Antônio Camargo apcamargo

## query_sra_duckdb.sh
duckdb -c "
INSTALL httpfs;
LOAD httpfs;
INSTALL parquet;
LOAD parquet;
COPY (
  SELECT *
  FROM read_parquet('s3://sra-pub-metadata-us-east-1/sra/metadata/*')
) TO STDOUT WITH (FORMAT CSV, DELIMITER E'\t', HEADER);"

## download_mg_rast.py
#!/usr/bin/env python

import json
import re
import sys
from typing import Generator, Dict, Any, Optional

import requests
from tqdm import tqdm

## polars-fastx.py
from pathlib import Path
from typing import Iterator, Optional, Union

import polars as pl
from needletail import parse_fastx_file
from polars.io.plugins import register_io_source


def scan_fastx(fastx_file: Union[str, Path]) -> pl.LazyFrame:
    schema = pl.Schema(

## sam2tsv.py
#!/usr/bin/env python

"""
This script processes SAM (Sequence Alignment/Map format) inputs from standard
input and extracts alignment information that is then provided in a tab-separated
table. The following fields are produced: query, target, query_length, query_start,
query_end, target_start, target_end, alignment_length, alignment_identity.

This script was designed for use with SAM files produced by minimap2. However,
it will work with any SAM data that:

## calculate_neff.py
#!/usr/bin/env python

import math
import re

import click
from scipy.cluster.hierarchy import fcluster, linkage
from skbio import DistanceMatrix, Protein, TabularMSA, io
from skbio.sequence.distance import hamming

## color_palette_generation.ipynb

      
              1 file
            
          
              0 forks
            
          
                0 comments
              
            
              0 stars
            
          
                apcamargo
                / color_palette_generation.ipynb
            
            
              Created
              September 30, 2024 00:35
            
          
      Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## color_manipulation.py
from coloraide import Color


def lighten(
    color: Color,
    amount: float,
) -> Color:
    """
    Lighten a color by a given amount.
    """

## retrieve_assembly_accession.py
import subprocess

def get_assembly_accession(genbank_accession):
    p1 = subprocess.Popen(
        ["elink", "-db", "nuccore", "-target", "assembly", "-id", genbank_accession],
        stdout=subprocess.PIPE,
        stderr=subprocess.PIPE,
    )
    p2 = subprocess.Popen(
        ["efetch", "-format", "docsum"],

## parse_hhr.py
#!/usr/bin/env python

# hhblits -v 0 -cpu 1 -n 1 -p 90 -z 0 -Z 5000 -b 0 -B 5000 -M 50 -d busco_db/busco -i msa.faa -o msa.hhr

from collections import namedtuple
from pathlib import Path
import argparse

parser = argparse.ArgumentParser(description='Parse hhsearch hhr output file.')
parser.add_argument('-i', help='input hrr path', dest='input_file',type=str, required=True)

## fancy_fasta_reader.py
import bz2
import gzip
import lzma
import textwrap
from contextlib import contextmanager
from enum import Enum, auto
from pathlib import Path


class Compression(Enum):
	duckdb -c "
	INSTALL httpfs;
	LOAD httpfs;
	INSTALL parquet;
	LOAD parquet;
	COPY (
	SELECT *
	FROM read_parquet('s3://sra-pub-metadata-us-east-1/sra/metadata/*')
	) TO STDOUT WITH (FORMAT CSV, DELIMITER E'\t', HEADER);"
	#!/usr/bin/env python

	import json
	import re
	import sys
	from typing import Generator, Dict, Any, Optional

	import requests
	from tqdm import tqdm
	from pathlib import Path
	from typing import Iterator, Optional, Union

	import polars as pl
	from needletail import parse_fastx_file
	from polars.io.plugins import register_io_source


	def scan_fastx(fastx_file: Union[str, Path]) -> pl.LazyFrame:
	schema = pl.Schema(
	#!/usr/bin/env python

	"""
	This script processes SAM (Sequence Alignment/Map format) inputs from standard
	input and extracts alignment information that is then provided in a tab-separated
	table. The following fields are produced: query, target, query_length, query_start,
	query_end, target_start, target_end, alignment_length, alignment_identity.

	This script was designed for use with SAM files produced by minimap2. However,
	it will work with any SAM data that:
	#!/usr/bin/env python

	import math
	import re

	import click
	from scipy.cluster.hierarchy import fcluster, linkage
	from skbio import DistanceMatrix, Protein, TabularMSA, io
	from skbio.sequence.distance import hamming
	from coloraide import Color


	def lighten(
	color: Color,
	amount: float,
	) -> Color:
	"""
	Lighten a color by a given amount.
	"""
	import subprocess

	def get_assembly_accession(genbank_accession):
	p1 = subprocess.Popen(
	["elink", "-db", "nuccore", "-target", "assembly", "-id", genbank_accession],
	stdout=subprocess.PIPE,
	stderr=subprocess.PIPE,
	)
	p2 = subprocess.Popen(
	["efetch", "-format", "docsum"],
	#!/usr/bin/env python

	# hhblits -v 0 -cpu 1 -n 1 -p 90 -z 0 -Z 5000 -b 0 -B 5000 -M 50 -d busco_db/busco -i msa.faa -o msa.hhr

	from collections import namedtuple
	from pathlib import Path
	import argparse

	parser = argparse.ArgumentParser(description='Parse hhsearch hhr output file.')
	parser.add_argument('-i', help='input hrr path', dest='input_file',type=str, required=True)
	import bz2
	import gzip
	import lzma
	import textwrap
	from contextlib import contextmanager
	from enum import Enum, auto
	from pathlib import Path


	class Compression(Enum):