CAPRI- Content-based Analysis of Protein Structure for Retrieval and Indexing
Bibliographic record
Abstract
In molecular biology, current research suggests that the function of a protein may be inferred from its structure. Two proteins with similar local parts (or active sites) and shape are often closely related. This observation is of importance when determining the adverse effects of new medicine, identifying new protein architectures, predicting protein interactions such as the docking-problem (where the so-called receptor connects to the ligand) and explaining unexpected evolutions. Due to the vast amounts of newly discovered protein structures, there is an urgent need for multimedia data mining systems which can efficiently find similar proteins structures, based on both shape and physical properties. In this paper, we describe the Content-based Analysis of Protein Structure for Retrieval and Indexing (CAPRI) data mining system, which is used to explore very large multimedia databases containing numerous protein structure families. CAPRI is able to find similar proteins based on their structure, by utilizing firstly, the 2D colours, textures and composition and secondly, the 3D structure of the proteins. Our results against more than 26,000 protein structures as contained in the Protein Data Bank shows that our system is able to accurately and efficiently locate related protein structures. Through the use of the CAPRI system, domain experts are able to find these similar protein structures, using a “query by prototype ” example. In this way, they are aided in the task of labelling new structures effectively, finding the families of existing proteins, identifying mutations and explaining unexpected evolutions. 1.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.009 | 0.007 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.011 |
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".