Skip to content

RoseTTAFold2 protein/nucleic acid complex prediction

License

Notifications You must be signed in to change notification settings

GanQiao1990/RoseTTAFold2NA

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

36 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RF2NA

GitHub repo for RoseTTAFold2 with nucleic acids

New: April 13, 2023 v0.2

  • Updated weights (https://files.ipd.uw.edu/dimaio/RF2NA_apr23.tgz) for better prediction of homodimer:DNA interactions and better DNA-specific sequence recognition
  • Bugfixes in MSA generation pipeline
  • Support for paired protein/RNA MSAs

Installation

  1. Clone the package
git clone https://github.com/uw-ipd/RoseTTAFold2NA.git
cd RoseTTAFold2NA
  1. Create conda environment
# create conda environment for RoseTTAFold2NA
conda env create -f RF2na-linux.yml

You also need to install NVIDIA's SE(3)-Transformer (please use SE3Transformer in this repo to install).

conda activate RF2NA
cd SE3Transformer
pip install --no-cache-dir -r requirements.txt
python setup.py install
  1. Download pre-trained weights under network directory
cd network
wget https://files.ipd.uw.edu/dimaio/RF2NA_apr23.tgz
tar xvfz RF2NA_apr23.tgz
ls weights/ # it should contain a 1.1GB weights file
cd ..
  1. Download sequence and structure databases
# uniref30 [46G]
wget http://wwwuser.gwdg.de/~compbiol/uniclust/2020_06/UniRef30_2020_06_hhsuite.tar.gz
mkdir -p UniRef30_2020_06
tar xfz UniRef30_2020_06_hhsuite.tar.gz -C ./UniRef30_2020_06

# BFD [272G]
wget https://bfd.mmseqs.com/bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz
mkdir -p bfd
tar xfz bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt.tar.gz -C ./bfd

# structure templates (including *_a3m.ffdata, *_a3m.ffindex)
wget https://files.ipd.uw.edu/pub/RoseTTAFold/pdb100_2021Mar03.tar.gz
tar xfz pdb100_2021Mar03.tar.gz

# RNA databases
mkdir -p RNA
cd RNA

# Rfam [300M]
wget ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/Rfam.full_region.gz
wget ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/Rfam.cm.gz
gunzip Rfam.cm.gz
cmpress Rfam.cm

# RNAcentral [12G]
wget ftp://ftp.ebi.ac.uk/pub/databases/RNAcentral/current_release/rfam/rfam_annotations.tsv.gz
wget ftp://ftp.ebi.ac.uk/pub/databases/RNAcentral/current_release/id_mapping/id_mapping.tsv.gz
wget ftp://ftp.ebi.ac.uk/pub/databases/RNAcentral/current_release/sequences/rnacentral_species_specific_ids.fasta.gz
../input_prep/reprocess_rnac.pl id_mapping.tsv.gz rfam_annotations.tsv.gz   # ~8 minutes
gunzip -c rnacentral_species_specific_ids.fasta.gz | makeblastdb -in - -dbtype nucl  -parse_seqids -out rnacentral.fasta -title "RNACentral"

# nt [151G]
update_blastdb.pl --decompress nt
cd ..

Usage

conda activate RF2NA
cd example
# run Protein/RNA prediction
../run_RF2NA.sh rna_pred rna_binding_protein.fa R:RNA.fa
# run Protein/dsDNA prediction
../run_RF2NA.sh dna_pred dna_binding_protein.fa D:DNA.fa

The first argument to the script is the output folder; remaining arguments are fasta files for individual chains in the structure. Use the tags P:xxx.fa R:xxx.fa D:xxx.fa S:xxx.fa and PR:xxx.fa to specify protein, RNA, dsDNA, ssDNA, and paired protein/RNA respectively (default is protein).

Each chain is a separate file; 'D' will automatically generate a complementary DNA strand to the input strand. Outputs are written to the folder dna_pred and rna_pred.

Expected outputs

You will get a prediction with estimated per-residue LDDT in the B-factor column (models/model_00.pdb)

About

RoseTTAFold2 protein/nucleic acid complex prediction

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 96.7%
  • Shell 2.7%
  • Other 0.6%