SenSeqNet: A Deep Learning Framework for Cellular Senescence Detection From Protein Sequences.

Abstract

Cellular senescence, defined as the irreversible arrest of cell proliferation in response to stress, contributes to tissue dysfunction and drives the progression of age-related diseases. Accurate detection of senescent states is therefore essential for understanding aging mechanisms and identifying therapeutic targets. However, conventional laboratory assays are time-consuming and difficult to scale. Here, we present SenSeqNet, a deep learning framework that predicts cellular senescence directly from protein sequences. SenSeqNet integrates embeddings from the Evolutionary Scale Modeling (ESM-2) with a hybrid LSTM-CNN architecture to capture both sequential and higher-order structural features. The model achieved 86.43% accuracy in independent testing, outperforming traditional machine learning and deep learning approaches. Importantly, the high-confidence genes predicted by SenSeqNet were significantly enriched in canonical senescence-associated pathways, indicating that the model captures biologically coherent regulatory programs rather than overfitting to sequence labels. These results establish SenSeqNet as a robust and biologically informed tool for senescence detection and provide a foundation for accelerating research into aging and age-related therapeutics.