DRAMMA-QUIN
DRAMMA QUIN is a web service for the identification of antimicrobial resistance genes (ARGs) in genomic and metagenomic samples. The platform detects both ARGs that are similar to previously characterized resistance genes and novel resistance gene candidates with little or no similarity to known ARGs. Novel candidates are identified using the DRAMMA machine-learning model, enabling the discovery of previously unrecognized resistance determinants.
DRAMMA-QUIN (Detection of Resistance to AntiMicrobials using Machine-learning Approaches - Query-Upload INterface) provides two tools to analyze genomic data for antimicrobial resistance (AMR) detection: DRAMMA and FAMUS.
DRAMMA: Detection of Resistance to AntiMicrobials using Machine-learning Approaches
DRAMMA is a multifaceted machine-learning approach for novel antimicrobial resistance gene detection in metagenomic data. Unlike most existing methods that rely on sequence similarity to a predefined gene database, DRAMMA utilizes variety of biological features to predict new ARGs with no sequence similarity to known resistance or even annotated genes.
FAMUS: Functional Annotation Method Using Supervised contrastive learning
FAMUS is a SupCon (Supervised Contrastive) learning based framework that annotates protein sequences with function. Input sequences are transformed to numeric vectors with pre-trained neural networks tailored to individual protein family databases, and then compared to sequences of those databases to find the closest match.