ViBA

CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cells.

Zeng Y, Xie J, Shangguan N · Nature communications · 2025 · Article

10.1038/s41467-025-59926-5

Verified evidence

Model embedding comparison

723db3d3-bf81-536b-8272-48cfeef9d843
Gene expression and transcriptomicsPrediction or fitting error

Prediction source Version of record · PDF page(s) 4

Study b941a96f-bc07-505c-b868-d1eda8643419 · Prediction record (JSON)

Prediction fields

Endpoint
mean_square_error · PDF page(s) 4
Family
prediction_error · PDF page(s) 4
Role
prediction_error · PDF page(s) 4

Validation Direct comparison · Same source · Unknown · Supports · Matched conditions · Not reported

Model embedding comparison

8e2fabf0-088e-5b52-a9ed-2fbfaea7eb96
Gene expression and transcriptomics

Prediction source Version of record · PDF page(s) 4

Study b941a96f-bc07-505c-b868-d1eda8643419 · Prediction record (JSON)

Validation Direct comparison · Same source · Unknown · Supports · Matched conditions · Not reported