gene-fetch 1.0.6__tar.gz

gene_fetch-1.0.6/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Dan Parsons
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

gene_fetch-1.0.6/PKG-INFO

@@ -0,0 +1,87 @@
+Metadata-Version: 2.3
+Name: gene-fetch
+Version: 1.0.6
+Summary: Gene Fetch: High-throughput NCBI Sequence Retrieval Tool
+License: MIT
+Keywords: bioinformatics,ncbi,sequence,genomics,taxonomy,barcodes
+Author: D. Parsons
+Author-email: d.parsons@nhm.ac.uk>, B. Price <b.price@nhm.ac.uk
+Requires-Python: >=3.9
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Dist: biopython (>=1.80)
+Requires-Dist: ratelimit (>=2.2.1)
+Project-URL: Bug Tracker, https://github.com/bge-barcoding/gene_fetch/issues
+Project-URL: Homepage, https://github.com/bge-barcoding/gene_fetch
+Project-URL: Repository, https://github.com/bge-barcoding/gene_fetch
+Description-Content-Type: text/markdown
+
+# Gene Fetch
+Gene Fetch enables high-throughput retreival of sequence data from NCBI databases based on taxonomy IDs (taxids) or taxonomic heirarchies. It can retrieve both protein and/or nucleotide sequences for various genes, including protein-coding genes (e.g., cox1, cytb, rbcl, matk) and rRNA genes (e.g., 16S, 18S).
+
+## Installation:
+Install from PyPI
+```bash
+pip install gene-fetch
+```
+
+## Post-instllation testing:
+- The Gene Fetch package includes comprehensive tests - Testing is divided into basic tests (which don't require external API access) and integration tests (which may require NCBI API credentials).
+Install pytest:
+```bash
+pip install pytest
+```
+Run basic tests:
+```bash
+pytest
+```
+* This will take a few minutes to run 65 tests, consisting of 8 test modules (tests/test_*.py). You will get 1 warning regarding API credentials as these are not provided in the basic tests.
+
+## Usage:
+```bash
+python gene_fetch.py -g/--gene <gene_name> --type <sequence_type> -i/--in <samples.csv> -o/--out <output_directory> 
+```
+`--h/--help`: Show help and exit.
+
+### Required arguments:
+`-g/--gene`: Name of gene to search for in NCBI GenBank database (e.g., cox1/16s/rbcl).
+`--type`: Sequence type to fetch; 'protein', 'nucleotide', or 'both' ('both' will initially search and fetch a protein sequence, and then fetches the corresponding nucleotide CDS for that protein sequence).
+`-i/--in`: Path to input CSV file containing sample IDs and TaxIDs (see [Input](#input) section below).
+`i2/--in2`: Path to alternative input CSV file containing sample IDs and taxonomic information for each sample (see [Input](#input) section below).
+`o/--out`: Path to output directory. The directory will be created if it does not exist.
+`e/--email` and `-k/--api-key`: Email address and associated API key for NCBI account. An NCBI account is required to run this tool (due to otherwise strict API limitations) - information on how to create an NCBI account and find your API key can be found [here](https://support.nlm.nih.gov/kbArticle/?pn=KA-05317).
+### Optional arguments:
+`--protein-size`: Minimum protein sequence length filter. Applicable to mode 'batch' and 'single' search modes (default: 500).
+`--nucleotide-size`: Minimum nucleotide sequence length filter. Applicable to mode 'batch' and 'single' search modes (default: 1500).
+`s/--single`: Taxonomic ID for 'single' sequence search mode (`-i` and `-i2` are ignored when run with `-s` mode). 'single' mode will fetch all (or N if specifying `--max-sequences`) target gene or protein sequences on GenBank for a specific taxonomic ID.
+`--max-sequences`: Maximum number of sequences to fetch for a specific taxonomic ID (only applies when run in 'single' mode).
+`-b/--genbank`: Saves genbank (.gb) files for fetched nucleotide and/or protein sequences to `genbank/` (applies when run in 'batch' or 'single' mode).
+
+
+## Input:
+**Example 'samples.csv' input file (-i/--in)**
+| ID | taxid |
+| --- | --- |
+| sample-1  | 177658 |
+| sample-2 | 177627 |
+| sample-3 | 3084599 |
+
+**Example 'samples_taxonomy.csv' input file (-i2/--in2)**
+| ID | phylum | class | order | family | genus | species |
+| --- | --- | --- | --- | --- | --- | --- |
+| sample-1  | Arthropoda | Insecta | Diptera | Acroceridae | Astomella | |
+| sample-2 | Arthropoda | Insecta | Hemiptera | Cicadellidae | Psammotettix | Psammotettix sabulicola |
+| sample-3 | Arthropoda | Insecta | Trichoptera | Limnephilidae | Dicosmoecus | Dicosmoecus palatus |
+* Leave blank if taxonomic information not known/needed
+
+
+Authored by Dan Parsons and Ben Price @ NHMUK (2025).
+

gene_fetch-1.0.6/README.md

@@ -0,0 +1,60 @@
+# Gene Fetch
+Gene Fetch enables high-throughput retreival of sequence data from NCBI databases based on taxonomy IDs (taxids) or taxonomic heirarchies. It can retrieve both protein and/or nucleotide sequences for various genes, including protein-coding genes (e.g., cox1, cytb, rbcl, matk) and rRNA genes (e.g., 16S, 18S).
+
+## Installation:
+Install from PyPI
+```bash
+pip install gene-fetch
+```
+
+## Post-instllation testing:
+- The Gene Fetch package includes comprehensive tests - Testing is divided into basic tests (which don't require external API access) and integration tests (which may require NCBI API credentials).
+Install pytest:
+```bash
+pip install pytest
+```
+Run basic tests:
+```bash
+pytest
+```
+* This will take a few minutes to run 65 tests, consisting of 8 test modules (tests/test_*.py). You will get 1 warning regarding API credentials as these are not provided in the basic tests.
+
+## Usage:
+```bash
+python gene_fetch.py -g/--gene <gene_name> --type <sequence_type> -i/--in <samples.csv> -o/--out <output_directory> 
+```
+`--h/--help`: Show help and exit.
+
+### Required arguments:
+`-g/--gene`: Name of gene to search for in NCBI GenBank database (e.g., cox1/16s/rbcl).
+`--type`: Sequence type to fetch; 'protein', 'nucleotide', or 'both' ('both' will initially search and fetch a protein sequence, and then fetches the corresponding nucleotide CDS for that protein sequence).
+`-i/--in`: Path to input CSV file containing sample IDs and TaxIDs (see [Input](#input) section below).
+`i2/--in2`: Path to alternative input CSV file containing sample IDs and taxonomic information for each sample (see [Input](#input) section below).
+`o/--out`: Path to output directory. The directory will be created if it does not exist.
+`e/--email` and `-k/--api-key`: Email address and associated API key for NCBI account. An NCBI account is required to run this tool (due to otherwise strict API limitations) - information on how to create an NCBI account and find your API key can be found [here](https://support.nlm.nih.gov/kbArticle/?pn=KA-05317).
+### Optional arguments:
+`--protein-size`: Minimum protein sequence length filter. Applicable to mode 'batch' and 'single' search modes (default: 500).
+`--nucleotide-size`: Minimum nucleotide sequence length filter. Applicable to mode 'batch' and 'single' search modes (default: 1500).
+`s/--single`: Taxonomic ID for 'single' sequence search mode (`-i` and `-i2` are ignored when run with `-s` mode). 'single' mode will fetch all (or N if specifying `--max-sequences`) target gene or protein sequences on GenBank for a specific taxonomic ID.
+`--max-sequences`: Maximum number of sequences to fetch for a specific taxonomic ID (only applies when run in 'single' mode).
+`-b/--genbank`: Saves genbank (.gb) files for fetched nucleotide and/or protein sequences to `genbank/` (applies when run in 'batch' or 'single' mode).
+
+
+## Input:
+**Example 'samples.csv' input file (-i/--in)**
+| ID | taxid |
+| --- | --- |
+| sample-1  | 177658 |
+| sample-2 | 177627 |
+| sample-3 | 3084599 |
+
+**Example 'samples_taxonomy.csv' input file (-i2/--in2)**
+| ID | phylum | class | order | family | genus | species |
+| --- | --- | --- | --- | --- | --- | --- |
+| sample-1  | Arthropoda | Insecta | Diptera | Acroceridae | Astomella | |
+| sample-2 | Arthropoda | Insecta | Hemiptera | Cicadellidae | Psammotettix | Psammotettix sabulicola |
+| sample-3 | Arthropoda | Insecta | Trichoptera | Limnephilidae | Dicosmoecus | Dicosmoecus palatus |
+* Leave blank if taxonomic information not known/needed
+
+
+Authored by Dan Parsons and Ben Price @ NHMUK (2025).

gene_fetch-1.0.6/pyproject.toml

@@ -0,0 +1,45 @@
+[tool.poetry]
+name = "gene-fetch" 
+version = "1.0.6"
+description = "Gene Fetch: High-throughput NCBI Sequence Retrieval Tool"
+authors = ["D. Parsons <d.parsons@nhm.ac.uk>, B. Price <b.price@nhm.ac.uk>"]
+license = "MIT"
+readme = "README.md"
+packages = [{include = "gene_fetch", from = "src"}]
+include = ["tests/*"]
+repository = "https://github.com/bge-barcoding/gene_fetch"
+keywords = ["bioinformatics", "ncbi", "sequence", "genomics", "taxonomy", "barcodes"]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+]
+
+[tool.poetry.dependencies]
+python = ">=3.9"
+biopython = ">=1.80"
+ratelimit = ">=2.2.1"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.0"
+black = "^23.0"
+flake8 = "^6.0"
+pytest-cov = "^6.1.1"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = "test_*.py"
+
+[tool.poetry.scripts]
+gene-fetch = "gene_fetch.main:main"
+
+[tool.poetry.urls]
+"Homepage" = "https://github.com/bge-barcoding/gene_fetch"
+"Bug Tracker" = "https://github.com/bge-barcoding/gene_fetch/issues"

gene_fetch-1.0.6/src/gene_fetch/__init__.py

@@ -0,0 +1,16 @@
+"""
+Gene Fetch - NCBI Sequence Retrieval Tool
+
+This package fetches sequence data from NCBI databases
+using sample taxonomic information.
+"""
+
+__version__ = "1.0.0"
+
+from .core import Config
+from .entrez_handler import EntrezHandler
+from .sequence_processor import SequenceProcessor
+from .output_manager import OutputManager, save_genbank_file
+
+# Expose main entry point for usage
+from .main import main

gene_fetch-1.0.6/src/gene_fetch/core.py

@@ -0,0 +1,410 @@
+# src/gene_fetch/core.py
+"""
+Core functionality for Gene Fetch.
+Contains Config class and basic utility functions.
+"""
+
+import logging
+import sys
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Optional, Set, Dict, List, Any, FrozenSet
+
+logger = logging.getLogger("gene_fetch")
+
+def make_out_dir(path: Path) -> None:
+    """Ensure output directory exists and create if it doesn't."""
+    path.mkdir(parents=True, exist_ok=True)
+
+def setup_logging(output_dir: Path) -> logging.Logger:
+    """Setup logging with both file and console handlers."""
+    make_out_dir(output_dir)
+    
+    # Clear existing handlers
+    logger.handlers.clear()
+    logger.setLevel(logging.INFO)
+    
+    formatter = logging.Formatter("%(asctime)s [%(levelname)s] %(message)s")
+    
+    console_handler = logging.StreamHandler(sys.stdout)
+    console_handler.setFormatter(formatter)
+    logger.addHandler(console_handler)
+    
+    log_path = output_dir / "gene_fetch.log"
+    file_handler = logging.FileHandler(log_path)
+    file_handler.setFormatter(formatter)
+    logger.addHandler(file_handler)
+    
+    logger.info(f"Logging initialised. Log file: {log_path}")
+    return logger
+
+def log_progress(current: int, total: int, interval: int = 10) -> None:
+    """Log progress at specified intervals."""
+    if current == 0:
+        logger.info("")
+        logger.info(f"Starting processing: 0/{total} samples processed (0%)")
+    elif current == total:
+        logger.info(f"Processed: {total}/{total} samples processed (100%)")
+    elif current % interval == 0:
+        percentage = (current / total) * 100
+        logger.info(
+            f"=====   Progress: {current}/{total} samples processed "
+            f"({percentage:.2f}%)"
+        )
+
+def get_process_id_column(header):
+    """Identify the ID column from possible variations."""
+    # Print what's in the header
+    logger.info("")
+    logger.info(f"CSV header detected: {header}")
+    
+    valid_names = [
+        "ID",
+        "process_id",
+        "Process ID",
+        "process id",
+        "Process id",
+        "PROCESS ID",
+        "sample",
+        "SAMPLE",
+        "Sample",
+    ]
+    
+    # Print repr of each header item to see any hidden chars
+    for i, col in enumerate(header):
+        logger.info(f"Header column {i}: {repr(col)}")
+    
+    # Try direct comparison first
+    for col in header:
+        if col in valid_names:
+            logger.info(f"Found matching column: {col}")
+            return col
+    
+    # Try trimming whitespace (in case of spaces)
+    for col in header:
+        trimmed = col.strip()
+        if trimmed in valid_names:
+            logger.info(f"Found matching column after trimming: {trimmed}")
+            return col
+    
+    # Try case-insensitive comparison as last attempt
+    for col in header:
+        if col.upper() in [name.upper() for name in valid_names]:
+            logger.info(f"Found matching column case-insensitive: {col}")
+            return col
+    
+    logger.error(f"No matching column found in {header}")
+    return None
+
+
+# =============================================================================
+# Configuration
+# =============================================================================
+@dataclass
+class Config:
+    """Configuration class for Gene Fetch, containing all runtime settings."""
+    def __init__(self, email, api_key):
+        # Email and API key required
+        if not email:
+            raise ValueError(
+                "Email address required for NCBI API requests. Use -e/--email "
+                "to provide your email."
+            )
+        if not api_key:
+            raise ValueError(
+                "API key required for NCBI API requests. Use -k/--api-key "
+                "to provide your API key."
+            )
+
+
+        # Set run parameters
+        self.email = email
+        self.api_key = api_key
+
+        # With an API key, 10 requests per second can be made
+        self.max_calls_per_second = 10
+
+        # Default batch size for fetching sequences
+        self.fetch_batch_size = 200
+
+        # Delay between batches (seconds) - uniform random delay between 1-2 seconds
+        self.batch_delay = (1, 2)
+
+        # Set search 'type'
+        self.valid_sequence_types = frozenset({"protein", "nucleotide", "both"})
+
+        # Minimum nucleotide and protein lengths for 'batch' mode
+        self.protein_length_threshold = 500
+        self.nucleotide_length_threshold = 1000
+
+        # Minimum nucleotide and protein lengths for 'single' mode
+        self.min_nucleotide_size_single_mode = 200
+        self.min_protein_size_single_mode = 100
+
+        self.gene_search_term = ""
+    
+        # Define gene type categories
+        self._rRNA_genes = {
+            "16s": [
+                "16S ribosomal RNA[Gene]",
+                "16S rRNA[Gene]",
+                "rrs[Gene]",
+                "rrn16[Gene]",
+                "16S ribosomal RNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "16S rRNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "16S[Title] NOT methylase[Title] NOT methyltransferase[Title] "
+                "NOT pseudouridylate[Title] NOT synthase[Title]",
+                "16S ribosomal RNA[All Fields]",
+                "rrs[All Fields]",
+                "rrn16[All Fields]",
+            ],
+            "18s": [
+                "18S ribosomal RNA[Gene]",
+                "18S rRNA[Gene]",
+                "rrn18[Gene]",
+                "SSU rRNA[Gene]",
+                "18S ribosomal RNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "18S rRNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "18S[Title] NOT methylase[Title] NOT methyltransferase[Title] "
+                "NOT pseudouridylate[Title] NOT synthase[Title]",
+                "18S ribosomal RNA[rRNA]",
+                "SSU rRNA[rRNA]",
+                "rrn18[rRNA]",
+            ],
+            "23s": [
+                "23S ribosomal RNA[Gene]",
+                "23S rRNA[Gene]",
+                "rrl[Gene]",
+                "rrn23[Gene]",
+                "23S ribosomal RNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "23S rRNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "23S[Title] NOT methylase[Title] NOT methyltransferase[Title] "
+                "NOT pseudouridylate[Title] NOT synthase[Title]",
+                "23S ribosomal RNA[rRNA]",
+                "rrl[rRNA]",
+                "rrn23[rRNA]",
+            ],
+            "28s": [
+                "28S ribosomal RNA[Gene]",
+                "28S rRNA[Gene]",
+                "rrn28[Gene]",
+                "LSU rRNA[Gene]",
+                "28S ribosomal RNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "28S rRNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "28S[Title] NOT methylase[Title] NOT methyltransferase[Title] "
+                "NOT pseudouridylate[Title] NOT synthase[Title]",
+                "28S ribosomal RNA[rRNA]",
+                "LSU rRNA[rRNA]",
+                "rrn28[rRNA]",
+            ],
+            "12s": [
+                "12S ribosomal RNA[Gene]",
+                "12S rRNA[Gene]",
+                "mt-rrn1[Gene]",
+                "mt 12S rRNA[Gene]",
+                "12S ribosomal RNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "12S rRNA[Title] NOT methylase[Title] NOT "
+                "methyltransferase[Title] NOT pseudouridylate[Title] NOT "
+                "synthase[Title]",
+                "12S[Title] NOT methylase[Title] NOT methyltransferase[Title] "
+                "NOT pseudouridylate[Title] NOT synthase[Title]",
+                "12S ribosomal RNA[rRNA]",
+                "mt-rrn1[rRNA]",
+                "mt 12S rRNA[rRNA]",
+            ],
+            "its1": [
+                "ITS1[Title]",
+                "internal transcribed spacer 1[Title]",
+                "ITS-1[Title]",
+                "ITS 1[Title]",
+                "ITS1 ribosomal DNA[Title]",
+                "ITS1 rDNA[Title]",
+            ],
+            "its2": [
+                "ITS2[Title]",
+                "internal transcribed spacer 2[Title]",
+                "ITS-2[Title]",
+                "ITS 2[Title]",
+                "ITS2 ribosomal DNA[Title]",
+                "ITS2 rDNA[Title]",
+            ],
+            "its": [
+                "ITS[Title]",
+                "internal transcribed spacer[Title]",
+                "ITS region[Title]",
+                "ITS1-5.8S-ITS2[Title]",
+                "ribosomal ITS[Title]",
+                "rDNA ITS[Title]",
+            ],
+            "trnl": [
+                "trnL[Title]",
+                "trnL gene[Title]",
+                "tRNA-Leu[Title]",
+                "tRNA-Leucine[Title]",
+                "trnL-trnF[Title]",
+                "trnL-F[Title]",
+                "chloroplast trnL[Title]",
+                "cp trnL[Title]",
+                "trnL intron[Title]",
+                "trnL-UAA[Title]",
+                '"trnL gene"[Gene]',
+            ],
+        }
+
+        self._protein_coding_genes = {
+            "cox1": [
+                "cox1[Gene]",
+                "COI[Gene]",
+                '"cytochrome c oxidase subunit 1"[Protein Name]',
+                '"cytochrome oxidase subunit 1"[Protein Name]',
+                '"cytochrome c oxidase subunit I"[Protein Name]',
+                '"COX1"[Protein Name]',
+                '"COXI"[Protein Name]',
+            ],
+            "cox2": [
+                "cox2[Gene]",
+                "COII[Gene]",
+                '"cytochrome c oxidase subunit 2"[Protein Name]',
+                '"cytochrome oxidase subunit 2"[Protein Name]',
+                '"cytochrome c oxidase subunit II"[Protein Name]',
+                '"COX2"[Protein Name]',
+                '"COXII"[Protein Name]',
+            ],
+            "cox3": [
+                "cox3[Gene]",
+                "COIII[Gene]",
+                '"cytochrome c oxidase subunit 3"[Protein Name]',
+                '"cytochrome oxidase subunit 3"[Protein Name]',
+                '"cytochrome c oxidase subunit III"[Protein Name]',
+                '"COX3"[Protein Name]',
+                '"COXIII"[Protein Name]',
+            ],
+            "cytb": [
+                "cytb[Gene]",
+                "cob[Gene]",
+                '"cytochrome b"[Protein Name]',
+                '"cytochrome b"[Gene]',
+                '"CYTB"[Protein Name]',
+            ],
+            "nd1": [
+                "nd1[Gene]",
+                "NAD1[Gene]",
+                '"NADH dehydrogenase subunit 1"[Protein Name]',
+                '"ND1"[Protein Name]',
+            ],
+            "nd2": [
+                "nd2[Gene]",
+                "NAD2[Gene]",
+                '"NADH dehydrogenase subunit 2"[Protein Name]',
+                '"ND2"[Protein Name]',
+            ],
+            "rbcl": [
+                "rbcL[Gene]",
+                "RBCL[Gene]",
+                '"ribulose-1,5-bisphosphate carboxylase/oxygenase large '
+                'subunit"[Protein Name]',
+                '"ribulose 1,5-bisphosphate carboxylase/oxygenase large '
+                'subunit"[Protein Name]',
+                '"ribulose bisphosphate carboxylase large chain"[Protein Name]',
+                '"RuBisCO large subunit"[Protein Name]',
+                '"ribulose-1,5-bisphosphate carboxylase/oxygenase small '
+                'subunit"[Protein Name]',
+                '"ribulose 1,5-bisphosphate carboxylase/oxygenase small '
+                'subunit"[Protein Name]',
+                '"ribulose-1,5-bisphosphate carboxylase/oxygenase small '
+                'chain"[Protein Name]',
+                '"RuBisCO small subunit"[Protein Name]',
+                '"Ribulose bisphosphate carboxylase/oxygenase ' 'activase"[Gene]',
+                '"rbcL gene"[Gene]',
+                '"RBCL gene"[Gene]',
+                "rbcL[Title]",
+                "RBCL[Title]",
+            ],
+            "matk": [
+                "matK[Gene]",
+                "MATK[Gene]",
+                '"maturase K"[Protein Name]',
+                '"maturase K"[Gene]',
+                '"maturase-K"[Protein Name]',
+                '"maturase-K"[Gene]',
+                '"Maturase K"[Protein Name]',
+                '"Maturase K"[Gene]',
+                '"matK gene"[Gene]',
+                '"MATK gene"[Gene]',
+                '"trnK-matK"[Gene]',
+                '"maturase type II intron splicing factor"[Protein Name]',
+                '"chloroplast group II intron splicing factor maturase '
+                'K"[Protein Name]',
+                '"type II intron maturase K"[Protein Name]',
+                '"tRNA-lysine maturase K"[Protein Name]',
+            ],
+            "psba": [
+                "psbA[Gene]",
+                "PSBA[Gene]",
+                '"photosystem II protein D1"[Protein Name]',
+                '"photosystem II protein D1"[Gene]',
+                '"PSII D1 protein"[Protein Name]',
+                '"PSII D1 protein"[Gene]',
+                '"photosystem II reaction center protein D1"[Protein Name]',
+                '"photosystem II reaction center protein D1"[Gene]',
+                '"photosystem Q(B) protein"[Protein Name]',
+                '"32 kDa thylakoid membrane protein"[Protein Name]',
+                '"psbA gene"[Gene]',
+                '"PSBA gene"[Gene]',
+                "psbA[Title]",
+                "PSBA[Title]",
+                '"trnH-psbA"[Title]',
+                '"psbA-trnH"[Title]',
+            ],
+        }
+
+    # Update sequence length thresholds
+    def update_thresholds(self, protein_size: int, nucleotide_size: int):
+        """Update the sequence length thresholds."""
+        self.protein_length_threshold = protein_size
+        self.nucleotide_length_threshold = nucleotide_size
+
+    # Set search term based on gene name and type
+    def set_gene_search_term(self, gene_name: str) -> str:
+        """Set the gene search term based on the gene name and type."""
+        gene_name = gene_name.lower()
+
+        # Check if rRNA
+        if gene_name in self._rRNA_genes:
+            self.gene_search_term = "(" + " OR ".join(self._rRNA_genes[gene_name]) + ")"
+            search_type = "rRNA"
+
+        # Check if protein-coding
+        elif gene_name in self._protein_coding_genes:
+            self.gene_search_term = (
+                "(" + " OR ".join(self._protein_coding_genes[gene_name]) + ")"
+            )
+            search_type = "protein-coding"
+
+        else:
+            # Generic search term for non-listed genes
+            self.gene_search_term = (
+                f"({gene_name}[Title] OR {gene_name}[Gene] OR "
+                f'"{gene_name}"[Text Word])'
+            )
+            search_type = "generic"
+
+        return search_type  # Return the type for logging purposes