# ProPath: Disease-Specific Protein Language Model for Variant Pathogenicity

arXiv: https://arxiv.org/abs/2311.03429 · HTML: https://mlsanity.com/paper/2311.03429/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 25 references that are in the map.
- First posted on arXiv 6 Nov 2023.

## Builds on (most cited first, 1 of 1)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)

## Abstract (arXiv)

Clinical variant classification of pathogenic versus benign genetic variants remains a pivotal challenge in clinical genetics. Recently, the proposition of protein language models has improved the generic variant effect prediction (VEP) accuracy via weakly-supervised or unsupervised training. However, these VEPs are not disease-specific, limiting their adaptation at point-of-care. To address this problem, we propose a disease-specific textscprotein language model for variant textscpathogenicity, termed ProPath, to capture the pseudo-log-likelihood ratio in rare missense variants through a siamese network. We evaluate the performance of ProPath against pre-trained language models, using clinical variant sets in inherited cardiomyopathies and arrhythmias that were not seen during training. Our results demonstrate that ProPath surpasses the pre-trained ESM1b with an over 5% improvement in AUC across both datasets. Furthermore, our model achieved the highest performances across all baselines for both datasets. Thus, our ProPath offers a potent disease-specific variant effect prediction, particularly valuable for disease associations and clinical applicability.