<scp>SenSeqNet</scp> : A Deep Learning Framework for Cellular Senescence Detection From Protein Sequences
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".