Final hw python bi

README.md

@@ -1 +1,100 @@
-# gene_code_tools
+![image](https://github.com/CaptnClementine/gene_code_tools/assets/131146976/68f2999b-5b6e-4668-9865-fae0d4e0b778)
+# Gene code tools
+
+This repository contains Python scripts for processing bioinformatics files such as FASTA, GenBank (GBK), and BLAST output files. The main scripts, `main.py` and `bio_file_processor.py`, provide functionality to parse, extract, and convert data from these file formats.  It also includes a Telegram logger to send notifications when specific functions or tasks are completed.
+
+ Moreover, it offers a custom implementation of a Random Forest Classifier in `custom_random_forest.py`, enabling users to train and make predictions using Random Forest models. This implementation supports parallel processing, allowing for efficient utilization of multiple threads.
+
+PS <span style="color: #bdc3c7;">Based on python homeworks from the [Bioinformatics Institute](https://bioinf.me/)</span>
+
+## Table of Contents
+- [Description](#description)
+- [Installation](#installation)
+- [Script contents](#script-contents)
+  - main.py
+  - bio_file_processor.py
+  - custom_random_forest.py
+- [Contacts](#contacts)
+
+# Description
+
+The repository includes three main scripts:
+
+- [ ] **main.py**: Contains classes and functions for handling biological sequences, filtering DNA sequences, running GENSCAN analysis, and logging function execution with Telegram integration.
+- [ ] **bio_file_processor.py**: Provides additional functions for processing biological sequence files.
+- [ ] **custom_random_forest.py**: Custom Implementation of a Random Forest Classifier with support for Parallel Processing Utilizing Multiple Threads
+
+For detailed documentation of each method and parameter, please refer to the docstrings within each script file. If you want to try out just one function, check the Showcases.ipnyb notebook 💜 Example files can be found in the `example_files` directory.
+
+# Installation
+
+Clone this repository and install all requirements:
+   ```bash
+   git clone https://github.com/your_username/bioinformatics-file-processor.git
+
+   cd bioinformatics-file-processor
+
+   pip install -r requirements.txt
+   ```
+
+# Script contents 
+
+## ⭐ What could be found in **main.py**
+
+### Classes
+
+- `BiologicalSequence`: An abstract base class representing a biological sequence.
+- `NucleicAcidSequence`: Represents a nucleic acid sequence.
+- `DNASequence`: Represents a DNA sequence.
+- `RNASequence`: Represents an RNA sequence.
+- `AminoAcidSequence`: Represents an amino acid sequence.
+- `GenscanOutput`: Represents the output of a GENSCAN analysis.
+
+### Functions
+
+- `filter_dna`: Filters and processes FASTQ sequences based on specified criteria like GC content, length, and quality.
+- `is_in_gc_bounds`: Checks if the GC content of a DNA sequence falls within specified bounds.
+- `is_in_length_bounds`: Checks if the length of a DNA sequence falls within specified bounds.
+- `create_env_file`: Creates a .env file with the provided Telegram API token.
+- `telegram_logger`: Decorator for logging function execution and sending logs to a Telegram chat.
+- `send_telegram_message`: Sends a message to a Telegram chat.
+- `send_telegram_document`: Sends a document to a Telegram chat.
+- `run_genscan`: Runs GENSCAN analysis on the provided sequence or sequence file.
+- `parse_introns`: Parses introns information from the status string parsed from HTML.
+- `parse_exons`: Parses exons information from the status string parsed from HTML.
+- `parse_proteins`: Parses protein sequences from the status string parsed from HTML.
+
+
+## ⭐ What could be found in **bio_file_processor.py**
+### Classes:
+
+- `FastaRecord`: Represents a FASTA record containing sequence information.
+- `OpenFasta`: Opens and iterates through a FASTA file, yielding FastaRecord objects.
+
+### Functions:
+
+
+- `select_genes_from_gbk_to_fasta`: Selects specific genes from a GenBank (GBK) file and saves them as a FASTA file.
+- `convert_multiline_fasta_to_oneline`: Converts a multiline FASTA file into a one-line FASTA format and saves it to a new file.
+- `parse_blast_output`: Parses the output of a BLAST search and extracts sequence identifiers producing significant alignments.
+
+## ⭐ Custom Random Forest Classifier
+
+This Python module provides a custom implementation of a Random Forest Classifier, built using the scikit-learn library. It allows users to train a Random Forest model with various parameters and perform predictions on new data.
+
+### Features
+
+- Customizable number of estimators (trees) in the forest.
+- Ability to specify maximum depth of the trees.
+- Option to set the maximum number of features to consider when looking for the best split.
+- Control over the randomness of the estimator through a random state parameter.
+- Supports parallel processing using multiple threads.
+
+# Contacts
+
+<p align="center">
+  <img src="https://github.com/CaptnClementine/gene_code_tools/assets/131146976/83e7d702-ba84-4e60-8ce9-d7ec3e5b7149" alt="image">
+</p>
+
+
+If you have any questions, suggestions, or encounter any issues while using the amino-analyzer tool, feel free to reach out to [CaptnClementine](https://github.com/CaptnClementine) 💛. You can also contact me directly on Telegram via [this link](https://t.me/Capnclementine).