This is the public archive with ID 9a379e8618a1ba1f2730ec33fa3a736d created
on 2024-01-15 17:47:18 by Richard Michael, DIKU <richard.michael@di.ku.dk>.
Archive Meta Data
Author(s)
Richard Michael, Jacob Kæstel-Hansen, Peter Mørch Groth, Simon Bartels, Jesper Salomon, Pengfei Tian, Nikos S. Hatzakis, Wouter Boomsma
Title
ProteinRegressionArchive
Description
This directory contains all data required to run the experiments of the "Protein Regression Assessment"
and replicate the presented figures.
The original data-sets (alignments, protein sequences, and experimental observations) is a subset of data contained in the ProteinGym,
see
Notin, Pascal, et al. "Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval." International Conference on Machine Learning. PMLR, 2022.
and
Notin, Pascal, et al. "Proteingym: Large-scale benchmarks for protein fitness prediction and design." Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track. 2023.