Comprehensive classification of proteins based on structures that engage lipids by COMPOSEL
Bibliographic record
Abstract
Structures can now be predicted for any protein using programs like AlphaFold and Rosetta, which rely on a foundation of experimentally determined structures of architecturally diverse proteins. The accuracy of such artificial intelligence and machine learning (AI/ML) approaches benefits from the specification of restraints which assist in navigating the universe of folds to converge on models most representative of a given protein's physiological structure. This is especially pertinent for membrane proteins, with structures and functions that depend on their presence in lipid bilayers. Structures of proteins in their membrane environments could conceivably be predicted from AI/ML approaches with user-specificized parameters that describe each element of the architecture of a membrane protein accompanied by its lipid environment. We propose the Classification Of Membrane Proteins based On Structures Engaging Lipids (COMPOSEL), which builds on existing nomenclature types for monotopic, bitopic, polytopic and peripheral membrane proteins as well as lipids. Functional and regulatory elements are also defined in the scripts, as shown with membrane fusing synaptotagmins, multidomain PDZD8 and Protrudin proteins that recognize phosphoinositide (PI) lipids, the intrinsically disordered MARCKS protein, caveolins, the β barrel assembly machine (BAM), an adhesion G-protein coupled receptor (aGPCR) and two lipid modifying enzymes - diacylglycerol kinase DGKε and fatty aldehyde dehydrogenase FALDH. This demonstrates how COMPOSEL communicates lipid interactivity as well as signaling mechanisms and binding of metabolites, drug molecules, polypeptides or nucleic acids to describe the operations of any protein. Moreover COMPOSEL can be scaled to express how genomes encode membrane structures and how our organs are infiltrated by pathogens such as SARS-CoV-2.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.004 |
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".