xNNPCD identifies regulators of programmed cell death by integrating perturbation transcriptomes with cancer dependency profiles
Abstract
Programmed cell death (PCD) encompasses regulated processes whose dysregulation shapes cancer fitness, yet computational studies use known PCD genes for prognosis rather than discovering regulators. We developed xNNPCD, an interpretable neural-network framework that links CRISPR–Cas9 perturbation signatures from CMap to gene dependency profiles from DepMap. The model constrains hidden neurons to five PCD pathways and iteratively refines a prior gene–PCD pathway mask matrix derived from GO, KEGG, and Reactome using pathway–neuron ablation. This converts binary gene–pathway relationships into continuous-valued associations and improves dependency prediction over random forests, fully connected multi-layer perceptrons, and its own non-iterative variant. The learned mask matrix recovers annotated death regulators and nominates candidate regulators, including RPL23A, HSPA5, SNRPA1, SLC6A2, and ASAH1; combined with dependency scores, it separates pathway coupling from regulatory direction. Transferring the refined mask matrix and learned weights to compound-induced perturbation data enables in silico drug screening, identifying BRD-K19103580 and decitabine as therapeutic agents for apoptosis and ferroptosis, respectively. The pathway-resolved drug profiles can facilitate the design of combination therapies targeting complementary PCD pathways to overcome single-pathway resistance. Overall, xNNPCD offers a pan-cancer, interpretable approach that generalizes across perturbation modalities for mapping the regulatory landscape and elucidating the molecular processes of PCD in cancer.
Related
- Integrating single-cell and bulk transcriptomes identifies neuronal heat-stress-associated candidate genes in a reef-building coral
- Cross-platform comparison of diabetic foot ulcer transcriptomes identifies partially concordant disease-associated signals
- A genome-wide CRISPR knockout screen identifies host dependency factors and potential viral-induced cell death regulators for porcine deltacoronavirus infection
- A chemical perturbation scan on a K2P channel modulator pocket identifies affinity hotspots
- Integrating metabolomic and transcriptomic analyses to identify candidate genes and transcriptional regulators associated with triterpenoid saponin accumulation in developing Momordica charantia fruits
BibTeX
@article{yin2026xnnpcd,
title = {{xNNPCD identifies regulators of programmed cell death by integrating perturbation transcriptomes with cancer dependency profiles}},
author = {Qingyang Yin and Liang Chen},
journal = {NAR Cancer},
year = {2026},
month = oct,
doi = {10.1093/narcan/zcag031},
url = {https://doi.org/10.1093/narcan/zcag031},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - xNNPCD identifies regulators of programmed cell death by integrating perturbation transcriptomes with cancer dependency profiles
AU - Qingyang Yin
AU - Liang Chen
PY - 2026
DA - 2026/10/26
JO - NAR Cancer
DO - 10.1093/narcan/zcag031
UR - https://doi.org/10.1093/narcan/zcag031
AB - Programmed cell death (PCD) encompasses regulated processes whose dysregulation shapes cancer fitness, yet computational studies use known PCD genes for prognosis rather than discovering regulators. We developed xNNPCD, an interpretable neural-network framework that links CRISPR–Cas9 perturbation signatures from CMap to gene dependency profiles from DepMap. The model constrains hidden neurons to five PCD pathways and iteratively refines a prior gene–PCD pathway mask matrix derived from GO, KEGG, and Reactome using pathway–neuron ablation. This converts binary gene–pathway relationships into continuous-valued associations and improves dependency prediction over random forests, fully connected multi-layer perceptrons, and its own non-iterative variant. The learned mask matrix recovers annotated death regulators and nominates candidate regulators, including RPL23A, HSPA5, SNRPA1, SLC6A2, and ASAH1; combined with dependency scores, it separates pathway coupling from regulatory direction. Transferring the refined mask matrix and learned weights to compound-induced perturbation data enables in silico drug screening, identifying BRD-K19103580 and decitabine as therapeutic agents for apoptosis and ferroptosis, respectively. The pathway-resolved drug profiles can facilitate the design of combination therapies targeting complementary PCD pathways to overcome single-pathway resistance. Overall, xNNPCD offers a pan-cancer, interpretable approach that generalizes across perturbation modalities for mapping the regulatory landscape and elucidating the molecular processes of PCD in cancer.
SN - 2632-8674
ER -