-
Notifications
You must be signed in to change notification settings - Fork 0
Home
Thank you for your interest in PhageScanner! This wiki serves as the official documentation and will be continuously updated. It contains comprehensive details on how to install, configure, and use PhageScanner, along with practical examples. For a quick start, you may prefer to begin with our Quick Start Guide.
NOTE: PhageScanner is optimized for 64-bit macOS and Ubuntu Linux. Windows users can utilize the tool via the Docker image or by installing the Ubuntu Windows Subsystem for Linux (WSL). This workaround is necessary because some dependencies, such as cd-hit, phanotate, and megahit, rely on C++ libraries not natively supported on Windows. For the best experience, we recommend using PhageScanner on macOS or Linux.
PhageScanner incorporates three main pipelines, each designed to seamlessly lead into the next:
- Download Pipeline: Sets up the local database of proteins.
- Training Pipeline: Handles the training of machine learning models.
- Prediction Pipeline: Applies models to annotate genomes and metagenomics datasets.
These pipelines support extensive customization to suit various research needs, such as predicting different protein classes like "Toxic Protein" or "Phage Virion Protein".
For details on how to configure these pipelines using configuration files, refer to: