Prediction of KIR3DL1 and human leukocyte antigen binding
Bibliographic record
Abstract
KIR3DL1 is a polymorphic inhibitory receptor on natural killer (NK) cells that recognizes HLA class I allotypes. While the Bw4 motif spanning residues 77 to 83 is central to this interaction, structural studies have shown that polymorphisms elsewhere in the HLA molecule also influence binding. To address the challenge of predicting interactions across the extensive diversity of both KIR3DL1 and HLA, we developed a machine learning model trained on binding data from nine KIR3DL1 tetramers tested against a panel of HLA class I allotypes. Multiple models were evaluated using different subsets of HLA sequence features, including the full α1/α2 domains, the Bw4 motif, and α-helical residues excluding loop regions. The best-performing model, using Multi Label Vector Optimization (MLVO) and trained on α-helix positions, achieved AUC scores ranging from 0.74 to 0.974 across all KIR3DL1 allotypes. The model effectively distinguished high and low binders, revealing that residues beyond the Bw4 motif contribute to binding strength in a nonadditive manner. These findings demonstrate that binding affinity cannot be accurately captured by binary classifiers or single-motif rules. Our approach offers a more nuanced framework for modeling KIR3DL1-HLA interactions, with broad applicability to immunogenetic research and clinical decision-making.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".