DEPRECATED Enformer (Human) Model Predictor (Avsec et al. 2021) using the Genomic API for Model Evaluation (GAME) Framework
Bibliographic record
Abstract
This record provides a Predictor container for the Enformer model (Avsec et al. 2021, Nature Methods). Enformer is a deep-learning architecure that substantially improves gene expression prediction from DNA sequences by integrating information from long-range interactions up to 100 kb away. Its key innovation is the use of novel transformer layers, which more effectively model the influence of distal regulatory elements like enhancers on gene expression and chromatin states in humans (and mice, but this Predictor is for humans only). The model predicts genomic tracks for the human genome, including CAGE for transcriptional activity, histone modifications, transcription factor binding, and DNA accessibility, all aggregated into 128-bp bins. It was trained in a multitask setting on a vast collection of human and mouse epigenomic datasets to study cis-regulatory evolution. The Predictor container (predictor_enformer.sif) includes: API Predictor script for sequence processing and error handling. Integrated Enformer model with its dependencies. Helper scripts and model weights. NOTE: This container requires a GPU for execution due to the computational demands of the transformer architecture. Running the container: Ensure Apptainer is intalled in the system the container is intended to run. Always run the Predictor first, so it can listen for incoming connections from Evaluators: apptainer run --containall --nv predictor_enformer.sif HOST_IP HOST_PORT MATCHER_IP MATCHER_PORT Additional information about the GAME framework can be found on GitHub: Genomic API for Model Evaluation Enformer Human Predictor-specific information, can be found within the same repository: [Enformer Predictor Link] Code repository for Enformer model: Enformer GitHub Paper can be found here: Avsec, Ž., Agarwal, V., Visentin, D. et al. Effective gene expression prediction from sequence by integrating long-range interactions. Nat Methods 18, 1196–1203 (2021). https://doi.org/10.1038/s41592-021-01252-x
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.062 | 0.029 |
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".