We are thrilled to announce that Cure Cancer With AI now supports predictions from the IBM MAMMAL (Molecular Aligned Multi-Modal Architecture and Language) biomedical foundation model through our free public API. Developed by IBM Research, MAMMAL is a groundbreaking multi-modal model designed to transform drug discovery and cancer research by integrating diverse biological data types, including proteins, small molecules, and gene/omics data.

But what does "multi-modal" mean, and why is it important? In simple terms, a multi-modal model can analyze and understand different types of biological information simultaneously. This capability is crucial for cancer and drug-discovery research, where the interplay between various biological components can be complex and nuanced. MAMMAL’s unique architecture allows researchers to gain deeper insights into molecular interactions and drug efficacy, paving the way for targeted therapies and improved patient outcomes.

Research Behind MAMMAL

The efficacy of MAMMAL is backed by rigorous research detailed in the paper published in npj Drug Discovery (Nature). This state-of-the-art model was trained on approximately 2 billion biological samples, covering a wide array of biological modalities. In its evaluation, MAMMAL was tested on 11 diverse drug-discovery tasks and achieved new state-of-the-art results on 9 of them, demonstrating its robust predictive capabilities.

By harnessing the power of multi-task learning and advanced data representations, MAMMAL not only excels in predicting protein interactions and drug-target affinities but also addresses critical challenges in the realms of toxicity prediction and drug efficacy. This research positions MAMMAL as a transformative tool for accelerating drug discovery and enhancing our understanding of complex biological systems.

MAMMAL in the Cure Cancer With AI API

With MAMMAL now integrated into the Cure Cancer With AI API, researchers and developers can access its powerful predictions for free. We offer three main endpoints that serve different purposes:

• Protein–Protein Interaction Prediction: /api/v1/mammal/ppi
  This endpoint helps researchers determine whether two given proteins interact. You will need to provide two amino-acid sequences (protein_a and protein_b) as input. The model returns a binding-affinity class label of "1" if the proteins are predicted to interact or "0" if they do not interact.
• Drug–Target Interaction: /api/v1/mammal/dti
  This endpoint predicts the interaction between a specific drug and a target protein. You must provide the target protein's amino-acid sequence (target_seq) and the drug in SMILES notation (drug_seq). The output will be a predicted pKd value (−log₁₀ Kd), where a higher value indicates a stronger predicted binding affinity between the drug and the target protein.
• ClinTox Clinical-Trial Toxicity Prediction: /api/v1/mammal/clintox
  This endpoint assesses the potential toxicity of a compound during clinical trials. To use it, input the compound in SMILES notation (smiles). The model will return a toxicity prediction (pred 1 = toxic/likely to fail trials, 0 = not toxic) along with a raw toxicity score.

These MAMMAL capabilities are now available for free use on curecancerwithai.com. Each API key allows up to 100 requests per hour, making it both accessible and practical for various research needs.

Start Using It for Free

Getting started with the MAMMAL API is easy! Simply create a free API key at /api-keys and dive into our detailed documentation at /developers. The documentation includes information on parameters, example requests, and response formats, so you can seamlessly integrate MAMMAL predictions into your research workflow.

Conclusion

With MAMMAL’s advanced predictive capabilities now available for free on curecancerwithai.com, researchers have a powerful tool at their fingertips to enhance their drug discovery efforts. Whether you are interested in protein interactions, drug-target affinities, or toxicity predictions, MAMMAL can help illuminate the complexities of biomedical research.

As a reminder, please note that the predictions generated by MAMMAL are research signals and should not be considered medical or clinical advice. We encourage you to explore this innovative API and contribute to the ongoing fight against cancer.

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.