pub_soft/PPLM
3
0
Fork 0
mirror of https://github.com/junliu621/PPLM.git synced 2026-06-04 14:24:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Jun Liu
2025-06-24 17:11:22 +08:00
committed by GitHub
parent 7b6f925233
commit 3ffc88fdc5
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@@ -31,11 +31,11 @@ binding affinity, and identifying interface residue contacts, respectively.
- Linux Kernel OS
## Software & Dataset Requirements (for PPLM-Contact)
1. **HH-suite3** for MSA Search: [Install HH-suite3](https://github.com/soedinglab/hh-suite)
2. **Uniclust Database**: [Download Uniclust](http://wwwuser.gwdg.de/~compbiol/uniclust/2021_03/)
3. **CCMpred** for DCA: [Install CCMpred](https://github.com/soedinglab/CCMpred)
4. **LoadHHM** for PSSM Calculation: [LoadHHM.py](https://github.com/j3xugit/RaptorX-Contact/blob/master/Common/LoadHHM.py)
5. **ESM-MSA** for Feature Generation: [Install ESM](https://github.com/facebookresearch/esm)
1. **HH-suite3** for MSA Search: Install [HH-suite3](https://github.com/soedinglab/hh-suite) and set the "hhsuite_dir" parameter in the "pplm_contact/config.py" file.
2. **Uniclust Database**: Download the [Uniclust30 database](http://wwwuser.gwdg.de/~compbiol/uniclust/2021_03/) and set the "UniRef_database" parameter in the "config.py" file.
3. **CCMpred** for DCA: Install [ccmpred](https://github.com/soedinglab/CCMpred), or use the pre-packaged version in the "pplm_contact/external_tools" directory. Set the "ccmpred" parameter in the "config.py" file.
4. **LoadHHM** for PSSM Calculation: Download [LoadHHM.py](https://github.com/j3xugit/RaptorX-Contact/blob/master/Common/LoadHHM.py) and place the file in the "pplm_contact" directory of the PPLM package, or use the pre-packaged version within the "pplm_contact" directory.
5. **ESM-MSA** for Feature Generation: Install the [ESM package](https://github.com/facebookresearch/esm), or use the pre-packaged version within "pplm_contact/external_tools" directory. Download the pre-trained [ESM-MSA model](https://dl.fbaipublicfiles.com/fair-esm/models/esm_msa1_t12_100M_UR50S.pt) and set the "esm_msa_model" parameter in the "config.py" file.
## Download parameters
Run the download_parameter.sh script located in the models/ folder of pplm/, pplm_ppi/, pplm_affinity/, and pplm_contact/