Published December 30, 2023 | Version v1
Dataset Open

MuToN dataset

Authors/Creators

Description

This dataset is associated with the MuToN project hosted on GitHub (https://github.com/zpliulab/MuToN). It includes mutation records, PPI complexes, and pre-computed LLM embeddings for the SKEMPI dataset.

Contents:

├── data/
│   ├── skempi_v2.csv                # contains the mutation records in SKEMPI dataset.
│   ├── SKEMPI/
│   │   ├── raws/                    # contains the PPI complexes in SKEMPI dataset.
│   │   │   ├── 1CSE.pdb
│   │   ├── raw_pdb/                 # contains the single wild and mutant structure.
│   │   │   ├── 1CSE_E.pdb           # extrated from 1CSE.pdb
│   │   │   ├── 1CSE_I.pdb
│   │   │   ├── 1CSE_I.mut.38_E.pdb  # computed mutant structure of 1CSE_E.pdb
│   │   ├── llm_embedding/           # contains the pre-computed LLM embeddings using ESM-2.
│   │   │   ├── 1CSE_E.npy           # LLM embedding of 1CSE_E.pdb, shape=(L, 1280)
│   │   │   ├── 1CSE_I.npy
│   │   │   ├── 1CSE_I.mut.38_E.npy

Files

data.zip

Files (4.8 GB)

Name Size Download all
md5:0da9e5aaa90552f700866c37e701f5b5
4.8 GB Preview Download

Additional details

Identifiers

Other
MuToN

Related works

Is supplemented by
MuToN (Other)

Dates

Created
2023-12-31

References

  • MuToN quantifies binding affinity changes upon protein mutations by geometric deep learning