Unseen Epitope-TCR Interaction Prediction based on Amino Acid Physicochemical Properties
Bibliographic record
Abstract
Successful prediction of epitope-T cell receptor (TCR) interactions can help with effective vaccination and personalized healthcare. Unseen epitope-TCR interaction prediction is based on independent sets of training and testing data, which is good to find their corresponding epitopes for novel, unseen diseases. In this study, we present a framework for predicting the unseen epitope-TCR interactions based on physicochemical properties of constituent amino acids of epitope and TCR CDR3 sequences. Sequence based models for epitope-TCR interaction prediction generally extract features individually from each sequence and then combine them together. However, in this study, the features for the unseen epitope-TCR interaction model have been generated as images from both sequences simultaneously by computing the absolute difference and outer product of two vectors consisting of the physicochemical property values of amino acids. The performances based on nine different physicochemical properties of amino acids have been compared and the best performing properties are selected. Some properties are combined together to achieve the highest performance. The model exhibits much higher performance in comparison with the existing unseen epitope prediction models. The model produces the AUC of 0.64 for absolute difference based features with only two best performing properties, and the AUC of 0.60 for vector outer product with the same two properties. Furthermore, our model achieves the AUC of 0.82 by combining both types of features while the best existing model achieves the AUC of only 0.55 in the setting of unseen epitope-TCR interaction prediction.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".