Summary of Codonmpnn For Organism Specific and Codon Optimal Inverse Folding, by Hannes Stark et al.
CodonMPNN for Organism Specific and Codon Optimal Inverse Folding
by Hannes Stark, Umesh Padia, Julia Balla, Cameron Diao, George Church
First submitted to arxiv on: 25 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Quantitative Methods (q-bio.QM)
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 paper proposes CodonMPNN, a novel technique for generating codon sequences conditioned on protein backbone structures and organism labels. The goal is to improve the expression rates of engineered proteins by optimizing codon choices. Current methods often rely on heuristics, which can lead to suboptimal results. CodonMPNN leverages inverse folding approaches and learns to generate codon sequences with higher expression yields. Experimental results show that it retains the performance of previous methods while recovering wild-type codons more frequently. Furthermore, it has a higher likelihood of generating high-fitness codon sequences than low-fitness ones for the same protein sequence. The authors make their code available on GitHub. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps scientists create new proteins by choosing the right building blocks (codons) for each part of the protein. Currently, this process can be tricky because not all codons are equal – some work better than others in different organisms. To solve this problem, the researchers developed a new method called CodonMPNN. This technique uses information about the protein’s shape and the organism it will be expressed in to create better codons. The results show that CodonMPNN works well and is more likely to create good codons than other methods. This could be very helpful for scientists trying to make new proteins. |
Keywords
* Artificial intelligence * Likelihood
