scBench-Long is a benchmark with 21 evaluations where the strongest AI model-harness pair succeeds on 25.4% of long-horizon single-cell biology tasks.
Best practices for single-cell analysis across modalities
3 Pith papers cite this work, alongside 1,052 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1,052
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
A pathway-constrained autoencoder extended to multi-omics integration improves breast cancer stratification and provides interpretable pathway activity scores.
DINO-based ViT models pretrained on HPA FOV achieve macro F1 of 0.822 zero-shot and 0.860 after fine-tuning for protein localization on OpenCell, demonstrating effective transfer from SSL pretraining.
citing papers explorer
-
scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology
scBench-Long is a benchmark with 21 evaluations where the strongest AI model-harness pair succeeds on 25.4% of long-horizon single-cell biology tasks.
-
Biologically Informed Deep Neural Networks for Multi-Omic Integration, Pathway Activity Inference and Risk Stratification in Cancer
A pathway-constrained autoencoder extended to multi-omics integration improves breast cancer stratification and provides interpretable pathway activity scores.
-
Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization
DINO-based ViT models pretrained on HPA FOV achieve macro F1 of 0.822 zero-shot and 0.860 after fine-tuning for protein localization on OpenCell, demonstrating effective transfer from SSL pretraining.