Skip to content

Commit f4edd53

Browse files
Update CrossLabsAI-CrossRoads45-METL-Biophysics-based-Protein-Language-Model.qmd
1 parent b5d118a commit f4edd53

File tree

1 file changed

+5
-10
lines changed

1 file changed

+5
-10
lines changed

Applications/Highlights/CrossLabsAI-CrossRoads45-METL-Biophysics-based-Protein-Language-Model.qmd

Lines changed: 5 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -24,19 +24,14 @@ categories:
2424
>
2525
> We introduce Mutational Effect Transfer Learning (METL), a specialized protein language model that bridges the gap between traditional biophysics-based and machine learning approaches by incorporating synthetic data from molecular simulations. We pretrain a transformer on millions of molecular simulations to capture the relationship between protein sequence, structure, energetics, and stability. We then finetune the neural network to harness these fundamental biophysical signals and apply them when predicting protein functional scores from experimental assays. METL excels in protein engineering tasks like generalizing from small training sets and extrapolating to new sequence positions. We demonstrate METL's ability to design functional green fluorescent protein variants when trained on only 64 experimental examples.
2626
27-
### Links
27+
### Links & code
2828
- About the Speaker → [samgelman.com](https://samgelman.com)
2929
- Check out the [preprint](https://www.biorxiv.org/content/10.1101/2024.03.15.585128v1)
30-
- A collection of METL software repositories is provided to reproduce the results of this manuscript and run METL on new data:
30+
- All code is available under the MIT license. A collection of METL software repositories is provided to reproduce the results of this manuscript and run METL on new data:
3131
- [github.com/gitter-lab/metl](https://github.com/gitter-lab/metl) for pretraining and finetuning METL PLMs (archived at doi:10.5281/zenodo.10819483)
32-
33-
- [https://github.com/gitter-lab/metl-sim](https://github.com/gitter-lab/metl-sim) for generating biophysical attributes with Rosetta (archived at doi:10.5281/zenodo.10819523)
34-
35-
- [https://github.com/gitter-lab/metl-pretrained](https://github.com/gitter-lab/metl-pretrained) for making predictions with pretrained METL PLMs (archived at doi:10.5281/zenodo.10819499)
36-
37-
- [https://github.com/gitter-lab/metl-pub](https://github.com/gitter-lab/metl-pub) for additional code and data to reproduce these results (archived at doi:10.5281/zenodo.10819536)
38-
39-
All code is available under the MIT license.
32+
- [github.com/gitter-lab/metl-sim](https://github.com/gitter-lab/metl-sim) for generating biophysical attributes with Rosetta (archived at doi:10.5281/zenodo.10819523)
33+
- [github.com/gitter-lab/metl-pretrained](https://github.com/gitter-lab/metl-pretrained) for making predictions with pretrained METL PLMs (archived at doi:10.5281/zenodo.10819499)
34+
- [github.com/gitter-lab/metl-pub](https://github.com/gitter-lab/metl-pub) for additional code and data to reproduce these results (archived at doi:10.5281/zenodo.10819536)
4035

4136
{{< video https://www.youtube.com/watch?v=milM6-2RF18 >}}
4237

0 commit comments

Comments
 (0)