Konwar, K. | Search bioRxiv

bioRxiv2024

MetaPathways v3.5: Modularity and Scalability Improvements for Pathway Inference from Environmental Genomes

Over the past decade MO_SCPLOWETAC_SCPLOWPO_SCPLOWATHWAYSC_SCPLOW has advanced as a modular pipeline for constructing environmental pathway genome databases (ePGDBs), increasing our understanding of microbial metabolism at the individual, population and community levels of biological organization. With this release, we have addressed several user experience issues related to installation, module integration, and database management. With a refactored code base, MO_SCPLOWETAC_SCPLOWPO_SCPLOWATHWAYSC_SCPLOW v3.5 enhances the user experience through streamlined installation via package indexes or containers, refined modules, and interface upgrades. It boasts updated algorithm support for sequence feature prediction, annotation, metabolic inference, and coverage metrics including genome resolved metagenomes. Tested and refined on synthetic datasets, MO_SCPLOWETAC_SCPLOWPO_SCPLOWATHWAYSC_SCPLOW v3.5 demonstrates improved performance and usability; facilitating more in-depth exploration of microbial interactions and metabolic functions in environmental genomes that scales with con-temporary sequencing throughput. Availability and ImplementationMO_SCPLOWETAC_SCPLOWPO_SCPLOWATHWAYSC_SCPLOW v3.5 is available via AO_SCPLOWNACONDAC_SCPLOW, DO_SCPLOWOCKERC_SCPLOW, and AO_SCPLOWPPTAINERC_SCPLOW. The source code is available on BO_SCPLOWITC_SCPLOWBO_SCPLOWUCKETC_SCPLOW:https://bitbucket.org/BCB2/metapathways/ The documentation is available via RO_SCPLOWEADC_SCPLOWTO_SCPLOWHEC_SCPLOWDO_SCPLOWOCSC_SCPLOW:https://metapathways.readthedocs.io Contactshallam@mail.ubc.ca

bioinformatics↗

bioRxiv2022

MetaPredict: A machine learning-based tool for predicting metabolic modules in incomplete bacterial genomes

The reconstruction of complete microbial metabolic pathways using omics data from environmental samples remains challenging. Computational pipelines for pathway reconstruction that utilize machine learning methods to predict the presence or absence of KEGG modules in incomplete genomes are lacking. Here, we present MetaPathPredict, a software tool that incorporates machine learning models to predict the presence of complete KEGG modules within bacterial genomic datasets. Using gene annotation data and information from KEGG module databases, MetaPathPredict employs neural network and XGBoost stacked ensemble models to reconstruct and predict the presence of KEGG modules in a genome. MetaPathPredict can be used as a command line tool or as an R package, and both options are designed to be run locally or on a compute cluster. In our benchmarks, MetaPathPredict makes robust predictions of KEGG module presence within highly incomplete genomes.

bioinformatics↗