https://bioinformaticsonline.com/snippets?offset=10 https://bioinformaticsonline.com/snippets/view/44670/extract-the-fasta-sequence-using-ids Thu, 03 Oct 2024 01:27:32 -0500 https://bioinformaticsonline.com/snippets/view/44670/extract-the-fasta-sequence-using-ids #Extract sequences with names in file name.list, one sequence name per line: seqtk subseq input.fasta name.list > output.fasta]]> LEGE https://bioinformaticsonline.com/snippets/view/44665/r-script-to-add-p-values-in-plots Tue, 17 Sep 2024 20:23:02 -0500 https://bioinformaticsonline.com/snippets/view/44665/r-script-to-add-p-values-in-plots library(ggplot2) library(tidyverse) library(ggpubr) my_comp <- list( c("0.5", "1"), c("1", "2"), c("0.5", "2") ) ggboxplot(ToothGrowth, x = "dose", y = "len", fill = "dose", palette = "Dark2")+ stat_compare_means(label = "p.format", comparisons = my_comp, method = "t.test", symnum.args = list(cutpoints = c(0, 0.001, 1), symbols = "p < 0.001"))]]> LEGE https://bioinformaticsonline.com/snippets/view/44567/python-script-to-parse-a-fastq-file Mon, 10 Jun 2024 11:20:27 -0500 https://bioinformaticsonline.com/snippets/view/44567/python-script-to-parse-a-fastq-file #Python script to parse a FASTQ file and extract basic information such as the sequence identifier, sequence, and quality scores #pip install biopython from Bio import SeqIO def parse_fastq(fastq_file): # Initialize a list to store parsed sequences sequences = [] # Read the sequences from the FASTQ file for record in SeqIO.parse(fastq_file, "fastq"): sequence_info = { "id": record.id, "sequence": str(record.seq), "quality": record.letter_annotations["phred_quality"] } sequences.append(sequence_info) return sequences # Example usage fastq_file = "path/to/your/sequences.fastq" parsed_sequences = parse_fastq(fastq_file) # Print out the parsed sequences for seq in parsed_sequences: print(f"ID: {seq['id']}") print(f"Sequence: {seq['sequence']}") print(f"Quality: {seq['quality']}") print()]]> Abhi https://bioinformaticsonline.com/snippets/view/44566/python-script-to-calculate-basic-genome-stats Mon, 10 Jun 2024 11:18:32 -0500 https://bioinformaticsonline.com/snippets/view/44566/python-script-to-calculate-basic-genome-stats from Bio import SeqIO def calculate_genome_stats(fasta_file): # Initialize variables to store genome statistics genome_length = 0 gc_count = 0 a_count = 0 t_count = 0 c_count = 0 g_count = 0 # Read the genome sequence from the FASTA file for record in SeqIO.parse(fasta_file, "fasta"): sequence = record.seq genome_length += len(sequence) a_count += sequence.count('A') t_count += sequence.count('T') c_count += sequence.count('C') g_count += sequence.count('G') gc_count += sequence.count('G') + sequence.count('C') # Calculate GC content gc_content = (gc_count / genome_length) * 100 if genome_length > 0 else 0 # Print genome statistics print(f"Genome Length: {genome_length} bp") print(f"A Count: {a_count}") print(f"T Count: {t_count}") print(f"C Count: {c_count}") print(f"G Count: {g_count}") print(f"GC Content: {gc_content:.2f}%") # Example usage fasta_file = "path/to/your/genome.fasta" calculate_genome_stats(fasta_file)]]> Abhi https://bioinformaticsonline.com/snippets/view/44565/python-script-to-create-fastq-file-with-random-sequences Mon, 10 Jun 2024 08:21:32 -0500 https://bioinformaticsonline.com/snippets/view/44565/python-script-to-create-fastq-file-with-random-sequences import random def generate_random_sequence(length): bases = ['A', 'C', 'G', 'T'] return ''.join(random.choice(bases) for _ in range(length)) def generate_random_quality(length): return ''.join(chr(random.randint(33, 73)) for _ in range(length)) def generate_fastq_entry(sequence_length): sequence = generate_random_sequence(sequence_length) quality = generate_random_quality(sequence_length) return f"@SEQ_ID\n{sequence}\n+\n{quality}\n" def generate_fastq_file(num_entries, sequence_length, file_path): with open(file_path, 'w') as f: for _ in range(num_entries): entry = generate_fastq_entry(sequence_length) f.write(entry) # Generate a FASTQ file with 5 entries, each with a sequence length of 50 bases generate_fastq_file(100, 50, 'random.fastq')]]> Abhi https://bioinformaticsonline.com/snippets/view/44532/commands-to-create-conda-env Mon, 13 May 2024 06:38:11 -0500 https://bioinformaticsonline.com/snippets/view/44532/commands-to-create-conda-env (base) [lege@hn1 testVisanu]$ conda create -n pythonENV python=3.10 scipy=1.13.0 astroid babel Channels: - conda-forge - bioconda - defaults Platform: linux-64 Collecting package metadata (repodata.json): done Solving environment: done ==> WARNING: A newer version of conda exists. <== current version: 24.3.0 latest version: 24.4.0 Please update conda by running $ conda update -n base -c conda-forge conda ## Package Plan ## environment location: /home/lege/miniforge3/envs/pythonENV added / updated specs: - astroid - babel - python=3.10 - scipy=1.13.0 The following packages will be downloaded: package | build ---------------------------|----------------- astroid-3.2.0 | py310hff52083_0 389 KB conda-forge babel-2.14.0 | pyhd8ed1ab_0 7.3 MB conda-forge libblas-3.9.0 |22_linux64_openblas 14 KB conda-forge libcblas-3.9.0 |22_linux64_openblas 14 KB conda-forge libgfortran-ng-13.2.0 | h69a702a_7 24 KB conda-forge libgfortran5-13.2.0 | hca663fb_7 1.4 MB conda-forge liblapack-3.9.0 |22_linux64_openblas 14 KB conda-forge libopenblas-0.3.27 |pthreads_h413a1c8_0 5.3 MB conda-forge numpy-1.26.4 | py310hb13e2d6_0 6.7 MB conda-forge pytz-2024.1 | pyhd8ed1ab_0 184 KB conda-forge scipy-1.13.0 | py310h93e2701_1 15.8 MB conda-forge typing-extensions-4.11.0 | hd8ed1ab_0 10 KB conda-forge typing_extensions-4.11.0 | pyha770c72_0 37 KB conda-forge ------------------------------------------------------------ Total: 37.1 MB The following NEW packages will be INSTALLED: _libgcc_mutex conda-forge/linux-64::_libgcc_mutex-0.1-conda_forge _openmp_mutex conda-forge/linux-64::_openmp_mutex-4.5-2_gnu astroid conda-forge/linux-64::astroid-3.2.0-py310hff52083_0 babel conda-forge/noarch::babel-2.14.0-pyhd8ed1ab_0 bzip2 conda-forge/linux-64::bzip2-1.0.8-hd590300_5 ca-certificates conda-forge/linux-64::ca-certificates-2024.2.2-hbcca054_0 ld_impl_linux-64 conda-forge/linux-64::ld_impl_linux-64-2.40-h55db66e_0 libblas conda-forge/linux-64::libblas-3.9.0-22_linux64_openblas libcblas conda-forge/linux-64::libcblas-3.9.0-22_linux64_openblas libffi conda-forge/linux-64::libffi-3.4.2-h7f98852_5 libgcc-ng conda-forge/linux-64::libgcc-ng-13.2.0-h77fa898_7 libgfortran-ng conda-forge/linux-64::libgfortran-ng-13.2.0-h69a702a_7 libgfortran5 conda-forge/linux-64::libgfortran5-13.2.0-hca663fb_7 libgomp conda-forge/linux-64::libgomp-13.2.0-h77fa898_7 liblapack conda-forge/linux-64::liblapack-3.9.0-22_linux64_openblas libnsl conda-forge/linux-64::libnsl-2.0.1-hd590300_0 libopenblas conda-forge/linux-64::libopenblas-0.3.27-pthreads_h413a1c8_0 libsqlite conda-forge/linux-64::libsqlite-3.45.3-h2797004_0 libstdcxx-ng conda-forge/linux-64::libstdcxx-ng-13.2.0-hc0a3c3a_7 libuuid conda-forge/linux-64::libuuid-2.38.1-h0b41bf4_0 libxcrypt conda-forge/linux-64::libxcrypt-4.4.36-hd590300_1 libzlib conda-forge/linux-64::libzlib-1.2.13-hd590300_5 ncurses conda-forge/linux-64::ncurses-6.5-h59595ed_0 numpy conda-forge/linux-64::numpy-1.26.4-py310hb13e2d6_0 openssl conda-forge/linux-64::openssl-3.3.0-hd590300_0 pip conda-forge/noarch::pip-24.0-pyhd8ed1ab_0 python conda-forge/linux-64::python-3.10.14-hd12c33a_0_cpython python_abi conda-forge/linux-64::python_abi-3.10-4_cp310 pytz conda-forge/noarch::pytz-2024.1-pyhd8ed1ab_0 readline conda-forge/linux-64::readline-8.2-h8228510_1 scipy conda-forge/linux-64::scipy-1.13.0-py310h93e2701_1 setuptools conda-forge/noarch::setuptools-69.5.1-pyhd8ed1ab_0 tk conda-forge/linux-64::tk-8.6.13-noxft_h4845f30_101 typing-extensions conda-forge/noarch::typing-extensions-4.11.0-hd8ed1ab_0 typing_extensions conda-forge/noarch::typing_extensions-4.11.0-pyha770c72_0 tzdata conda-forge/noarch::tzdata-2024a-h0c530f3_0 wheel conda-forge/noarch::wheel-0.43.0-pyhd8ed1ab_1 xz conda-forge/linux-64::xz-5.2.6-h166bdaf_0 Proceed ([y]/n)? y Downloading and Extracting Packages: Preparing transaction: done Verifying transaction: done Executing transaction: done # # To activate this environment, use # # $ conda activate pythonENV # # To deactivate an active environment, use # # $ conda deactivate]]> LEGE https://bioinformaticsonline.com/snippets/view/44524/python-script-to-finds-extact-similar-sequence-between-two-multi-fasta-files Thu, 02 May 2024 02:54:56 -0500 https://bioinformaticsonline.com/snippets/view/44524/python-script-to-finds-extact-similar-sequence-between-two-multi-fasta-files from Bio.Blast.Applications import NcbiblastnCommandline import os import sys def perform_local_blast(query_file, subject_file, output_file): # Set up the BLAST command with format 6 (tab-delimited) blastn_cline = NcbiblastnCommandline(query=query_file, subject=subject_file, out=output_file, outfmt=6, word_size=16, perc_identity=100) # Run BLAST stdout, stderr = blastn_cline() # Check for errors if stderr: print("Error running BLAST:") print(stderr) def parse_blast_results(output_file): # Parse BLAST results with open(output_file, "r") as result_handle: for line in result_handle: fields = line.strip().split('\t') qseq = fields[0] # Extract the aligned query sequence (qseq) #print("Aligned Query Sequence:", qseq) # Print other relevant information if needed def main(): if len(sys.argv) != 4: print("Usage: python script.py query.fasta subject.fasta output.txt") sys.exit(1) query_file = sys.argv[1] subject_file = sys.argv[2] output_file = sys.argv[3] # Perform local BLAST perform_local_blast(query_file, subject_file, output_file) # Parse and print BLAST results #parse_blast_results(output_file) if __name__ == "__main__": main()]]> LEGE https://bioinformaticsonline.com/snippets/view/44494/python-script-to-parse-gff-file Wed, 27 Mar 2024 20:42:11 -0500 https://bioinformaticsonline.com/snippets/view/44494/python-script-to-parse-gff-file def parse_gff(gff_file): features = [] with open(gff_file, 'r') as f: for line in f: if not line.startswith('#'): # Ignore comment lines fields = line.strip().split('\t') feature = { 'seqid': fields[0], 'source': fields[1], 'type': fields[2], 'start': int(fields[3]), 'end': int(fields[4]), 'score': fields[5], 'strand': fields[6], 'phase': fields[7], 'attributes': dict(item.split('=') for item in fields[8].split(';')) } features.append(feature) return features # Usage example gff_file = 'example.gff' parsed_features = parse_gff(gff_file) for feature in parsed_features: print(feature)]]> LEGE https://bioinformaticsonline.com/snippets/view/44493/python-script-to-convert-fastq-to-fasta Wed, 27 Mar 2024 20:30:32 -0500 https://bioinformaticsonline.com/snippets/view/44493/python-script-to-convert-fastq-to-fasta def fastq_to_fasta(fastq_file, fasta_file): with open(fastq_file, 'r') as fq: with open(fasta_file, 'w') as fa: while True: # Read four lines from the FASTQ file header = fq.readline().strip() sequence = fq.readline().strip() fq.readline() # Skip the '+' line quality = fq.readline().strip() # Check for EOF if not header: break # Write to the FASTA file fa.write('>' + header[1:] + '\n') fa.write(sequence + '\n') # Usage example fastq_to_fasta('input.fastq', 'output.fasta')]]> LEGE https://bioinformaticsonline.com/snippets/view/44485/fasta-to-fastq-conversion Mon, 18 Mar 2024 02:41:42 -0500 https://bioinformaticsonline.com/snippets/view/44485/fasta-to-fastq-conversion seqtk seq -F '#' in.fa > out.fq # "#" is fake score.]]> LEGE