# BERTology Meets Biology: Interpreting Attention in Protein Language Models

arXiv: https://arxiv.org/abs/2006.15222 · HTML: https://mlsanity.com/paper/2006.15222/

## Key facts

- Cited by 85 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2020.

## Built on by (most cited first, 30 of 85)

- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [Pre-trained Language Models in Biomedical Domain: A Systematic Survey](https://mlsanity.com/paper/2110.05006/) (2021)
- [Graph Representation Learning in Biomedicine](https://mlsanity.com/paper/2104.04883/) (2021)
- [A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks](https://mlsanity.com/paper/2306.07303/) (2023)
- [OntoProtein: Protein Pretraining With Gene Ontology Embedding](https://mlsanity.com/paper/2201.11147/) (2022)
- [Regression Transformer: Concurrent sequence regression and generation for molecular language modeling](https://mlsanity.com/paper/2202.01338/) (2022)
- [What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code](https://mlsanity.com/paper/2202.06840/) (2022)
- [A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?](https://mlsanity.com/paper/2402.05015/) (2024)
- [Learning to Estimate Shapley Values with Vision Transformers](https://mlsanity.com/paper/2206.05282/) (2022)
- [Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling](https://mlsanity.com/paper/2301.06568/) (2023)
- [Graph Denoising Diffusion for Inverse Protein Folding](https://mlsanity.com/paper/2306.16819/) (2023)
- [Structure-aware Protein Self-supervised Learning](https://mlsanity.com/paper/2204.04213/) (2022)
- [BEND: Benchmarking DNA Language Models on biologically meaningful tasks](https://mlsanity.com/paper/2311.12570/) (2023)
- [Sparse Autoencoders for Hypothesis Generation](https://mlsanity.com/paper/2502.04382/) (2025)
- [ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding](https://mlsanity.com/paper/2408.11363/) (2024)
- [Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model](https://mlsanity.com/paper/2110.15527/) (2021)
- [Exploring evolution-aware & -free protein language models as protein function predictors](https://mlsanity.com/paper/2206.06583/) (2022)
- [Transformers with Competitive Ensembles of Independent Mechanisms](https://mlsanity.com/paper/2103.00336/) (2021)
- [ProtChatGPT: Towards Understanding Proteins with Large Language Models](https://mlsanity.com/paper/2402.09649/) (2024)
- [Protein Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2502.17504/) (2025)
- [Cross-lingual Transfer of Monolingual Models](https://mlsanity.com/paper/2109.07348/) (2021)
- [A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design](https://mlsanity.com/paper/2311.16126/) (2023)
- [Towards Interpretable Protein Structure Prediction with Sparse Autoencoders](https://mlsanity.com/paper/2503.08764/) (2025)
- [Less can be more for predicting properties with large language models](https://mlsanity.com/paper/2406.17295/) (2024)
- [Generative power of a protein language model trained on multiple sequence alignments](https://mlsanity.com/paper/2204.07110/) (2022)
- [Influence Functions for Sequence Tagging Models](https://mlsanity.com/paper/2210.14177/) (2022)
- [Protein language models trained on multiple sequence alignments learn phylogenetic relationships](https://mlsanity.com/paper/2203.15465/) (2022)
- [Linguistically inspired roadmap for building biologically reliable protein language models](https://mlsanity.com/paper/2207.00982/) (2022)
- [Linguistic Laws Meet Protein Sequences: A Comparative Analysis of Subword Tokenization Methods](https://mlsanity.com/paper/2411.17669/) (2024)
- [Transformers and the representation of biomedical background knowledge](https://mlsanity.com/paper/2202.02432/) (2022)

## Abstract (arXiv)

Transformer architectures have proven to learn useful representations for protein classification and generation tasks. However, these representations present challenges in interpretability. In this work, we demonstrate a set of methods for analyzing protein Transformer models through the lens of attention. We show that attention: (1) captures the folding structure of proteins, connecting amino acids that are far apart in the underlying sequence, but spatially close in the three-dimensional structure, (2) targets binding sites, a key functional component of proteins, and (3) focuses on progressively more complex biophysical properties with increasing layer depth. We find this behavior to be consistent across three Transformer architectures (BERT, ALBERT, XLNet) and two distinct protein datasets. We also present a three-dimensional visualization of the interaction between attention and protein structure. Code for visualization and analysis is available at https://github.com/salesforce/provis.