TransformerChrome: Transformer-based Model for Prediction ofGene Expression from Histone Modifications
Bibliographic record
Abstract
Epigenetic mechanisms play a crucial role in regulating the expression of genes affecting the development, growth, and functioning of organisms, ensuring the activation or repression of specific genes at the appropriate times and in the correct cells. This functionality enables organisms to adapt to internal and external stimuli, uphold homeostasis, and execute diverse biological processes. One such mechanism modulating the expression of genes involves modification of histone proteins. Consequently, there is a need for identifying and comprehensively understanding various histone modifications and their effect on gene expression. The laboratory-based identification process entails the examination of histone modifications (HMs) to analyze the chemical alterations of histone proteins associated with DNA. On the other hand, technological advancements empower AI to address these challenges by discerning protein chemical alterations at HMs associated with DNA, facilitating accelerated comprehension of gene expression with maintained precision, result accuracy, and substantial cost reduction. In this paper, we introduce TransformerChrome, a computational model-based on the transformer neural network architecture, designed to take HMs from gene sites as input and predict gene expression as output. The developed TransformerChrome model has been trained and tested across 56 distinct cell types, using five core HMs. The presented model has been compared against state-of-the-art HM based gene expression predictive models across benchmark datasets in humans. The model is evaluated in terms of area under the receiver operating characteristic curve. The results show superior performance, especially on cell types for which other models show significantly lower performance.
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".