BactoAI logo, AI-powered antimicrobial resistance prediction
Request a Pilot

BactoAI: Research predictions from assembled genomes.

See the Demo Request a Pilot

BactoAI model statistics

BactoAI model statistics

  • 97.1%
    sensitivity / 96.4% specificity
    Meropenem, internal hold-out, n=125
  • Under 10 minutes
    Under 10 minutes from an assembled genome
    Sequencing and assembly come first
  • 3
    3 antibiotics currently modeled, with more planned
    Meropenem · Ciprofloxacin · Cefotaxime
The Stakes

A silent pandemic is outpacing the drugs we have to fight it.

1.27M+
Estimated deaths attributable to bacterial AMR in 2019

Source: The Lancet, 2022, global bacterial AMR burden estimate for 2019.

16-20h
Further incubation for phenotypic testing after isolation
10M
Estimated annual AMR deaths by 2050 under the 2015 no-action scenario

Source: Review on Antimicrobial Resistance, 2015. Older modeled projection, not a measured outcome.

$100T
Estimated cumulative global economic cost by 2050 under the 2015 no-action scenario

Source: Review on Antimicrobial Resistance, 2015. Older modeled projection, not a measured outcome.

Bacterial culture plate used for phenotypic susceptibility testing
Today
16-20h
A further 16-20 hours of incubation for phenotypic testing after isolation
→
With BactoAI
<10
Under 10 minutes from an assembled genome. Sequencing and assembly come first. Supports phenotypic testing; does not replace it.
"Antimicrobial resistance is one of the top ten global public health threats facing humanity."
World Health Organization
See how BactoAI changes this →
Research and entrepreneurship journey
Grant
CDIE Catalyst
Program
East Africa Biodesign
First project pitch
GEES Bootcamp
The Problem

Antimicrobial resistance is one of the greatest global health threats.

Traditional culture-based diagnostics delay clinical decisions, contributing to inappropriate antibiotic use, prolonged hospital stays, and increasing antimicrobial resistance.

1.27M+

Estimated deaths attributable to bacterial AMR in 2019. Source: The Lancet, 2022 (doi:10.1016/S0140-6736(21)02724-0).

16-20 hrs

A further 16-20 hours of incubation for phenotypic testing after isolation. BactoAI: Under 10 minutes from an assembled genome. Sequencing and assembly come first.

Research

BactoAI is a research prototype, not approved for clinical use. It supports phenotypic susceptibility testing and does not replace it.

Our Solution

Meet BactoAI

BactoAI is a research prototype for antimicrobial resistance prediction. Under 10 minutes from an assembled genome; sequencing and assembly come first. It is most useful for isolates already sequenced, for example in surveillance.

STEP 1
Patient

Clinical presentation & bacterial infection identified.

STEP 2
Sample

Bacterial isolate collected from the patient.

STEP 3
Sequencing and assembly

Sequencing and assembly → assembled genome (FASTA).

STEP 4
BactoAI

ML models analyze genomic features.

STEP 5
Prediction

Resistance profile & confidence per antibiotic.

STEP 6
Decision support

Research prototype; supports, not replaces, phenotypic susceptibility testing.

Loading demonstration…