Machine learning-based Algorithm Identifies Key Mitochondria-Related Genes in Non-Alcoholic Steatohepatitis
Bibliographic record
Abstract
Abstract Background In hepatocytes, mitochondrial dysfunction drives aberrant fatty acid metabolism, oxidative stress, and cell apoptosis, promoting the occurrence and progression of NASH. Given the pivotal role of mitochondrial dysfunction in the advancement of NASH, the identification of mitochondrial core genes within NASH may offer potential targets for NASH treatment. Methods According to 101 machine learning algorithms assembled from 10 different machine learning algorithms, mitochondrial core genes were identified in NASH patients. The relationship between mitochondrial core genes and inflammation, lipid metabolism, liver fibrosis, and immune infiltration was investigated. Results AKR1B10, TYMS, and TREM2 were identified. A predictive model constructed using these three mitochondrial genes exhibited excellent diagnostic performance for NASH in the GEO cohorts. AKR1B10, TYMS, and TREM2 were significantly upregulated in NASH, F3-F4 stage liver fibrosis patients, and NAFLD-HCC patients. The expression levels of AKR1B10, TYMS, and TREM2 were positively correlated with pro-inflammatory genes, lipid synthesis genes, liver fibrosis genes, NAS score, pro-inflammatory immune signatures, and M1 macrophage content. Conversely, they were significantly negatively correlated with fatty acid oxidation genes and M2 macrophage content. Moreover, the biological and mitochondrial pathways enriched when AKR1B10, TYMS, and TREM2 were upregulated were related to NASH progression. NASH patients were further classified into Cluster 1 and Cluster 2. Pro-inflammatory genes, lipid synthesis genes, liver fibrosis genes, NAS score, pro-inflammatory immune signatures, and M1 macrophage content were significantly upregulated in Cluster 1. Conversely, fatty acid oxidation genes and M2 macrophage content were significantly downregulated in Cluster 1. Conclusion AKR1B10, TYMS, and TREM2 are associated with the severity of NASH. High expression of AKR1B10, TYMS, and TREM2 indicates a more severe condition in NASH patients.
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 | 0.003 |
| 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 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".