Single-cell gene set scoring with nearest neighbor graph smoothed data (gssnng)
Bibliographic record
Abstract
Summary: Gene set scoring (or enrichment) is a common dimension reduction task in bioinformatics that can be focused on the differences between groups or at the single sample level. Gene sets can represent biological functions, molecular pathways, cell identities, and more. Gene set scores are context dependent values that are useful for interpreting biological changes following experiments or perturbations. Single sample scoring produces a set of scores, one for each member of a group, which can be analyzed with statistical models that can include additional clinically important factors such as gender or age. However, the sparsity and technical noise of single-cell expression measures create difficulties for these methods, which were originally designed for bulk expression profiling (microarrays, RNAseq). This can be greatly remedied by first applying a smoothing transformation that shares gene measure information within transcriptomic neighborhoods. In this work, we use the nearest neighbor graph of cells for matrix smoothing to produce high quality gene set scores on a per-cell, per-group, level which is useful for visualization and statistical analysis. Availability and implementation: The gssnng software is available using the python package index (PyPI) and works with Scanpy AnnData objects. It can be installed using "pip install gssnng." More information and demo notebooks: see https://github.com/IlyaLab/gssnng.
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 | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.021 | 0.009 |
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".