BiomedSciAI
Our mission is to accelerate scientific discovery in Biomedical Sciences through a variety of tools that can help scientists do their research quicker and more effectively.
Whether you use population-scale data like EHRs, body-part data like medical imaging, subcellullar-scale data like spatially resolved omics, or a combination of various modalities, we host tools that will help you make the most out of it.
If you want to contribute and get involved check out the guidelines of the repository of your interest and our code of conduct.
We have plenty of stuff you can do with BiomedSciAI. A good starting point is to check out the pinned repositories. You can find all implementation details and some examples in the docs.
Try out the examples in the repositories that we prepared for various applications.
Pinned Loading
Repositories
- biomed-multi-alignment Public
We introduce ibm/biomed.omics.bl.sm.ma-ted-458m. A biomedical foundation model trained over 2 billion biological samples across multiple modalities, including proteins, small molecules, and single-cell gene data.
- fuse-med-ml Public
A python framework accelerating ML based discovery in the medical field by encouraging code reuse. Batteries included :)
- biomed-multi-view Public
This repository contains the implementation of the Multi-view Molecular Embedding with Late Fusion (MMELON) architecture. MMELON combines molecular representations from three views — image, graph, and text —to learn a joint embedding that can be finetuned for downstream tasks in chemical and biological property prediction.
- genet Public
- biomed-llm Public
Representation Alignment of Biomedical Modalities to LLMs for Multi-Modal Reasoning
- r-BRICS Public
Revised breaking of retrosynthetically interesting chemical substructures (r-BRICS) – a revised BRICS module based on rdKit that breaks ring structures and carbon chains
Top languages
Loading…
Most used topics
Loading…