Resources

Protein-MGEM Mutation Guided by an Embedded Manifold (MGEM)

MGEM (Mutation Guided by an Embedded Manifold), a methodology for guiding protein abundance through sequence modifications.

COMPSS Computational Scoring and Experimental Evaluation of Enzymes Generated by Neural Networks

Calculates various sequence- and structure-based quality scores for proteins, such as those produced by generative models to enrich sequences for functionality in experiments.

metaGEM Reconstruction of genome scale metabolic models directly from metagenomes

An easy-to-use workflow for generating context specific genome-scale metabolic models and predicting metabolic interactions within microbial communities directly from metagenomic data. metaGEM is a Snakemake workflow that integrates an array of existing bioinformatics and metabolic modeling tools, for the purpose of predicting metabolic interactions within bacterial communities of microbiomes. From whole metagenome shotgun datasets, metagenome assembled genomes (MAGs) are reconstructed, which are then converted into genome-scale metabolic models (GEMs) for in silico simulations. Additional outputs include abundance estimates, taxonomic assignment, growth rate estimation, pangenome analysis, and eukaryotic MAG identification.

ProteinGAN Generative Adversarial Network for generation of protein sequence from a family of proteins

ProteinGAN, a specialised variant of the generative adversarial network that is able to ‘learn’ natural protein sequence diversity and enables the generation of functional protein sequences. ProteinGAN learns the evolutionary relationships of protein sequences directly from the complex multidimensional amino acid sequence space and creates new, highly diverse sequence variants with natural-like physical properties.

CANDIA Canonical Decomposition of Data-Independent-Acquired Spectra

CANDIA is a GPU-powered unsupervised multiway factor analysis framework that deconvolves multispectral scans to individual analyte spectra, chromatographic profiles, and sample abundances, using the PARAFAC (or canonical decomposition) method. The deconvolved spectra can be annotated with traditional database search engines or used as a high-quality input for de novo sequencing methods.

Mining of metagenomes for plastics degrading enzymes Scripts and models from Zrimec et. al. mBIO 2021

Repository contains scripts to reproduce the analysis and figures. The data is available at Zenodo, extract the archive to a folder named ‘data’.

Prediction of gene expression levels from DNA sequence Scripts and models for Zrimec et. al. Nature Communications 2020

This repository contains scripts to reproduce the analysis and figures. The data is available at Zenodo, extract the archive to a folder named ‘data’.