Gene expression models based on transcription factor binding events confer insight into functional <i>cis</i> -regulatory variants
Bibliographic record
Abstract
MOTIVATION: Deciphering the functional roles of cis-regulatory variants is a critical challenge in genome analysis and interpretation. It has been hypothesized that altered transcription factor (TF) binding events are a central mechanism by which cis-regulatory variants impact gene expression levels. However, we lack a computational framework to understand and quantify such mechanistic contributions. RESULTS: We present TF2Exp, a gene-based framework to predict the impact of altered TF-binding events on gene expression levels. Using data from lymphoblastoid cell lines, TF2Exp models were applied successfully to predict the expression levels of 3196 genes. Alterations within DNase I hypersensitive, CTCF-bound and tissue-specific TF-bound regions were the greatest contributing features to the models. TF2Exp models performed as well as models based on common variants, both in cross-validation and external validation. Combining TF alteration and common variant features can further improve model performance. Unlike variant-based models, TF2Exp models have the unique advantage to evaluate the functional impact of variants in linkage disequilibrium and uncommon variants. We find that adding TF-binding events altered only by uncommon variants could increase the number of predictable genes (R2 > 0.05). Taken together, TF2Exp represents a key step towards interpreting the functional roles of cis-regulatory variants in the human genome. AVAILABILITY AND IMPLEMENTATION: The code and model training results are publicly available at https://github.com/wqshi/TF2Exp. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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 teacher head, 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".