities are now available free to use on curecancerwithai.com. This powerful tool can significantly enhance your research in cancer and drug discovery. With MAMMAL, you can access cutting-edge predictions that will help you navigate the complexities of biomedical data.

As a reminder, while these predictions can provide valuable insights, they are intended as research signals and do not replace professional medical or clinical advice. The potential of MAMMAL is immense, and we look forward to seeing how it can support your research efforts!

To dive deeper into practical AI-for-cancer-research updates, explore our latest blog posts, learn more about our mission, and see how you can support ongoing work on our donations page.

Cure Cancer With AI is an educational research and information platform. It does not provide medical advice, diagnosis, or treatment recommendations; always discuss care decisions with a qualified healthcare professional.