Summary of Repurformer: Transformers For Repurposing-aware Molecule Generation, by Changhun Lee et al.
Repurformer: Transformers for Repurposing-Aware Molecule Generation
by Changhun Lee, Gyumin Lee
First submitted to arxiv on: 16 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); 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 The proposed Repurformer model leverages multi-hop relationships among proteins and compounds to address the sample bias problem in deep generative models. By integrating bi-directional pretraining with Fast Fourier Transform (FFT) and low-pass filtering (LPF), Repurformer captures complex interactions and generates diverse molecules. Experimental results on the BindingDB dataset demonstrate that Repurformer successfully creates substitutes for anchor compounds that resemble positive compounds, increasing diversity between the anchor and generated compounds. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers developed a new model to help find new medicines by generating lots of different molecules with good properties. They wanted to solve a problem where their computer programs kept making similar molecules instead of really diverse ones. To fix this, they created a new program called Repurformer that looks at relationships between proteins and compounds in a special way. It uses two techniques called Fast Fourier Transform (FFT) and low-pass filtering (LPF) to understand these relationships better. They tested Repurformer on some data and it worked well, making many different molecules that are good substitutes for existing medicines. |
Keywords
* Artificial intelligence * Pretraining
