We are thrilled to announce that the cutting-edge 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 represents a significant advancement in biomedical foundation models, offering researchers a powerful tool for cancer and drug-discovery research.

What is MAMMAL and Why Does it Matter?

MAMMAL is a multi-modal biomedical foundation model that unifies data from proteins, small molecules, and single-cell gene/omics studies into a single framework. This unification allows researchers to work across various biological datasets, facilitating more comprehensive analyses and insights. The term "multi-modal" refers to MAMMAL's ability to handle different types of biological data simultaneously, making it an invaluable asset in the quest to understand complex biological interactions, especially in the context of cancer research and drug discovery.

The significance of a model like MAMMAL cannot be overstated. It provides a structured and sophisticated approach to predicting interactions between proteins and small molecules, as well as assessing potential toxicity in clinical trials. This capability can streamline the drug discovery process, making it faster and more efficient, which is critical in the fight against cancer.

The Research Behind MAMMAL

The capabilities of MAMMAL are detailed in the research paper published in npj Drug Discovery, a journal of Nature. The model was trained on approximately 2 billion biological samples, covering a wide range of modalities. In its evaluation, MAMMAL was tested on 11 diverse drug-discovery tasks, achieving new state-of-the-art results on 9 of them, while performing comparably on the remaining 2 tasks. This impressive performance showcases the model's robustness and versatility in tackling complex biomedical challenges.

MAMMAL in the Cure Cancer With AI API

We are excited to integrate MAMMAL's capabilities into the Cure Cancer With AI API. Three powerful endpoints are now available for free, enabling researchers to access valuable predictions:

• Protein–Protein Interaction (PPI):
  • Endpoint: /api/v1/mammal/ppi
  • Input: Two amino-acid sequences representing the proteins (protein_a, protein_b).
  • Output: A binding-affinity class label: "1" (indicating the proteins interact) or "0" (indicating no interaction).
• Drug–Target Interaction (DTI):
  • Endpoint: /api/v1/mammal/dti
  • Input: A target protein amino-acid sequence (target_seq) and a drug in SMILES notation (drug_seq).
  • Output: A predicted pKd value (−log₁₀ Kd), where a higher value indicates a stronger predicted binding affinity.
• ClinTox Clinical-Trial Toxicity:
  • Endpoint: /api/v1/mammal/clintox
  • Input: A compound in SMILES notation (smiles).
  • Output: A toxicity prediction, with "1" indicating the compound is toxic or likely to fail trials, and "0" indicating it is not toxic, along with a raw score.

These endpoints provide essential predictions that can aid in research and facilitate drug discovery processes. Best of all, all of this is available for free on curecancerwithai.com.

Start Using It for Free

Getting started with the MAMMAL API is simple! You can create a free API key at /api-keys and view full documentation, including parameters and code samples, at /developers. The free tier allows for 100 requests per hour per key, making it accessible for researchers and developers alike. Remember, calls are authenticated with an "Authorization: Bearer ccw_live_..." header and must remain server-side.

Conclusion

With the introduction of MAMMAL capability through our free public API, Cure Cancer With AI is empowering researchers with state-of-the-art tools for biomedical discovery. We encourage you to take advantage of this opportunity to explore the potential of MAMMAL in your own research. Keep in mind that while MAMMAL provides valuable predictions, they are research signals and should not be interpreted as medical advice or guarantees of clinical outcomes.

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.