The model was open-sourced on Hugging Face and GitHub concurrent with its release as a bioRxiv preprint. (IMAGE)
Caption
That same year, Insilico collaborated with the Vadim N. Gladyshev Lab at Harvard Medical School to release Precious3GPT. As a true multimodal Transformer, the model integrated text, tabular data, and knowledge graph representations, covering four species, including mouse, rat, monkey, and human, and three omics modalities: transcriptomics, methylation, and proteomics. It could perform cross-species age prediction, target discovery, disease/tissue/sex classification, and compound sensitivity prediction within a unified framework. Its synthetic data generation used "biological age" as one of the conditional inputs, ensuring that generated omics data carried age and time labels.
Credit
Insilico Medicine
Usage Restrictions
None
License
Original content