AI tech company Bioptimus has signed a partnership with one of France’s leading academic cancer research organisations in efforts to build an AI model of biology. 

The partnership with the Fédération Francophone de Cancérologie Digestive (FFCD) will grant Bioptimus access to a unique cohort of deeply phenotyped clinical trial data from more than 3,000 gastrointestinal (GI) cancer patients.  

Bioptimus will integrate the data, enriched with spatial omics, into STELA (Spatial Tissue Embedding Learning Atlas), the company’s global initiative to build the world’s largest clinically linked, multimodal tissue atlas.  

Under the agreement, the FFCD gains access to Bioptimus’s M-Optimus multimodal foundation model and Bioptimus will sponsor the generation of new spatial transcriptomics data on their patient cohorts.  

This additional data will measure and map gene activity within a tissue sample, enabling researchers to use AI on routine pathology slides to predict missing gene expression data directly from the image, effectively mapping out molecular signatures within the tumour. 

FFCD retains full ownership of the generated data – which it will share with Bioptimus – and will have access to all newly generated spatial omics data produced under the collaboration for use in its own research programmes. 

Bioptimus says the agreement represents the largest GI cancer spatial omics atlas generated to date. 

“High-quality clinical data is the key to building a foundation AI model in biotechnology and this agreement will boost vital precision oncology research and patient health,” said David Cahané, Co-Founder and Managing Director of Bioptimus. 

“The FFCD data brings European disease biology into STELA adding distinct cultural and genomic backgrounds that will sharpen M-Optimus’s ability to generalise across the global population.  

“It also anchors STELA’s GI cancer coverage in the kind of high-quality, outcome-linked clinical data that spatial atlases rarely include.”