In an exciting development for the biomedical research community, Cure Cancer With AI is now offering free access to the groundbreaking IBM MAMMAL AI through our public API. Built by IBM Research, MAMMAL stands for "Molecular Aligned Multi-Modal Architecture and Language." This innovative multi-modal biomedical foundation model is designed to enhance drug discovery and cancer research by integrating data across proteins, small molecules, and gene/omics information.

So, what exactly does it mean to be a multi-modal biomedical foundation model? In simple terms, MAMMAL can analyze and unify different types of biological data, which is essential for understanding complex interactions in drug discovery. By leveraging this model, researchers can gain insights into how proteins interact, how drugs target specific proteins, and the potential toxicity of compounds, all of which are critical elements in the fight against cancer.

The Research Behind MAMMAL

The capabilities of MAMMAL are based on extensive research documented in the paper titled "MAMMAL — Molecular Aligned Multi-Modal Architecture and Language for biomedical discovery," published in npj Drug Discovery (Nature). This state-of-the-art model has been trained on approximately 2 billion biological samples across multiple modalities. It was evaluated on 11 diverse drug-discovery tasks and achieved new state-of-the-art results on 9 of those tasks, demonstrating its exceptional performance and reliability in the field.

The breadth of MAMMAL's training data and its ability to handle various biological inputs make it a powerful tool for researchers. By representing proteins, small molecules, and transcriptomic data in a unified sequence framework, it can support a wide range of research applications, from fundamental biology to advanced drug discovery.

MAMMAL in the Cure Cancer With AI API

Cure Cancer With AI is thrilled to provide access to MAMMAL's predictive capabilities through three dedicated API endpoints. Each endpoint serves a unique purpose, allowing researchers to explore protein interactions, drug-target interactions, and potential clinical toxicity. Here’s a breakdown of what each endpoint does and how to use them:

• Protein–Protein Interaction Prediction (/api/v1/mammal/ppi): This endpoint takes two amino-acid sequences (representing two proteins) as input. Based on this data, it predicts whether the proteins interact with each other, returning a binding-affinity class label of "1" (interacting) or "0" (non-interacting).
• Drug–Target Interaction Prediction (/api/v1/mammal/dti): For researchers focused on drug development, this endpoint allows users to input a target protein's amino-acid sequence along with a drug in SMILES notation (a way to represent chemical structures). The output is a predicted pKd value (−log₁₀ Kd), where a higher number indicates stronger predicted binding between the drug and the target protein.
• ClinTox Clinical-Trial Toxicity Prediction (/api/v1/mammal/clintox): This endpoint helps assess the safety of compounds by taking a compound's SMILES notation as input. It predicts whether the compound is likely to be toxic (pred 1 = toxic/likely to fail trials) or not (0 = not toxic), along with a raw toxicity score.

All of these MAMMAL capabilities are available FREE to use on curecancerwithai.com. Anyone interested can create a free API key at /api-keys and access detailed documentation, parameters, and code samples at /developers. The free tier allows up to 100 requests per hour per key, making it accessible for researchers and developers alike.

Start Using It for Free

Don’t miss out on the opportunity to leverage MAMMAL's powerful predictive capabilities in your research. To get started, simply create your free API key at /api-keys and dive into the full documentation available at /developers. With this robust tool at your fingertips, you can enhance your understanding of protein interactions, drug efficacy, and potential toxicity, all at no cost.

Conclusion

We are excited to announce that MAMMAL inference is now available free to use on curecancerwithai.com. By providing access to this advanced AI model, we hope to foster innovation and collaboration in the biomedical research community. Please remember that while MAMMAL's predictions are incredibly valuable as research signals, they do not constitute medical or clinical advice. Always consult a healthcare professional for medical guidance.

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.