We are excited to announce that the groundbreaking IBM MAMMAL (Molecular Aligned Multi-Modal Architecture and Language) is now available for free through the Cure Cancer With AI public API. Developed by IBM Research, MAMMAL is a state-of-the-art biomedical foundation model designed to enhance cancer and drug-discovery research. This multi-modal model effectively integrates data from proteins, small molecules, and gene/omics information, providing valuable insights for researchers worldwide.

What is MAMMAL and Why Does It Matter?

MAMMAL stands for "Molecular Aligned Multi-Modal Architecture and Language." It is a sophisticated model that has been trained on approximately 2 billion biological samples across various modalities, including proteins, small molecules, and single-cell gene/omics data. This multi-modal approach allows researchers to gain deeper insights into the complex interactions that underlie biological processes, making it a crucial tool in the fight against diseases like cancer.

The significance of a multi-modal biomedical foundation model lies in its ability to unify disparate types of biological data into a cohesive framework. MAMMAL represents proteins and small molecules in a structured sequence format, which enables it to perform a range of tasks, including classification, regression, and generation. This versatility is vital for drug discovery and understanding disease mechanisms, allowing scientists to make informed decisions based on comprehensive data analysis.

The Research Behind MAMMAL

The capabilities of MAMMAL are detailed in the research paper published in npj Drug Discovery (Nature), titled MAMMAL — Molecular Aligned Multi-Modal Architecture and Language for biomedical discovery. In this study, MAMMAL was evaluated on 11 diverse drug-discovery tasks and achieved new state-of-the-art results on 9 of them, with performance comparable to the best on the remaining 2 tasks. This remarkable performance underscores MAMMAL's potential to accelerate biomedical discoveries, particularly in the context of cancer research.

MAMMAL in the Cure Cancer With AI API

Now, researchers and developers can leverage MAMMAL's capabilities through the Cure Cancer With AI public API. Three specific endpoints have been designed to facilitate easy access to MAMMAL's predictions:

1. Protein–Protein Interaction Prediction: POST /api/v1/mammal/ppi

• Input: Two amino-acid sequences (protein_a and protein_b).
• Output: A binding-affinity class label, returning "1" if the proteins are likely to interact and "0" if they do not.

This endpoint allows researchers to explore potential interactions between proteins, which is crucial for understanding biological processes and pathways in cancer.

2. Drug–Target Interaction: POST /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), indicating the strength of binding between the drug and the target protein. A higher pKd value signifies a stronger predicted interaction.

This endpoint is particularly valuable for drug discovery, as it helps researchers identify promising drug candidates that may effectively target specific proteins involved in cancer.

3. ClinTox Clinical-Trial Toxicity Prediction: POST /api/v1/mammal/clintox

• Input: A compound in SMILES notation (smiles).
• Output: A toxicity prediction, returning "1" if the compound is likely toxic (and may fail clinical trials) or "0" if it is considered not toxic, along with a raw score for further analysis.

This endpoint assists researchers in evaluating the safety of compounds before they enter clinical trials, which is crucial for successful drug development.

Start Using It for Free!

We invite you to take advantage of the MAMMAL capabilities now available for free on curecancerwithai.com. To get started, simply create a free API key at /api-keys. You can make up to 100 requests per hour per key, making it an excellent opportunity for researchers and developers alike. For full documentation, parameters, and code samples, visit /developers.

Conclusion

The integration of IBM MAMMAL AI into the Cure Cancer With AI public API marks a significant advancement in accessible biomedical research tools. By making MAMMAL's predictive capabilities available for free, we aim to empower researchers in their quest for innovative solutions to combat cancer and enhance drug discovery processes. Remember, while MAMMAL's predictions provide valuable research signals, they are not a substitute for medical advice or clinical decisions.

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.