We are thrilled to announce that Cure Cancer With AI now offers free access to the IBM MAMMAL biomedical foundation model through our public API. Developed by IBM Research, MAMMAL stands for "Molecular Aligned Multi-Modal Architecture and Language," and it is designed to accelerate biomedical discovery by integrating various types of biological data. This multi-modal framework is particularly significant for cancer and drug-discovery research, enabling researchers to better understand the complex interactions between proteins, small molecules, and genomic information.

What is MAMMAL and Why Does It Matter?

MAMMAL represents a groundbreaking approach to biomedical modeling, as it processes and interprets data from multiple sources—namely proteins, small molecules, and single-cell gene/omics data. By aligning these diverse data types into a unified sequence framework, MAMMAL allows researchers to generate more accurate predictions about biological interactions and drug efficacy. This capability is vital for advancing cancer research and drug discovery, where understanding the intricate relationships between various biological entities can lead to more effective therapies.

The Research Behind MAMMAL

The capabilities of MAMMAL are underpinned by extensive research, as detailed in the paper published in npj Drug Discovery (Nature). Trained on approximately 2 billion biological samples, MAMMAL was evaluated on 11 diverse drug-discovery tasks, achieving state-of-the-art results in 9 of them. This impressive performance showcases MAMMAL's ability to handle complex biomedical challenges and reinforces its role as a powerful tool for researchers seeking to make groundbreaking discoveries in the field.

MAMMAL in the Cure Cancer With AI API

We are excited to provide three specific MAMMAL endpoints in our free public API, enabling users to make predictions in distinct areas of biomedical research. Each endpoint is designed to handle different types of queries and returns valuable insights based on the input data provided.

• Protein–Protein Interaction Prediction (PPI): The endpoint /api/v1/mammal/ppi allows you to input two amino-acid sequences (designated as protein_a and protein_b). It returns a binding-affinity class label of "1" (indicating that the proteins interact) or "0" (indicating no interaction). This information is crucial for understanding molecular pathways in cancer research.
• Drug–Target Interaction (DTI): With the endpoint /api/v1/mammal/dti, users can submit a target protein amino-acid sequence (target_seq) alongside a drug represented in SMILES notation (drug_seq). The API provides a predicted pKd value (the negative logarithm of the dissociation constant, Kd), where a higher pKd indicates stronger predicted binding between the drug and target protein. This prediction is invaluable for drug design and optimization.
• ClinTox Clinical-Trial Toxicity: The endpoint /api/v1/mammal/clintox predicts the potential toxicity of a compound based on its SMILES notation (smiles). The output includes a toxicity prediction (with values "1" indicating toxic/likely to fail trials and "0" indicating not toxic) along with a raw score. This information can help researchers assess the viability of compounds before entering costly clinical trials.

Start Using It for Free!

The best part? All of these MAMMAL capabilities are available to you at no cost through the Cure Cancer With AI platform! Anyone can create a free API key at /api-keys and start making requests immediately. Our API allows for 100 requests per hour per key, making it easy for researchers to leverage this powerful tool for their work. For additional information on how to use the API, including parameters and code samples, please visit our documentation at /developers.

Conclusion

We are excited to offer the advanced capabilities of the IBM MAMMAL biomedical foundation model for free on curecancerwithai.com. This unique resource empowers researchers to make significant strides in the fields of cancer research and drug discovery. Please remember that while the predictions generated by MAMMAL are incredibly valuable, they are research signals and should not be considered medical or clinical advice. Start exploring the potential of MAMMAL today!

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.