comparison scripts/validate_fasta.py @ 19:2f7702fd0a4c draft

planemo upload for repository https://github.com/usegalaxy-au/tools-au commit cd0379c8ecc24977dffa462c1897d402c85fa4e6

18:e4a053d67e24

import argparse
import re
import sys
from typing import List

MULTIMER_MAX_SEQUENCE_COUNT = 10
STRIP_SEQUENCE_CHARS = ['\n', '\r', '\t', ' ']


class Fasta:
    def __init__(self, header_str: str, seq_str: str):

            self.fastas.append(Fasta(header, sequence))


class FastaValidator:
    def __init__(
            self,
            min_length=None,
            max_length=None,
            multiple=False):
        self.multiple = multiple
        self.min_length = min_length
        self.max_length = max_length
        self.iupac_characters = {
            'A', 'B', 'C', 'D', 'E', 'F', 'G',
            'H', 'I', 'K', 'L', 'M', 'N', 'P',
            'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X',
            'Y', 'Z', '-'
        }

    def validate(self, fasta_list: List[Fasta]):
        """Perform FASTA validation."""
        self.fasta_list = fasta_list
        self.validate_num_seqs()

                    'Error encountered validating FASTA:\n'
                    'Multimer mode requires multiple input sequence.'
                    f' Only {fasta_count} sequences were detected in'
                    ' the provided file.')

            elif fasta_count > MULTIMER_MAX_SEQUENCE_COUNT:
                sys.stderr.write(
                    f'WARNING: detected {fasta_count} sequences but the'
                    f' maximum allowed is {MULTIMER_MAX_SEQUENCE_COUNT}'
                    ' sequences. The last'
                    f' {fasta_count - MULTIMER_MAX_SEQUENCE_COUNT} sequence(s)'
                    ' have been discarded.\n')
                self.fasta_list = self.fasta_list[:MULTIMER_MAX_SEQUENCE_COUNT]
        else:
            if fasta_count > 1:
                sys.stderr.write(
                    'WARNING: More than 1 sequence detected.'
                    ' Using first FASTA sequence as input.\n')

        # validate
        fv = FastaValidator(
            min_length=args.min_length,
            max_length=args.max_length,
            multiple=args.multimer,
        )
        clean_fastas = fv.validate(fas.fastas)

        # write clean data
        fw = FastaWriter()

        help="Maximum length of input protein sequence (AA)",
        default=None,
        type=int,
    )
    parser.add_argument(
        "--multimer",
        action='store_true',
        help="Require multiple input sequences",
    )
    return parser.parse_args()

19:2f7702fd0a4c

import argparse
import re
import sys
from typing import List

DEFAULT_MAX_SEQUENCE_COUNT = 10
STRIP_SEQUENCE_CHARS = ['\n', '\r', '\t', ' ']


class Fasta:
    def __init__(self, header_str: str, seq_str: str):

            self.fastas.append(Fasta(header, sequence))


class FastaValidator:
    def __init__(
        self,
        min_length=None,
        max_length=None,
        multiple=False,
        max_sequence_count=None,
    ):
        self.multiple = multiple
        self.min_length = min_length
        self.max_length = max_length
        self.iupac_characters = {
            'A', 'B', 'C', 'D', 'E', 'F', 'G',
            'H', 'I', 'K', 'L', 'M', 'N', 'P',
            'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X',
            'Y', 'Z', '-'
        }
        self.max_sequence_count = (
            max_sequence_count
            or DEFAULT_MAX_SEQUENCE_COUNT)

    def validate(self, fasta_list: List[Fasta]):
        """Perform FASTA validation."""
        self.fasta_list = fasta_list
        self.validate_num_seqs()

                    'Error encountered validating FASTA:\n'
                    'Multimer mode requires multiple input sequence.'
                    f' Only {fasta_count} sequences were detected in'
                    ' the provided file.')

            elif fasta_count > self.max_sequence_count:
                raise ValueError(
                    f'WARNING: detected {fasta_count} sequences but the'
                    f' maximum allowed is {self.max_sequence_count}'
                    ' sequences.')
        else:
            if fasta_count > 1:
                sys.stderr.write(
                    'WARNING: More than 1 sequence detected.'
                    ' Using first FASTA sequence as input.\n')

        # validate
        fv = FastaValidator(
            min_length=args.min_length,
            max_length=args.max_length,
            multiple=args.multimer,
            max_sequence_count=args.max_sequence_count,
        )
        clean_fastas = fv.validate(fas.fastas)

        # write clean data
        fw = FastaWriter()

        help="Maximum length of input protein sequence (AA)",
        default=None,
        type=int,
    )
    parser.add_argument(
        "--max-sequences",
        dest='max_sequence_count',
        help="Maximum number of input sequences",
        default=None,
        type=int,
    )
    parser.add_argument(
        "--multimer",
        action='store_true',
        help="Require multiple input sequences",
    )
    return parser.parse_args()