Kalfon et al. |

scPRINT: Cell Type Annotation

Apps are being retired soon. Locus, our AI co-scientist, can now take you from research question to results in a single conversation: it plans the analysis, runs the right tools on your data, and helps you interpret the findings. Just describe what you want to explore to get started.

Try Locus →
92
1
Omics
    More
Step 1: Upload your data

Upload Single Cell RNA-Seq h5ad File

Drag your file(s) or upload
  • Your file can be in the following formats:h5ad
    • The h5ad format in scRNA-seq refers to the Hierarchical Data Format 5 (HDF5) Annotated Data format. It is commonly used to store single-cell gene expression data.
Step 2: Set Parameters
None
-1
-1
5000
-1
-1
5000
most var
Step 3: Complete run profile

scPRINT (v1.6.0) is a large transformer model specifically designed for single-cell RNA sequencing (scRNA-seq) data analysis. This transformer-based model aids in gene network inference, which helps researchers understand the interactions between genes within single cells. Its capabilities include denoising scRNA-seq data (improving signal clarity), generating cell embeddings (condensed representations of cell types or states), and predicting labels for various cellular attributes, such as cell type, disease state, or origin of samples.

Example use case: Cell Type Annotation

Technology: Transformers

Limitation:

  • Some of the parameters were kept default. Please see this page for more details.
  • Only human datasets were tested.
Citation:
scPRINT: pre-training on 50 million cells allows robust gene network predictions Jérémie Kalfon, Jules Samaran, Gabriel Peyré, Laura Cantini bioRxiv 2024.07.29.605556; doi: https://doi.org/10.1101/2024.07.29.605556
Released:
Nov-12-2024
Previous Job Parameters
Your previous job parameters will show up here
so you can keep track of your jobs