Subcellular location of proteins based on immunofluorescently stained cells. The tab-separated file includes the following columns: Ensembl gene identifier ("Gene"), name of gene ("Gene name"), gene reliability score ("Reliability"), enhanced locations ("Enhanced"), supported locations ("Supported"), Approved locations ("Approved"), uncertain locations ("Uncertain"), locations with single-cell variation in intensity ("Single-cell variation intensity"), locations with spatial single-cell variation ("Single-cell variation spatial"), locations with observed cell cycle dependency (type can be one or more of biological definition, custom data or correlation) ("Cell cycle dependency"), Gene Ontology Cellular Component term identifier ("GO id"). The data is based on The Human Protein Atlas version 25.0 and Ensembl version 109.

subcellular_location.tsv.zip

SubCell is a suite of vision foundation models designed to represent single-cell biology including morphology and subcellular protein localization from fluorescence microscopy images (Gupta et al., bioRxiv, 2024). The models are trained on images from the standard ICC-IF assay of the subcellular resource. This file is a pytorch-file listing meta data, protein localization predictions from SubCell, and SubCell embedding features for each single cell in the standard ICC-IF images from the subcellular resource. The HPA-Cell-Segmentator (https://github.com/CellProfiling/HPACellSegmentatorPortable) was used for segmentation and single-cell cropping. The all channel version (DNA, MT, ER + Protein) of the SubCell model MAE-CellS-ProtS-Pool (https://github.com/CellProfiling/SubCellPortable) was applied.

subcell_embeddings.zip