scSniper: Single-cell Deep Neural Network-based Identification of Prominent Biomarkers
Bibliographic record
Abstract
Abstract Discovering disease biomarkers at the single-cell level is crucial for advancing our understanding of diseases and improving diagnostic accuracy. However, current computational methods often have limitations, such as a reliance on prior knowledge, constraints to unimodal data, and the use of conventional statistical tests for feature selection. To address these issues, we introduce scSniper, a novel approach that employs a specialized deep neural network framework tailored for robust single-cell multiomic biomarker detection. A standout feature of scSniper is the mimetic attention block, enhancing alignment across multi-modal data types. Moreover, scSniper utilizes sensitivity analysis based on a deep neural network for feature selection and uncovers intricate gene regulatory networks without requiring prior knowledge. Comprehensive evaluations on real-world datasets, including COVID-19 CITE-Seq and LUAD scRNA-Seq, demonstrate scSniper’s exceptional ability to identify critical biomarkers consistently outperforming traditional methods like MAST, Wilcox, and DESeq2. The scSniper tool and related experimental codes are publicly accessible at https://github.com/mcgilldinglab/scSniper .
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.003 | 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".