ORBIT: Learning Gene Program Co-Activation Structure for Cell-Type-Stratified Pathway Rewiring Analysis in Single-Cell Transcriptomics
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918479925346304 |
|---|---|
| author | Wang, Yuechen Jia, Lina Wang, Qinglong Tian, Feng |
| author_facet | Wang, Yuechen Jia, Lina Wang, Qinglong Tian, Feng |
| contents | Gene programs co-activate within cells, but existing single-cell methods either treat programs independently or require experimental perturbation data to model their interactions. We introduce ORBIT, a self-supervised transformer that learns asymmetric dependencies among gene programs from observational single-cell RNA-sequencing data alone, quantifying how strongly each program influences every other program. The key mechanism is an intervention-consistent training objective: the model learns each program's directional influence on every other program by predicting how the others change when that program is removed, yielding attention weights that reflect asymmetric influence rather than symmetric co-occurrence. Applied to 191,890 prefrontal cortex nuclei across three pathway vocabularies, ORBIT recovers co-activation structure consistent with established Alzheimer's disease vulnerability signatures, identifies cell-type-specific rewiring invisible to differential expression, and achieves 0.984 macro F1 on cell-type classification from 220 pathway scores, which is within 0.3 points of a state-of-the-art classifier using all 22,088 genes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02142 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ORBIT: Learning Gene Program Co-Activation Structure for Cell-Type-Stratified Pathway Rewiring Analysis in Single-Cell Transcriptomics Wang, Yuechen Jia, Lina Wang, Qinglong Tian, Feng Genomics Gene programs co-activate within cells, but existing single-cell methods either treat programs independently or require experimental perturbation data to model their interactions. We introduce ORBIT, a self-supervised transformer that learns asymmetric dependencies among gene programs from observational single-cell RNA-sequencing data alone, quantifying how strongly each program influences every other program. The key mechanism is an intervention-consistent training objective: the model learns each program's directional influence on every other program by predicting how the others change when that program is removed, yielding attention weights that reflect asymmetric influence rather than symmetric co-occurrence. Applied to 191,890 prefrontal cortex nuclei across three pathway vocabularies, ORBIT recovers co-activation structure consistent with established Alzheimer's disease vulnerability signatures, identifies cell-type-specific rewiring invisible to differential expression, and achieves 0.984 macro F1 on cell-type classification from 220 pathway scores, which is within 0.3 points of a state-of-the-art classifier using all 22,088 genes. |
| title | ORBIT: Learning Gene Program Co-Activation Structure for Cell-Type-Stratified Pathway Rewiring Analysis in Single-Cell Transcriptomics |
| topic | Genomics |
| url | https://arxiv.org/abs/2605.02142 |