Forest-based gene selection links PGAP1 and TMBIM1 expression to systemic sclerosis
Source check: Source checked. Not independent scientific confirmation.
Finding: Boruta and random forests prioritized PGAP1 and TMBIM1 from systemic-sclerosis expression data. The selected genes showed opposite expression changes in two small human skin datasets, with corresponding expression changes reported in mouse fibrotic tissues. The result is an association and expression validation, not a demonstrated disease mechanism or treatment.
Technology: Boruta random-forest feature selection; random forest
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Boruta and random-forest ranking reduced disease-associated candidates to genes taken forward for cross-dataset expression comparisons and targeted tissue-expression checks.
- Test and result
- Single-cell data from 12 systemic-sclerosis and 3 control skin samples informed candidate genes. Boruta-confirmed genes were intersected with top random-forest importance ranks. Human bulk datasets comprised 18 cases/15 controls and 10 cases/5 controls; the second dataset also participated in final gene filtering. PGAP1 was lower and TMBIM1 higher in affected human skin, with corresponding transcript/protein expression findings in source-reported mouse fibrotic tissues.
- Limitation / still unknown
- Small reused human datasets; the nominal validation dataset helped select genes, so it is not an untouched external diagnostic test. Mouse expression association does not establish causal antagonism, Th17 specificity, human diagnostic utility or therapeutic efficacy. PGAP1 lung expression changed with time. Detailed experimental replicate counts and supplementary datasets were not independently inspected; drug/docking predictions are not represented as treatments.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC12923484/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 21 Nov 2026. Review scope: Read primary data/cohort, Boruta/random-forest feature selection and validation-set filtering Methods, human expression Results, high-level mouse expression Results and mechanistic limitations. Operational experimental procedures and supplementary replicate details are outside the represented evidence scope. Exact primary identity/date and fresh primary PubMed correction/retraction relationships checked..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.