PyTDC: A multimodal machine learning training, evaluation, and inference platform for biomedical foundation models
This provides a platform for researchers in biomedical AI to streamline development of multimodal foundation models, though it is incremental as it builds on existing infrastructure concepts.
The authors tackled the lack of end-to-end infrastructure for training, evaluating, and inferring multimodal biomedical AI models by developing PyTDC, an open-source platform that unifies data and model weights, and they demonstrated its utility in a case study on a single-cell drug-target nomination task, where a context-aware geometric deep learning method outperformed state-of-the-art baselines but failed to generalize to unseen cell types.
Existing biomedical benchmarks do not provide end-to-end infrastructure for training, evaluation, and inference of models that integrate multimodal biological data and a broad range of machine learning tasks in therapeutics. We present PyTDC, an open-source machine-learning platform providing streamlined training, evaluation, and inference software for multimodal biological AI models. PyTDC unifies distributed, heterogeneous, continuously updated data sources and model weights and standardizes benchmarking and inference endpoints. This paper discusses the components of PyTDC's architecture and, to our knowledge, the first-of-its-kind case study on the introduced single-cell drug-target nomination ML task. We find state-of-the-art methods in graph representation learning and domain-specific methods from graph theory perform poorly on this task. Though we find a context-aware geometric deep learning method that outperforms the evaluated SoTA and domain-specific baseline methods, the model is unable to generalize to unseen cell types or incorporate additional modalities, highlighting PyTDC's capacity to facilitate an exciting avenue of research developing multimodal, context-aware, foundation models for open problems in biomedical AI.