Datasets For Predicting Tf Binding Using Virtual Chip-Seq
Bibliographic record
Abstract
This repository contains datasets necessary for using the Virtual ChIP-seq software. Virtual ChIP-seq requires the following datasets to predict transcription factor binding: chipExpDir_AtoH_V1.0.0.tar.gz: Reference matrices of correlation between TF binding and gene expression for TFs starting with letters A-H. chipExpDir_ItoZ_V1.0.0.tar.gz: Reference matrices of correlation between TF binding and gene expression for TFs starting with letters I-Z. refTables_V1.1.0.tar.gz: PhastCons genomic conservation, FIMO PWM scores for JASPAR motifs, and ChIP-seq data of ENCODE and Cistrome database. hg38_chrsize.tsv: Length of chromosomes in hg38 trainedModels_V1.0.0.tar.gz: Virtual ChIP-seq scikit-learn trained models saved in joblib format <CellType>.tar.gz: Pre-calculated matrices suitable for training with other algorithms or re-training with Virtual ChIP-seq. Some predictive features of TF binding are the same in each cell type and are stored together for simplicity in refTables_V1.0.0.tar.gz. You can use datasets from other cell types (named here as <CellType>.tar.gz) for the purpose of re-training the model. The <CellType>.tar.gz files contain pre-calculated predictive features of transcription factor binding in 4 chromosomes (5, 10, 15, 20). These features include: PhastCons genomic conservation FIMO score for sequence motifs of TF in the JASPAR database Chromatin accessibility TF binding in ENCODE + Cistrome DB datasets Virtual ChIP-seq expression score
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.005 | 0.000 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.002 |
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".