Kernel-Based Evaluation of Conditional Biological Sequence Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909852724363264 |
|---|---|
| author | Glaser, Pierre Paul, Steffanie Hummer, Alissa M. Deane, Charlotte M. Marks, Debora S. Amin, Alan N. |
| author_facet | Glaser, Pierre Paul, Steffanie Hummer, Alissa M. Deane, Charlotte M. Marks, Debora S. Amin, Alan N. |
| contents | We propose a set of kernel-based tools to evaluate the designs and tune the hyperparameters of conditional sequence models, with a focus on problems in computational biology. The backbone of our tools is a new measure of discrepancy between the true conditional distribution and the model's estimate, called the Augmented Conditional Maximum Mean Discrepancy (ACMMD). Provided that the model can be sampled from, the ACMMD can be estimated unbiasedly from data to quantify absolute model fit, integrated within hypothesis tests, and used to evaluate model reliability. We demonstrate the utility of our approach by analyzing a popular protein design model, ProteinMPNN. We are able to reject the hypothesis that ProteinMPNN fits its data for various protein families, and tune the model's temperature hyperparameter to achieve a better fit. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15601 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Kernel-Based Evaluation of Conditional Biological Sequence Models Glaser, Pierre Paul, Steffanie Hummer, Alissa M. Deane, Charlotte M. Marks, Debora S. Amin, Alan N. Machine Learning We propose a set of kernel-based tools to evaluate the designs and tune the hyperparameters of conditional sequence models, with a focus on problems in computational biology. The backbone of our tools is a new measure of discrepancy between the true conditional distribution and the model's estimate, called the Augmented Conditional Maximum Mean Discrepancy (ACMMD). Provided that the model can be sampled from, the ACMMD can be estimated unbiasedly from data to quantify absolute model fit, integrated within hypothesis tests, and used to evaluate model reliability. We demonstrate the utility of our approach by analyzing a popular protein design model, ProteinMPNN. We are able to reject the hypothesis that ProteinMPNN fits its data for various protein families, and tune the model's temperature hyperparameter to achieve a better fit. |
| title | Kernel-Based Evaluation of Conditional Biological Sequence Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.15601 |