Exploiting ancestral mammalian genomes for the prediction of human transcription factor binding sites
Bibliographic record
Abstract
BACKGROUND: The computational prediction of Transcription Factor Binding Sites (TFBS) remains a challenge due to their short length and low information content. Comparative genomics approaches that simultaneously consider several related species and favor sites that have been conserved throughout evolution improve the accuracy (specificity) of the predictions but are limited due to a phenomenon called binding site turnover, where sequence evolution causes one TFBS to replace another in the same region. In parallel to this development, an increasing number of mammalian genomes are now sequenced and it is becoming possible to infer, to a surprisingly high degree of accuracy, ancestral mammalian sequences. RESULTS: We propose a TFBS prediction approach that makes use of the availability of inferred ancestral mammalian genomes to improve its accuracy. This method aims to identify binding loci, which are regions of a few hundred base pairs that have preserved their potential to bind a given transcription factor over evolutionary time. After proposing a neutral evolutionary model of predicted TFBS counts in a DNA region of a given length, we use it to identify regions that have preserved the number of predicted TFBS they contain to an unexpected degree given their divergence. The approach is applied to human chromosome 1 and shows significant gains in accuracy as compared to both existing single-species and multi-species TFBS prediction approaches, in particular for transcription factors that are subject to high turnover rates. AVAILABILITY: The source code and predictions made by the program are available at http://www.cs.mcgill.ca/~blanchem/bindingLoci.
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".