At Cure Cancer With AI, we are excited to announce that we now offer access to the groundbreaking IBM MAMMAL (Molecular Aligned Multi-Modal Architecture and Language) through our free public API. Developed by IBM Research, MAMMAL is a state-of-the-art biomedical foundation model designed to accelerate drug discovery and cancer research. This multi-modal model processes data across proteins, small molecules, and gene/omics data, making it a vital tool for researchers aiming to uncover new insights in biomedical science.

What is MAMMAL and Why Does it Matter?

MAMMAL stands out as a multi-modal biomedical foundation model that integrates various biological data types into a unified framework. This means it can analyze and generate insights from different kinds of biological information, such as amino acid sequences of proteins, chemical structures of small molecules, and transcriptomic data derived from gene expression studies. The ability to work across these multiple modalities allows researchers to explore complex biological interactions and relationships more effectively.

The significance of a model like MAMMAL in cancer and drug-discovery research cannot be overstated. By leveraging a comprehensive understanding of biological data, scientists can identify potential drug targets, predict interactions between drugs and proteins, and assess the safety profiles of compounds—all crucial steps in developing new therapies. MAMMAL is designed to enhance our understanding of these processes, ultimately contributing to the fight against cancer.

Research Behind MAMMAL

The capabilities of the MAMMAL model are detailed in a research paper published in npj Drug Discovery, a journal from Nature. The paper outlines how MAMMAL was trained on approximately 2 billion biological samples, covering a wide array of biological modalities. It was evaluated across 11 diverse drug-discovery tasks and achieved state-of-the-art results on 9 of those tasks, demonstrating its robustness and versatility in the field of biomedical research. For a deeper dive into the technical details and findings, you can explore the full paper here.

MAMMAL in the Cure Cancer With AI API

Now available through our free public API, MAMMAL offers three powerful endpoints that provide predictions vital for drug discovery:

• Protein–Protein Interaction Prediction (PPI):

  Endpoint: /api/v1/mammal/ppi
  This endpoint takes two amino acid sequences, protein_a and protein_b, as inputs. It predicts whether the two proteins interact by returning a binding-affinity class label of "1" (indicating they interact) or "0" (indicating no interaction).

• Drug–Target Interaction Prediction (DTI):

  Endpoint: /api/v1/mammal/dti
  This endpoint requires a target protein's amino acid sequence (target_seq) and a drug represented in SMILES notation (drug_seq). It returns a predicted pKd value, which indicates the strength of the binding; a higher pKd implies a stronger predicted interaction between the drug and the target protein.

• ClinTox Clinical-Trial Toxicity Prediction:

  Endpoint: /api/v1/mammal/clintox
  For this endpoint, users input a compound in SMILES notation (smiles). The API predicts the toxicity of the compound, returning a binary prediction (1 for toxic/likely to fail trials and 0 for not toxic) along with a raw toxicity score.

All of these endpoints are accessible for free at curecancerwithai.com. You can leverage MAMMAL's powerful predictions to enhance your research and drug discovery efforts.

Start Using It for Free

Getting started with the MAMMAL API is simple! Anyone can create a free API key by visiting /api-keys. With this key, you can make up to 100 requests per hour, allowing you to explore the capabilities of this innovative model without any cost. For full documentation, parameters, and code samples, head over to /developers.

Conclusion

The IBM MAMMAL AI model is now freely available to researchers and developers through the Cure Cancer With AI API. This powerful tool provides essential predictions that can aid in drug discovery and cancer research. Remember, while MAMMAL offers valuable insights, the predictions generated are research signals and should not be considered medical or clinical advice. Join us in exploring the possibilities and advancing the science of cancer treatment!

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.