GeneComber: combining outputs of gene prediction programs for improved results
Bibliographic record
Abstract
UNLABELLED: We recently demonstrated that combining the output from Genscan and HMMgene can provide increased accuracy of gene predictions. We have created a robust software system that runs algorithms previously described on DNA sequences and provides a public web interface to the system for use by the biological community worldwide. The GeneComber system performs ab initio gene prediction by first taking a user inputted DNA sequence and running Genscan and HMMgene. The outputs of Genscan and HMMgene are then integrated using the EUI, GI and EUI_frame algorithms. All results are then stored into a relational database management system (RDBMS) and can then be retrieved through a web interface. The web interface provides a unified view of the GeneComber predictions by graphically overlaying outputs from Genscan, HMMgene, EUI, GI and EUI_frame. Outputs can also be retrieved in general feature format (GFF) or FASTA format. The software is written in the Perl programming language and is both dependent on and interoperable with the Bioperl toolkit. It includes high-level application programming interfaces (APIs) to run Genscan, HMMgene and a database API to insert prediction results into an RDBMS. The APIs are assembled into the genecomber script which is executed by the web interface or can be run directly from the Unix command line. The web interface is written in PHP and is structured so as to be easily modified for viewing data from any database that stores gene structures. AVAILABILITY: The GeneComber public web interface and supplementary information is located at http://bioinformatics.ubc.ca/genecomber The source code is released under the GNU General Public License and is available at ftp://ftp.bioinformatics.ubc.ca/pub/genecomber/software.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.023 | 0.013 |
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".