We are thrilled to announce that the powerful Molecular Aligned Multi-Modal Architecture and Language (MAMMAL) AI model from IBM Research is now accessible for free through our public API at curecancerwithai.com. This innovative biomedical foundation model is designed to enhance cancer and drug-discovery research by integrating various biological data types—specifically proteins, small molecules, and single-cell gene/omics data—into a unified framework. In simpler terms, MAMMAL helps researchers analyze and predict interactions between biological components, paving the way for breakthroughs in treatment and drug development.

What is MAMMAL?

MAMMAL stands for "Molecular Aligned Multi-Modal Architecture and Language." It is a multi-task model that has been trained on approximately 2 billion biological samples across different modalities. This extensive training allows the model to handle a variety of tasks relevant to biomedical research, including predicting how proteins interact with each other and how drugs bind to their target proteins.

The significance of a multi-modal model like MAMMAL lies in its ability to represent proteins, small molecules, and transcriptomic data within a single framework. This unified approach can lead to more accurate predictions and insights, making it a valuable tool for researchers focused on drug discovery and cancer treatment. By leveraging the power of MAMMAL, scientists can gather critical information that may accelerate the development of new therapies.

Research Behind MAMMAL

The capabilities of MAMMAL are outlined in the research paper titled "MAMMAL — Molecular Aligned Multi-Modal Architecture and Language for biomedical discovery" published in npj Drug Discovery (Nature). In this comprehensive study, MAMMAL was evaluated on 11 diverse drug-discovery tasks, achieving state-of-the-art results on 9 of them and showing competitive performance on the remaining tasks. This impressive performance highlights MAMMAL's potential for advancing biomedical research, particularly in the areas of drug discovery and personalized medicine.

MAMMAL in the Cure Cancer With AI API

As part of our commitment to providing cutting-edge tools for researchers, we have integrated three MAMMAL API endpoints into our platform. Each endpoint serves a unique purpose, providing valuable predictions that can assist in your research endeavors:

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

These MAMMAL capabilities are now available free to use on curecancerwithai.com. This empowers researchers and developers to access advanced predictive analytics without the financial barrier. Simply create a free API key at /api-keys and explore full documentation, including parameters and code samples, at /developers. The free tier allows for up to 100 requests per hour per key, enabling you to harness the power of MAMMAL efficiently.

Start Using It for Free

Don't miss out on this opportunity to enhance your research with MAMMAL's sophisticated predictions. To get started, visit /api-keys to create your free API key, and dive into the documentation at /developers to learn how to integrate these powerful tools into your work.

In conclusion, we are excited to bring the advanced capabilities of the MAMMAL inference model to the research community at no cost. This initiative aligns with our mission to support innovative research in the fight against cancer and improve drug discovery processes. Please remember that while MAMMAL provides predictive insights, these predictions are research signals and should not be considered medical or clinical advice. We encourage you to leverage this invaluable resource as part of your research toolkit!

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.