scFormer: A Universal Representation Learning Approach for Single-Cell Data Using Transformers
Bibliographic record
Abstract
A bstract Single-cell sequencing has emerged as a promising technique to decode cellular heterogeneity and analyze gene functions. With the high throughput of modern techniques and resulting large-scale sequencing data, deep learning has been used extensively to learn representations of individual cells for downstream tasks. However, most existing methods rely on fully connected networks and are unable to model complex relationships between both cell and gene representations. We hereby propose scFormer, a novel transformer-based deep learning framework to jointly optimize cell and gene embeddings for single-cell biology in an unsupervised manner. By drawing parallels between natural language processing and genomics, scFormer applies self-attention to learn salient gene and cell embeddings through masked gene modelling. scFormer provides a unified framework to readily address a variety of downstream tasks such as data integration, analysis of gene function, and perturbation response prediction. Extensive experiments using scFormer show state-of-the-art performance on seven datasets across the relevant tasks. The scFormer model implementation is available at https://github.com/bowang-lab/scFormer .
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".