RF2 Nucleic Acid

The rf2-nucleic-acid API provides an interface to access the RoseTTAFold2 Nucleic Acid tool. The source code and additional documentation can be found on the github page GitHub - uw-ipd/RoseTTAFold2NA: RoseTTAFold2 protein/nucleic acid complex prediction

This RosettaFold2 Nucleic Acid tool is capable modeling structures of protein protein complexes, protein/double strand dna complexes, protein/single strand dna, and protein/rna complexes.

The valid inputs are protein sequences, single strand dna sequences, double strand dna sequences, rna sequences, and paired protein-rna msas.

The input arguments are as follows:

--fasta-file: The path to the protein fasta file(s)

--single-strand-dna: The path to the dna fasta file(s) which should be treated as single strands

--double-strand-dna: The path to dna fasta file(s) which should have a paired second strand generated for them.

--rna-fasta: The path to rna fasta file(s)

--protein-rna-msa: Paired protein-rna MSAs. Contact support for help generating these if you need them for your project.

--gpu-type: The type of GPU to use. If more than about 500 protein residues or about 50 nucleic acid residues are present a A100 gpu should be used. Otherwise the default t4 should be sufficient.

Outputs:

The output pdb file can be found in out/results/models/model_00.pdb after running the “get” command.