# Variational auto-encoding of protein sequences

arXiv: https://arxiv.org/abs/1712.03346 · HTML: https://mlsanity.com/paper/1712.03346/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Dec 2017.

## Built on by (most cited first, 9 of 9)

- [A Survey on Protein Representation Learning: Retrospect and Prospect](https://mlsanity.com/paper/2301.00813/) (2022)
- [Advances in Protein Representation Learning: Methods, Applications, and Future Directions](https://mlsanity.com/paper/2503.16659/) (2025)
- [SFM-Protein: Integrative Co-evolutionary Pre-training for Advanced Protein Sequence Representation](https://mlsanity.com/paper/2410.24022/) (2024)
- [Training-Free Generation of Protein Sequences from Small Family Alignments via Stochastic Attention](https://mlsanity.com/paper/2603.14717/) (2026)
- [EvoVGM: a Deep Variational Generative Model for Evolutionary Parameter Estimation](https://mlsanity.com/paper/2205.13034/) (2022)
- [AntibodyFlow: Normalizing Flow Model for Designing Antibody Complementarity-Determining Regions](https://mlsanity.com/paper/2406.13162/) (2024)
- [Discriminative protein sequence modelling with Latent Space Diffusion](https://mlsanity.com/paper/2503.18551/) (2025)
- [RNAGenScape: Property-Guided, Optimized Generation of mRNA Sequences with Manifold Langevin Dynamics](https://mlsanity.com/paper/2510.24736/) (2025)
- [Reinforcement-guided generative protein language models enable de novo design of highly diverse AAV capsids](https://mlsanity.com/paper/2603.19473/) (2026)

## Abstract (arXiv)

Proteins are responsible for the most diverse set of functions in biology. The ability to extract information from protein sequences and to predict the effects of mutations is extremely valuable in many domains of biology and medicine. However the mapping between protein sequence and function is complex and poorly understood. Here we present an embedding of natural protein sequences using a Variational Auto-Encoder and use it to predict how mutations affect protein function. We use this unsupervised approach to cluster natural variants and learn interactions between sets of positions within a protein. This approach generally performs better than baseline methods that consider no interactions within sequences, and in some cases better than the state-of-the-art approaches that use the inverse-Potts model. This generative model can be used to computationally guide exploration of protein sequence space and to better inform rational and automatic protein design.