Nicheformer is a transformer-based foundation model designed to integrate single-cell and spatial transcriptomics data, enabling the learning of a unified cell representation that accounts for local dependencies and underlying cell interactions in the cellular microenvironment. The model is pre-trained on a large corpus of over 110 million cells from both human and mouse tissues, combining dissociated single-cell and spatial transcriptomics data. Nicheformer is evaluated on a variety of downstream tasks, including spatial density prediction, niche and region label prediction, and neighborhood composition prediction. The results demonstrate that Nicheformer can accurately transfer spatial context from spatial transcriptomics data to dissociated single-cell data, enhancing the understanding of cellular heterogeneity and tissue microenvironments. The model's ability to capture nuanced spatial information and transfer spatial annotations to dissociated data highlights its potential for advanced single-cell and spatial omics analysis.Nicheformer is a transformer-based foundation model designed to integrate single-cell and spatial transcriptomics data, enabling the learning of a unified cell representation that accounts for local dependencies and underlying cell interactions in the cellular microenvironment. The model is pre-trained on a large corpus of over 110 million cells from both human and mouse tissues, combining dissociated single-cell and spatial transcriptomics data. Nicheformer is evaluated on a variety of downstream tasks, including spatial density prediction, niche and region label prediction, and neighborhood composition prediction. The results demonstrate that Nicheformer can accurately transfer spatial context from spatial transcriptomics data to dissociated single-cell data, enhancing the understanding of cellular heterogeneity and tissue microenvironments. The model's ability to capture nuanced spatial information and transfer spatial annotations to dissociated data highlights its potential for advanced single-cell and spatial omics analysis.