Actionable Antibiotic Resistance Insights Without Delay

digitalABST® uses machine learning to translate metagenomic bacterial data into clinically relevant antibiotic resistance insights. Designed for critical care environments, it provides rapid, data-driven support for antimicrobial stewardship and treatment planning.

digitalABST®

Machine Learning–Driven Resistance Insights

digitalABST® analyzes output from Bactfast® to predict antibiotic resistance patterns at the species level. By combining genomic data with advanced analytics, it supports faster, more informed antimicrobial decisions in high-acuity settings.

digitalABST® delivers detailed resistance profiling across identified bacterial species. Its machine learning models assess genomic markers associated with resistance, providing clinicians with a comprehensive view of potential antimicrobial effectiveness.

The Challenge

The Limits of Conventional Susceptibility Testing

Slow Culture Turnaround

Delays in obtaining results can postpone targeted treatment, increasing the risk of complications in critical patients.

Culture-Negative Infections

When infections go undetected by traditional methods, clinicians face diagnostic uncertainty that can compromise timely care.

Limited Pathogen Scope

Tests that miss less common or slow-growing organisms may result in incomplete diagnoses, hindering effective treatment decisions.

Contamination ambiguity

Tests that miss less common or slow-growing organisms may result in incomplete diagnoses, hindering effective treatment decisions.

The SOLUTION

How digitalABST® Supports Confident Treatment Decisions

digitalABST® uses the data output from Bactfast® without the need for additional sequencing. Machine modelled resistanceTM provides predictive antimicrobial resistance covering both horizontal and vertical mechanisms. The generated synthetic variations are linked to antibiotic molecules to ascertain sensitivity and resistance. Bacteria replicate at 200 – 1000 bp/s which can cause evolving resistance patterns. digitalABST® used machine modelling to provide predictive AMR based on the ascensions found in Bactfast®

Conventional ABST
Sequenced ABST
digitalABST
Needs a positive culture to get expressed sensitivity
Presence of sequenced mutation does not translate to expression
Machine modelled predictive AMR covers horizontal and vertical mechanisms of resistance
Competitive inhibition causes variability in growth and expression response.
Established mutations are targeted and can miss minor variations. Does not consider horizontal transfer mechanisms of resistance.
Covers both horizontal and vertical mechanisms. ML models update consistently.
Culture dependent
Primer design / alignment on specific WGS of bacteria.
Metagenomic data along with MMRTM evaluates all possible resistance variations for reported accessions and link them to therapeutic molecules

Connect with Credence Genomics to learn more about our detection kits.

Data-Driven Antimicrobial Stewardship at the Point of Care

Dynamically Generated

Resistance Inherited & Acquired

No Additional Chemistry

Antibiotic Recommender

digitalABST®

digitalABST® uses the data output from Bactfast® without the need for additional sequencing. Machine Modelled Resistance™ provides predictive antimicrobial resistance, covering both horizontal and vertical mechanisms. The generated synthetic variations are linked to antibiotic molecules to determine sensitivity and resistance.

Bacteria replicate at 200–1,000 bp/s, which can lead to evolving resistance patterns. digitalABST® uses machine modelling to deliver predictive AMR based on the ascensions identified in Bactfast®.

Our Process

How Credence Genomics Detection Kits Work

Sample Collection & Preparation

Clinical samples are processed using validated wet-lab protocols designed to preserve microbial DNA while minimizing contamination. This ensures consistent, high-quality input across diverse sample types.

Metagenomic Sequencing & Analysis

Next-generation sequencing captures the full microbial landscape within each sample. Proprietary bioinformatics and machine learning algorithms identify pathogens while separating commensal organisms and contaminants.

Actionable Clinical Insights

Results are delivered in a clear, structured format—providing species-level identification and clinically relevant insights that support informed treatment decisions and faster patient care for your needs.

Credence Genomics
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.