RADI (Reduced Alphabet Direct Information): Improving execution time for direct-coupling analysis
Bibliographic record
Abstract
Abstract Motivation Direct-coupling analysis (DCA) for studying the coevolution of residues in proteins has been widely used to predict the three-dimensional structure of a protein from its sequence. Current algorithms for DCA, although efficient, have a high computational cost of determining Direct Information (DI) values for large proteins or domains. In this paper, we present RADI (Reduced Alphabet Direct Information), a variation of the original DCA algorithm that simplifies the computation of DI values by grouping physicochemically equivalent residues. Results We have compared the first top ranking 40 pairs of DI values and their closest paired contact in 3D. The ranking is also compared with results obtained using a similar but faster approach based on Mutual Information (MI). When we simplify the number of symbols used to describe a protein sequence to 9, RADI achieves similar results as the original DCA (i.e. with the classical alphabet of 21 symbols), while reducing the computation time around 30-fold on large proteins (with length around 1000 residues) and with higher accuracy than predictions based on MI. Interestingly, the simplification produced by grouping amino acids into only two groups (polar and non-polar) is still representative of the physicochemical nature that characterizes the protein structure, having a relevant and useful predictive value, while the computation time is reduced between 100 and 2500-fold. Availability RADI is available at https://github.com/structuralbioinformatics/RADI Contact baldo.oliva@upf.edu Supplementary information Supplementary data is available in the git repository.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.019 | 0.008 |
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".