Automated Protein Motif Localization using Concept Activation Vectors in Protein Language Model Embedding Space
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917106678759424 |
|---|---|
| author | Shamail, Ahmad McWhite, Claire D. |
| author_facet | Shamail, Ahmad McWhite, Claire D. |
| contents | We present an automated approach for identifying and annotating motifs and domains in protein sequences, using pretrained Protein Language Models (PLMs) and Concept Activation Vectors (CAVs), adapted from interpretability research in computer vision. We treat motifs as conceptual entities and represent them through learned CAVs in PLM embedding space by training simple linear classifiers to distinguish motif-containing from non-motif sequences. To identify motif occurrences, we extract embeddings for overlapping sequence windows and compute their inner products with motif CAVs. This scoring mechanism quantifies how strongly each sequence region expresses the motif concept and naturally detects multiple instances of the same motif within the same protein. Using a dataset of sixty-nine well-characterized motifs with curated positive and negative examples, our method achieves over 85\% F1 Score for segments strongly expressing the concept and accurately localizes motif positions across diverse protein families. As each motif is encoded by a single vector, motif detection requires only the pretrained PLM and a lightweight dictionary of CAVs, offering a scalable, interpretable, and computationally efficient framework for automated sequence annotation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21614 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automated Protein Motif Localization using Concept Activation Vectors in Protein Language Model Embedding Space Shamail, Ahmad McWhite, Claire D. Quantitative Methods We present an automated approach for identifying and annotating motifs and domains in protein sequences, using pretrained Protein Language Models (PLMs) and Concept Activation Vectors (CAVs), adapted from interpretability research in computer vision. We treat motifs as conceptual entities and represent them through learned CAVs in PLM embedding space by training simple linear classifiers to distinguish motif-containing from non-motif sequences. To identify motif occurrences, we extract embeddings for overlapping sequence windows and compute their inner products with motif CAVs. This scoring mechanism quantifies how strongly each sequence region expresses the motif concept and naturally detects multiple instances of the same motif within the same protein. Using a dataset of sixty-nine well-characterized motifs with curated positive and negative examples, our method achieves over 85\% F1 Score for segments strongly expressing the concept and accurately localizes motif positions across diverse protein families. As each motif is encoded by a single vector, motif detection requires only the pretrained PLM and a lightweight dictionary of CAVs, offering a scalable, interpretable, and computationally efficient framework for automated sequence annotation. |
| title | Automated Protein Motif Localization using Concept Activation Vectors in Protein Language Model Embedding Space |
| topic | Quantitative Methods |
| url | https://arxiv.org/abs/2511.21614 |