Summary of Efficiently Predicting Mutational Effect on Homologous Proteins by Evolution Encoding, By Zhiqiang Zhong and Davide Mottin
Efficiently Predicting Mutational Effect on Homologous Proteins by Evolution Encoding
by Zhiqiang Zhong, Davide Mottin
First submitted to arxiv on: 20 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Biomolecules (q-bio.BM)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research proposes a novel approach to predicting protein properties by leveraging evolutionary information. The EvolMPNN model learns evolution-aware protein embeddings, which can capture the effect of subtle mutations on protein properties. This is achieved through the use of anchor proteins, residues, and a differentiable aggregation scheme. The aggregated embeddings are then integrated with sequence embeddings to generate comprehensive protein embeddings. Experimental results show that EvolMPNN outperforms state-of-the-art methods by up to 6.4% and achieves a 36X inference speedup compared to large pre-trained models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Protein engineering is crucial for medical advancements, but existing methods often neglect subtle mutations. This paper introduces EvolMPNN, a model that learns evolution-aware protein embeddings. It uses anchor proteins, residues, and an aggregation scheme to capture the effect of mutations. The results show that EvolMPNN is better than other methods and can do things faster. |
Keywords
* Artificial intelligence * Inference
