Defining the characteristics of interferon-alpha–stimulated human genes: insight from expression data and machine learning
Bibliographic record
Abstract
BACKGROUND: A virus-infected cell triggers a signalling cascade, resulting in the secretion of interferons (IFNs), which in turn induces the upregulation of the IFN-stimulated genes (ISGs) that play a role in antipathogen host defence. Here, we conducted analyses on large-scale data relating to evolutionary gene expression, sequence composition, and network properties to elucidate factors associated with the stimulation of human genes in response to IFN-α. RESULTS: We find that ISGs are less evolutionary conserved than genes that are not significantly stimulated in IFN experiments (non-ISGs). ISGs show obvious depletion of GC content in the coding region. This influences the representation of some compositions following the translation process. IFN-repressed human genes (IRGs), downregulated genes in IFN experiments, can have similar properties to the ISGs. Additionally, we design a machine learning framework integrating the support vector machine and novel feature selection algorithm that achieves an area under the receiver operating characteristic curve (AUC) of 0.7455 for ISG prediction. Its application in other IFN systems suggests the similarity between the ISGs triggered by type I and III IFNs. CONCLUSIONS: ISGs have some unique properties that make them different from the non-ISGs. The representation of some properties has a strong correlation with gene expression following IFN-α stimulation, which can be used as a predictive feature in machine learning. Our model predicts several genes as putative ISGs that so far have shown no significant differential expression when stimulated with IFN-α in the cell/tissue types in the available databases. A web server implementing our method is accessible at http://isgpre.cvr.gla.ac.uk/. The docker image at https://hub.docker.com/r/hchai01/isgpre can be downloaded to reproduce the prediction.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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".