Centered cross-context perturbation transfer on the public 2025 Virtual Cell Challenge benchmark
- 1AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China
Abstract
Predicting transcriptional responses across cellular contexts requires transferring both expression direction and differential-expression priority. We developed a compact numerical method that combines public perturbation summaries with a differential-expression kernel fitted to H1 CRISPRi training targets. The method centers an independent KOLF2.1J source on known training targets, transfers its response signs and magnitude ranks, and uses isotonic regression to render predicted expression means. We evaluated the frozen model retrospectively on the released public TEST100 of the 2025 Virtual Cell Challenge, using an external KOLF source released in 2026. The model achieved DES 0.371834, PDS 0.8614, and MAE 0.302206. With reconstructed historical anchors, its composite score was 0.341344, compared with the archived champion score of 0.340052, a difference of +0.001292. The comparison showed higher DES and lower PDS, with zero normalized MAE contributions for both methods. Source centering also improved development PDS across all three TRAIN folds and official VALIDATION. These results demonstrate a practical numerical approach to cross-context perturbation transfer and differential-expression ranking.
Related
- Where single-cell foundation models help: a benchmark of annotation, perturbation and regulatory inference against simple baselines
- Genetic Perturbation Prediction Models Fail Out-of-Distribution: A Rigorous Benchmark and Systematic Evaluation
- Context-dependent vitamin D immunoregulation: how a shared VDR-centered pathway generates distinct human immune outcomes
- RELAY: Relational In-Context Learning for Cellular Perturbation Prediction
- Do Vision CIL Methods Transfer to Protein? A Diagnostic Benchmark of Frozen Protein Encoders
BibTeX
@misc{luan2026centered,
title = {{Centered cross-context perturbation transfer on the public 2025 Virtual Cell Challenge benchmark}},
author = {H. Luan and L. Chen and G. Yu and Y. Yang},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.20.760514},
url = {https://www.biorxiv.org/content/10.64898/2026.10.20.760514v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Centered cross-context perturbation transfer on the public 2025 Virtual Cell Challenge benchmark
AU - H. Luan
AU - L. Chen
AU - G. Yu
AU - Y. Yang
PY - 2026
DA - 2026/10/20
PB - bioRxiv
DO - 10.64898/2026.10.20.760514
UR - https://www.biorxiv.org/content/10.64898/2026.10.20.760514v1
AB - Predicting transcriptional responses across cellular contexts requires transferring both expression direction and differential-expression priority. We developed a compact numerical method that combines public perturbation summaries with a differential-expression kernel fitted to H1 CRISPRi training targets. The method centers an independent KOLF2.1J source on known training targets, transfers its response signs and magnitude ranks, and uses isotonic regression to render predicted expression means. We evaluated the frozen model retrospectively on the released public TEST100 of the 2025 Virtual Cell Challenge, using an external KOLF source released in 2026. The model achieved DES 0.371834, PDS 0.8614, and MAE 0.302206. With reconstructed historical anchors, its composite score was 0.341344, compared with the archived champion score of 0.340052, a difference of +0.001292. The comparison showed higher DES and lower PDS, with zero normalized MAE contributions for both methods. Source centering also improved development PDS across all three TRAIN folds and official VALIDATION. These results demonstrate a practical numerical approach to cross-context perturbation transfer and differential-expression ranking.
ER -