instanexus 0.1.0__py3-none-any.whl

instanexus/__main__.py

@@ -0,0 +1,54 @@
+import sys
+import argparse
+from . import script_dbg, script_greedy
+
+def main():
+    banner = r"""
+     ______                   __             __  __                                   
+    /\__  _\                 /\ \__         /\ \/\ \                                  
+    \/_/\ \/     ___     ____\ \ ,_\    __  \ \ `\\ \     __   __  _  __  __    ____  
+       \ \ \   /' _ `\  /',__\\ \ \/  /'__`\ \ \ , ` \  /'__`\/\ \/'\/\ \/\ \  /',__\ 
+        \_\ \__/\ \/\ \/\__, `\\ \ \_/\ \L\.\_\ \ \`\ \/\  __/\/>  </\ \ \_\ \/\__, `\
+        /\_____\ \_\ \_\/\____/ \ \__\ \__/.\_\\ \_\ \_\ \____\/\_/\_\\ \____/\/\____/
+        \/_____/\/_/\/_/\/___/   \/__/\/__/\/_/ \/_/\/_/\/____/\//\/_/ \/___/  \/___/ 
+    """
+
+    parser = argparse.ArgumentParser(
+        prog="instanexus",
+        description=(banner + "\n"
+            "InstaNexus CLI: de novo protein sequencing based on InstaNovo,\n\n" \
+            "an end-to-end workflow from de novo peptides to proteins\n\n"
+            "Usage:\n"
+            "  instanexus <command> [options]\n\n"
+            "Available commands:\n"
+            "  dbg       Run De Bruijn Graph assembly pipeline\n"
+            "  greedy    Run greedy assembly pipeline\n\n"
+            "Examples:\n"
+            "  instanexus dbg --input_csv inputs/sample.csv --chain light --folder_outputs outputs --reference\n"
+            "  instanexus greedy --input_csv inputs/sample.csv --folder_outputs outputs\n\n"
+            "Use 'instanexus <command> --help' for detailed options."
+        ),
+        formatter_class=argparse.RawTextHelpFormatter,
+    )
+    
+    parser.add_argument('--version', action='version', version='InstaNexus 0.1.0'),
+
+    subparsers = parser.add_subparsers(dest="command", help="subcommands")
+
+    # subcommands
+    subparsers.add_parser("dbg", help="Run de Bruijn graph assembly pipeline")
+    subparsers.add_parser("greedy", help="Run greedy assembly pipeline")
+
+    args, extra = parser.parse_known_args()
+
+    if args.command == "dbg":
+        sys.argv = [sys.argv[0]] + extra
+        script_dbg.cli()
+    elif args.command == "greedy":
+        sys.argv = [sys.argv[0]] + extra
+        script_greedy.cli()
+    else:
+        parser.print_help()
+
+if __name__ == "__main__":
+    main()

instanexus/alignment.py

@@ -0,0 +1,50 @@
+import os
+import shutil
+import subprocess
+
+from Bio import SeqIO
+
+
+def align_or_copy_fasta(fasta_file, output_file):
+
+    sequences = list(SeqIO.parse(fasta_file, "fasta"))
+
+    if len(sequences) == 1:
+        shutil.copy(fasta_file, output_file)
+    else:
+        subprocess.run(
+            ["clustalo", "-i", fasta_file, "-o", output_file, "--outfmt", "fa"]
+        )
+
+
+def process_alignment(input_folder):
+    """
+    Process all fasta files in the cluster_fasta folder, align them if necessary,
+    and save the results in the align folder.
+    """
+    cluster_fasta_folder = os.path.join(input_folder, "cluster_fasta")
+    align_folder = os.path.join(input_folder, "align")
+
+    # Create the align folder if it does not exist
+    os.makedirs(align_folder, exist_ok=True)
+
+    # Iterate over all folders in the cluster fasta folder
+    for cluster_folder in os.listdir(cluster_fasta_folder):
+        cluster_folder_path = os.path.join(cluster_fasta_folder, cluster_folder)
+        if os.path.isdir(cluster_folder_path):
+            # Create a corresponding folder in the align folder
+            output_cluster_folder = os.path.join(align_folder, cluster_folder)
+            os.makedirs(output_cluster_folder, exist_ok=True)
+
+            # Iterate over all fasta files in the cluster folder
+            for fasta_file in os.listdir(cluster_folder_path):
+                if fasta_file.endswith(".fasta"):
+                    fasta_file_path = os.path.join(cluster_folder_path, fasta_file)
+                    base_filename = os.path.splitext(fasta_file)[0]
+                    output_file = os.path.join(
+                        output_cluster_folder, f"{base_filename}_out.afa"
+                    )
+
+                    align_or_copy_fasta(fasta_file_path, output_file)
+
+    print("All alignment tasks completed.")

instanexus/clustering.py

@@ -0,0 +1,105 @@
+#!/usr/bin/env python
+
+r"""
+ _____  _______  _    _
+|  __ \|__   __|| |  | |
+| |  | |  | |   | |  | |
+| |  | |  | |   | |  | |
+| |__| |  | |   | |__| |
+|_____/   |_|   |______|
+
+__authors__ = Marco Reverenna & Konstantinos Kalogeropoulus
+__copyright__ = Copyright 2024-2025
+__research-group__ = DTU Biosustain (Multi-omics Network Analytics) and DTU Bioengineering
+__date__ = 21 Mar 2025
+__maintainer__ = Marco Reverenna
+__email__ = marcor@dtu.dk
+__status__ = Dev
+"""
+
+import os
+import shutil
+import subprocess
+from tempfile import mkdtemp
+
+import Bio.SeqIO
+import pandas as pd
+from tqdm import tqdm
+
+
+def cluster_fasta_files(input_folder):
+
+    cluster_folder = os.path.join(input_folder, "cluster")
+    os.makedirs(cluster_folder, exist_ok=True)
+
+    temp_dir = mkdtemp(prefix="mmseqs-")  # create a temporary directory for mmseqs
+
+    # Iterate over all fasta files in the folder
+    for fasta_file in os.listdir(input_folder):
+        if fasta_file.endswith(".fasta"):
+            fasta_path = os.path.join(input_folder, fasta_file)
+            print(f"the current fasta path is: {fasta_path}")
+
+            if os.path.isfile(fasta_path):
+
+                base_filename = os.path.splitext(fasta_file)[
+                    0
+                ]  # get the base filename with no extension
+
+                prefix = os.path.join(
+                    cluster_folder, base_filename
+                )  # define the prefix for mmseqs easy-cluster
+
+                print(f"Clustering {fasta_file}...")  # run mmseqs easy-cluster
+                subprocess.run(
+                    [
+                        "mmseqs",
+                        "easy-cluster",
+                        fasta_path,
+                        prefix,
+                        temp_dir,
+                        "--min-seq-id",
+                        "0.85",
+                        "-c",
+                        "0.8",
+                        "--cov-mode",
+                        "1",
+                        "-v",
+                        "1",
+                    ]
+                )
+                print(
+                    f"Clustering completed for {fasta_file}, results stored with prefix {prefix}"
+                )
+
+    shutil.rmtree(temp_dir)
+    print("All clustering tasks completed.")
+
+
+def process_fasta_and_clusters(fasta_file, cluster_tsv_folder, output_base_folder):
+
+    base_filename = os.path.basename(fasta_file).rsplit(".", 1)[0]
+
+    cluster_tsv = os.path.join(cluster_tsv_folder, f"{base_filename}_cluster.tsv")
+
+    if not os.path.isfile(cluster_tsv):
+        print(f"Cluster TSV file not found for {fasta_file}, skipping.")
+        return
+
+    output_folder = os.path.join(output_base_folder, f"{base_filename}_cluster_fasta")
+    os.makedirs(output_folder, exist_ok=True)
+
+    cluster_df = pd.read_csv(
+        cluster_tsv, sep="\t", header=None, names=["cluster", "contig"]
+    )
+
+    records = list(Bio.SeqIO.parse(fasta_file, "fasta"))
+
+    clusters = cluster_df["cluster"].unique()
+
+    for cluster in tqdm(clusters, desc=f"Processing clusters for {base_filename}"):
+        contigs = cluster_df[cluster_df["cluster"] == cluster]["contig"].values
+        contig_records = [record for record in records if record.id in contigs]
+        Bio.SeqIO.write(
+            contig_records, os.path.join(output_folder, f"{cluster}.fasta"), "fasta"
+        )

instanexus/clustering_stats.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python
+
+r"""
+ _____  _______  _    _
+|  __ \|__   __|| |  | |
+| |  | |  | |   | |  | |
+| |  | |  | |   | |  | |
+| |__| |  | |   | |__| |
+|_____/   |_|   |______|
+
+__authors__ = Marco Reverenna
+__copyright__ = Copyright 2025-2026
+__research-group__ = DTU Biosustain (Multi-omics Network Analytics) and DTU Bioengineering
+__date__ = 26 Jun 2025
+__maintainer__ = Marco Reverenna
+__email__ = marcor@dtu.dk
+__status__ = Dev
+"""
+
+import os
+
+import pandas as pd
+
+base_directory = (
+    "/home/marcor/works/assembly/outputs/ma1/light"  # Change this to your actual path
+)
+
+merged_data = []
+
+log_file_path = os.path.join(base_directory, "missing_statistics_log.txt")
+missing_folders = []
+
+for folder in os.listdir(base_directory):
+    folder_path = os.path.join(base_directory, folder)
+    statistics_path = os.path.join(folder_path, "statistics")
+
+    if os.path.isdir(statistics_path):
+        contigs_file = os.path.join(statistics_path, "contigs_stats_default.tsv")
+        scaffolds_file = os.path.join(statistics_path, "scaffolds_stats_default.tsv")
+
+        if os.path.exists(contigs_file) and os.path.exists(scaffolds_file):
+            # Read both files
+            df_contigs = pd.read_csv(contigs_file, sep="\t")
+            df_scaffolds = pd.read_csv(scaffolds_file, sep="\t")
+
+            # Add a column indicating the source folder
+            df_contigs["Source_Folder"] = folder
+            df_scaffolds["Source_Folder"] = folder
+
+            # Append to the merged list
+            merged_data.append(df_contigs)
+            merged_data.append(df_scaffolds)
+        else:
+            # Log missing files
+            missing_folders.append(folder)
+
+if merged_data:
+    final_df = pd.concat(merged_data, ignore_index=True)
+    final_df.to_csv(
+        os.path.join(base_directory, "merged_statistics.tsv"), sep="\t", index=False
+    )
+    print("Merged DataFrame saved as 'merged_statistics.tsv'.")
+else:
+    print("No valid statistics files found.")
+
+# Write the log file
+if missing_folders:
+    with open(log_file_path, "w") as log_file:
+        log_file.write("Missing statistics files in the following folders:\n")
+        log_file.write("\n".join(missing_folders))
+    print(f"Log file saved as '{log_file_path}'.")
+else:
+    print("All statistics files were found.")

instanexus/compute_statistics.py

@@ -0,0 +1,94 @@
+#!/usr/bin/env python
+
+"""Calculates and saves statistics.
+ _____  _______  _    _
+|  __ \|__   __|| |  | |
+| |  | |  | |   | |  | |
+| |  | |  | |   | |  | |
+| |__| |  | |   | |__| |
+|_____/   |_|   |______|
+
+__authors__ = Marco Reverenna
+__copyright__ = Copyright 2024-2025
+__reserach-group__ = DTU Biosustain (Multi-omics Network Analytics) and DTU Bioengineering
+__date__ = 26 Jun 2024
+__maintainer__ = Marco Reverenna
+__email__ = marcor@dtu.dk
+__status__ = Dev
+"""
+
+import json
+import os
+
+
+def compute_assembly_statistics(df, sequence_type, output_folder, reference, **params):
+    """Statistics for contigs and scaffolds
+
+    Args:
+        df: DataFrame with mapped values
+        sequence_type: either 'contigs' or 'scaffold'
+        output_folder: folder to save output
+        reference: reference protein normalized
+    """
+
+    statistics = {}
+    statistics.update(params)  # add the hyperparameters to the statistics
+
+    df["sequence_length"] = df["end"] - df["start"] + 1
+
+    # Reference coordinates
+    statistics["reference_start"] = int(0)
+    statistics["reference_end"] = int(len(reference) + 1)
+
+    # Sequences statistics
+    statistics["total_sequences"] = int(len(df))
+    statistics["average_length"] = float(df["sequence_length"].mean())
+    statistics["min_length"] = int(df["sequence_length"].min())
+    statistics["max_length"] = int(df["sequence_length"].max())
+
+    # Create a set of covered positions (adjusting for 0-based indexing)
+    covered_positions = set()
+    for start, end in zip(df["start"], df["end"]):
+        covered_positions.update(
+            range(start - 1, end)
+        )  # Convert 1-based to 0-based indexing
+    statistics["coverage"] = float(len(covered_positions) / statistics["reference_end"])
+
+    # Identity score statistics
+    statistics["mean_identity"] = float(df["identity_score"].mean())
+    statistics["median_identity"] = float(df["identity_score"].median())
+    # statistics['std_identity'] = float(df['identity_score'].std())
+
+    # Mismatch statistics
+    statistics["perfect_matches"] = int(
+        sum(df["mismatches_pos"].apply(len) == 0)
+    )  # sequences with no mismatches
+    all_mismatches = [pos for mismatches in df["mismatches_pos"] for pos in mismatches]
+    statistics["total_mismatches"] = int(len(set(all_mismatches)))
+
+    # N50 and N90 calculations
+    lengths = sorted(df["sequence_length"], reverse=True)
+    total_length = sum(lengths)
+
+    cumulative_length = 0
+    n50 = None
+    n90 = None
+    for length in lengths:
+        cumulative_length += length
+        if n50 is None and cumulative_length >= total_length * 0.5:
+            n50 = length
+        if n90 is None and cumulative_length >= total_length * 0.9:
+            n90 = length
+        if n50 is not None and n90 is not None:
+            break
+
+    statistics["N50"] = int(n50)
+    statistics["N90"] = int(n90)
+
+    # Save JSON file
+    file_name = f"{sequence_type}_stats.json"
+    output_path = os.path.join(output_folder, file_name)
+    with open(output_path, "w") as file:
+        json.dump(statistics, file, indent=4)
+
+    return statistics