We are excited to announce that Cure Cancer With AI now offers free access to the IBM MAMMAL (Molecular Aligned Multi-Modal Architecture and Language) biomedical foundation model through our public API. Developed by IBM Research, MAMMAL is a cutting-edge multi-modal model that integrates information from proteins, small molecules, and gene/omics data. This powerful tool aims to advance cancer research and drug discovery, making it easier for researchers to explore the complexities of biological systems.

What is MAMMAL and Why Does It Matter?

MAMMAL stands for "Molecular Aligned Multi-Modal Architecture and Language." This innovative model is designed to work across various types of biological data, seamlessly bridging the gap between proteins, small molecules, and transcriptomic data. The ability to combine these different modalities into a unified framework is crucial for enhancing the understanding of biological interactions, especially in the context of cancer research and drug discovery.

The significance of a multi-modal biomedical foundation model like MAMMAL lies in its potential to accelerate discoveries in the fight against cancer. By integrating multiple sources of biological information, MAMMAL can provide insights into how different proteins interact, how drugs target specific proteins, and what potential toxicity a compound may carry. This comprehensive approach is a game-changer for researchers seeking to develop effective therapies.

The Research 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 landmark study highlights the model's training on approximately 2 billion biological samples across diverse modalities. MAMMAL was rigorously evaluated on 11 different drug-discovery tasks, achieving state-of-the-art results on 9 of them, while performing comparably on the remaining 2 tasks. This impressive performance underscores MAMMAL's potential to transform the landscape of drug discovery and biomedical research.

MAMMAL in the Cure Cancer With AI API

Cure Cancer With AI now serves MAMMAL's predictive capabilities through three dedicated API endpoints. Each endpoint provides unique insights that can help enhance research efforts:

• Protein–Protein Interaction Prediction (POST /api/v1/mammal/ppi): This endpoint allows users to input two amino-acid sequences representing proteins (protein_a and protein_b). MAMMAL predicts whether these two proteins interact by returning a binding-affinity class label of "1" (interacting) or "0" (non-interacting). This functionality can help researchers understand critical protein interactions involved in cancer pathways.
• Drug–Target Interaction (POST /api/v1/mammal/dti): In this endpoint, users provide a target protein amino-acid sequence (target_seq) and a drug represented in SMILES notation (drug_seq). MAMMAL predicts the binding strength between the drug and target protein by returning a predicted pKd value (−log₁₀ Kd). Higher pKd values indicate stronger predicted binding, which is essential for drug design and development.
• ClinTox Clinical-Trial Toxicity Prediction (POST /api/v1/mammal/clintox): This endpoint lets users input a compound in SMILES notation (smiles) to receive a toxicity prediction. MAMMAL returns a prediction score of "1" for toxic/likely to fail in trials and "0" for not toxic, along with a raw score. This information is vital for assessing the safety of drugs in clinical trials.

All three MAMMAL endpoints are available for free on curecancerwithai.com, providing researchers with powerful tools to advance their work without financial barriers.

Start Using It for Free

Getting started with the MAMMAL API is easy! Simply create a free API key at /api-keys. With this API key, you can make up to 100 requests per hour, allowing you to explore the capabilities of MAMMAL without any cost. For detailed information about the API endpoints, including parameters and code samples, visit our documentation at /developers.

Conclusion

The MAMMAL inference capability is now available for free on curecancerwithai.com, empowering researchers with cutting-edge tools for drug discovery and cancer research. With its state-of-the-art predictions and seamless integration of multi-modal data, MAMMAL represents a significant advancement in the field. Remember, the predictions generated by MAMMAL serve as research signals and should not be considered medical advice or used as clinical recommendations.

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.