Summary of Peptide-gpt: Generative Design Of Peptides Using Generative Pre-trained Transformers and Bio-informatic Supervision, by Aayush Shah and Chakradhar Guntuboina and Amir Barati Farimani
Peptide-GPT: Generative Design of Peptides using Generative Pre-trained Transformers and Bio-informatic Supervision
by Aayush Shah, Chakradhar Guntuboina, Amir Barati Farimani
First submitted to arxiv on: 25 Oct 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 A novel protein language model, PeptideGPT, is introduced for generating protein sequences with specific properties. The model is trained to produce proteins with hemolytic activity, solubility, and non-fouling characteristics. To evaluate the generated sequences, a comprehensive pipeline is established, combining bioinformatics ideas to retain valid proteins with ordered structures. The pipeline involves ranking sequences by perplexity scores, filtering out those outside the permissible convex hull of proteins, predicting structure using ESMFold, and selecting proteins with pLDDT values greater than 70. Task-specific classifiers PeptideBERT and HAPPENN are used to evaluate the properties of generated sequences, achieving accuracy rates of 76.26% for hemolytic, 72.46% for non-hemolytic, 78.84% for non-fouling, and 68.06% for solubility protein generation. The study demonstrates the effectiveness of PeptideGPT in de novo protein design and highlights its potential to revolutionize synthetic biology and bioinformatics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary PeptideGPT is a new way to make proteins with specific properties. It’s like a special recipe book for building proteins. To test how well it works, scientists created a system that checks the generated proteins against what we know about real proteins. They used this system to see if the generated proteins have the right properties and found that it worked really well! This is important because it could help us make new medicines and materials in the future. |
Keywords
» Artificial intelligence » Language model » Perplexity
