We are excited to announce that the IBM MAMMAL AI model is now accessible for free through the Cure Cancer With AI public API! MAMMAL, which stands for "Molecular Aligned Multi-Modal Architecture and Language," is a cutting-edge biomedical foundation model designed to advance research in drug discovery and cancer treatment. Developed by IBM Research, MAMMAL integrates a wealth of biological data, making it a powerful tool for researchers and innovators in the biomedical field.

But what does "multi-modal" mean in this context? Simply put, MAMMAL can analyze and interpret various types of biological data, including proteins, small molecules, and gene/omics information. This capability is crucial for drug discovery and cancer research, as it allows scientists to draw connections between different biological elements and identify potential therapeutic targets or treatment pathways.

The Research Behind MAMMAL

MAMMAL's capabilities are grounded in extensive research, detailed in the paper titled "MAMMAL — Molecular Aligned Multi-Modal Architecture and Language for biomedical discovery", published in npj Drug Discovery. The model has been trained on approximately 2 billion biological samples across multiple modalities and evaluated on 11 diverse drug-discovery tasks. Impressively, MAMMAL achieved new state-of-the-art results in 9 of these tasks, demonstrating its effectiveness and reliability in the complex landscape of drug discovery.

This rigorous training and evaluation process ensures that MAMMAL can provide valuable insights into protein interactions, drug-target affinities, and even clinical trial toxicity predictions. By leveraging such a robust foundation, researchers can explore new avenues in cancer treatment and drug development.

MAMMAL in the Cure Cancer With AI API

Now, let’s dive into how you can harness the power of MAMMAL through our public API. We have integrated three specific endpoints, each tailored to provide unique insights into various aspects of biomedical research:

• POST /api/v1/mammal/ppi — This endpoint focuses on protein–protein interactions. By providing two amino-acid sequences (referred to as protein_a and protein_b), you will receive a binding-affinity class label in return. The output will indicate whether the proteins are interacting (label "1") or not interacting (label "0"). This information is essential for understanding the complex networks of cellular interactions that underpin cancer biology.
• POST /api/v1/mammal/dti — This endpoint is designed for drug–target interaction predictions. By inputting a target protein amino-acid sequence (called target_seq) and a drug represented in SMILES notation (called drug_seq), you will receive a predicted pKd value, which is a measure of the binding affinity between the drug and the target. A higher pKd indicates a stronger predicted binding, which is crucial for drug development and optimization.
• POST /api/v1/mammal/clintox — The ClinTox endpoint assesses clinical trial toxicity. By submitting a compound in SMILES notation (referred to as smiles), you’ll receive a toxicity prediction indicating whether the compound is likely to be toxic (pred 1 = toxic/likely to fail trials) or not toxic (0 = not toxic), along with a raw score. This prediction can help researchers evaluate the safety profiles of potential drug candidates before clinical trials begin.

All of these powerful predictions are available for free on CureCancerWithAI.com, and anyone can create a free API key at /api-keys. The free tier allows for up to 100 requests per hour per key, making it easy for researchers to explore the capabilities of MAMMAL without any financial barriers. For more detailed information on how to use the API, including parameters and code samples, please visit our documentation at /developers.

Start Using It for Free

Getting started with MAMMAL predictions is straightforward! To begin, simply create your free API key at /api-keys. Once you have your key, you can access the endpoints and start making predictions. Don't forget to check out the full documentation at /developers to ensure you’re using the API to its full potential. Remember, the free tier allows up to 100 requests per hour, making this an excellent opportunity to dive into advanced biomedical research!

Conclusion

With MAMMAL inference now available for free on CureCancerWithAI.com, we are empowering researchers and innovators to unlock new insights in drug discovery and cancer research. Take advantage of this opportunity to explore the capabilities of the IBM MAMMAL model through our API. However, please remember that while these predictions are valuable research signals, they are not medical or clinical advice and should not be interpreted as definitive diagnoses or treatment plans.

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.