Document the functions

.gitignore

@@ -0,0 +1,2 @@
+*.html
+data/multiqc_data

README.org

@@ -0,0 +1,59 @@
+* Adapter parser
+
+This tool parses fastqc reports to extract the adapter sequences, from the *Overrepresented sequences*, and then outputs them to a text file. It also outputs the mean and standard deviation of the sequences length.
+
+** Technologies
+
+- Pandas
+
+** Installation
+
+This project uses [[https://nixos.org][Nix]] to ensure reproducible
+builds.
+
+1.  Install Nix (compatible with MacOS, Linux and
+    [[https://docs.microsoft.com/en-us/windows/wsl/about][WSL]]):
+
+#+begin_src bash
+curl -L https://nixos.org/nix/install | sh
+#+end_src
+
+2.  Clone the repository:
+
+#+begin_src bash
+git clone https://git.coolneng.duckdns.org/coolneng/adapter-parser
+#+end_src
+
+3.  Change the working directory to the project:
+
+#+begin_src bash
+cd adapter-parser
+#+end_src
+
+4.  Enter the nix-shell:
+
+#+begin_src bash
+nix-shell
+#+end_src
+
+After running these commands, you will find yourself in a shell that
+contains all the needed dependencies.
+
+** Usage
+
+The program expects a folder containing the fastqc reports as an input and an output file where to store the sequences in the FASTA format.
+
+#+begin_src bash
+python src/parser.py <input> <output>
+#+end_src
+
+#+RESULTS:
+:
+: usage: parser.py [-h] input output
+:
+: positional arguments:
+:   input       directory containing the fastqc reports
+:   output      file where to export the sequences
+:
+: optional arguments:
+:   -h, --help  show this help message and exit

parser.py

@@ -0,0 +1,80 @@
+from argparse import ArgumentParser
+from glob import glob
+from typing import List, Tuple
+from re import sub
+
+from pandas import DataFrame, read_html, Series
+
+
+def remove_parenthesis(identifier):
+    """
+    Remove parenthesis from the sequence identifier
+    """
+    sequence_str = "".join(map(str, identifier))
+    return sub(r"[()]", "", sequence_str)
+
+
+def extract_adapters(files) -> Tuple[Series, List]:
+    """
+    Extract the adapters sequences and statistics from the files
+    """
+    all_adapters = DataFrame()
+    for entry in files:
+        tables = read_html(entry)
+        if len(tables) > 1:
+            adapter_sequences = tables[1].Sequence
+            all_adapters = all_adapters.append(adapter_sequences)
+    processed_adapters = preprocess_dataframe(all_adapters)
+    stats = [
+        processed_adapters.str.len().mean(),
+        processed_adapters.str.len().std(),
+    ]
+    return processed_adapters, stats
+
+
+def preprocess_dataframe(adapters) -> Series:
+    """
+    Remove empty sequences and duplicates
+    """
+    na_free_adapters = adapters.dropna(axis=1)
+    stacked_adapters = na_free_adapters.stack()
+    duplicate_free_adapters = stacked_adapters.drop_duplicates()
+    return duplicate_free_adapters
+
+
+def save_to_file(filename, adapters) -> None:
+    """
+    Save the adapter sequences as a FASTA file
+    """
+    with open(filename, "w") as f:
+        for index, value in adapters.iteritems():
+            sequence_id = remove_parenthesis(index)
+            fasta_entry = f">{sequence_id}\n{value}\n"
+            f.write(fasta_entry)
+
+
+def parse_arguments():
+    """
+    Parse the command-line arguments
+    """
+    parser = ArgumentParser()
+    parser.add_argument("input", help="directory containing the fastqc reports")
+    parser.add_argument("output", help="file where to export the sequences")
+    return parser.parse_args()
+
+
+def main():
+    """
+    Extract the adapters from FASTQC reports to a FASTA file and show sequence length statistics
+    """
+    args = parse_arguments()
+    file_list = glob(args.input + "/*fastqc.html")
+    adapters, stats = extract_adapters(file_list)
+    save_to_file(args.output, adapters)
+    print(
+        f"Mean of sequence length: {stats[0]}, standard deviation of sequence length {stats[1]}"
+    )
+
+
+if __name__ == "__main__":
+    main()

shell.nix

@@ -2,4 +2,4 @@
 
 with pkgs;
 
-mkShell { buildInputs = [ python39 python39Packages.beautifulsoup4 ]; }
+mkShell { buildInputs = [ python39 python39Packages.pandas ]; }