Function run_mmseqs2

modelscope/preprocessors/science/uni_fold.py:42–232

(
        x,
        prefix,
        use_env=True,
        use_templates=False,
        use_pairing=False,
        host_url='https://api.colabfold.com')

def run_mmseqs2(
        x,
        prefix,
        use_env=True,
        use_templates=False,
        use_pairing=False,
        host_url='https://api.colabfold.com') -> Tuple[List[str], List[str]]:
    submission_endpoint = 'ticket/pair' if use_pairing else 'ticket/msa'

    def submit(seqs, mode, N=101):
        n, query = N, ''
        for seq in seqs:
            query += f'>{n}\n{seq}\n'
            n += 1

        res = requests.post(
            f'{host_url}/{submission_endpoint}',
            data={
                'q': query,
                'mode': mode
            })
        try:
            out = res.json()
        except ValueError:
            out = {'status': 'ERROR'}
        return out

    def status(ID):
        res = requests.get(f'{host_url}/ticket/{ID}')
        try:
            out = res.json()
        except ValueError:
            out = {'status': 'ERROR'}
        return out

    def download(ID, path):
        res = requests.get(f'{host_url}/result/download/{ID}')
        with open(path, 'wb') as out:
            out.write(res.content)

    # process input x
    seqs = [x] if isinstance(x, str) else x

    mode = 'env'
    if use_pairing:
        mode = ''
        use_templates = False
        use_env = False

    # define path
    path = f'{prefix}'
    if not os.path.isdir(path):
        os.mkdir(path)

    # call mmseqs2 api
    tar_gz_file = f'{path}/out_{mode}.tar.gz'
    N, REDO = 101, True