CommunityBuilt with LlamaCase studiesBiofy

LLAMA 3.2 90B

Biofy Technologies

News card image
logo
logo
CASE STUDY

Saving lives with faster, more accurate diagnoses of infectious diseases

At a glance

Industry: Technology

Use case: Diagnoses and treatment recommendations for infections

Goal: Provide effective treatment to more patients and save lives

Llama versions: Llama 3.2 90B

Deployment: Oracle Cloud Infrastructure

4 hours
for a diagnosis instead of the typical 5 days
96.7% reduction
in time per diagnostic
2,000
estimated lives saved in the first year

*All results are self-reported and not identifiably repeatable. Generally expected individual results will differ.

THEIR STORY

Transforming life sciences with AI

Biofy Technologies is a Brazilian biotech company at the forefront of the AI revolution. The company provides advanced technological solutions for diverse industries like life sciences, which they serve with AI platforms for genetic data and DNA analysis.

THEIR GOAL

Cut diagnosis time for infections and recommend effective treatments

Infections are a common problem in hospitals, but treating them is challenging. Antibiotics aren’t one-size-fits-all, plus the bacteria and viruses that cause infections evolve rapidly and are becoming resistant to the drugs used to treat them.

Biofy Technologies wanted to use AI to quickly identify bacteria — including new, drug-resistant strains — and propose the appropriate antibiotic treatment. Rather than spending years researching and gathering data, Biofy used Llama to create synthetic training data to bring their life-saving ideas to market quickly.

THEIR SOLUTION

An AI-powered diagnostic and treatment platform

Biofy created the Abby Antibiotics Recommender, an AI-powered solution that diagnoses infections, classifies bacteria and then recommends effective antibiotics, cutting diagnostic times from days to hours.

their solution graphic

Abby classifies bacterial infections, identifies drug resistance and recommends the most effective antibiotics for the bacteria’s genome.

THEIR APPROACH

Open-source Llama synthesized bacterial DNA data for training

To train Abby, Biofy initially used data from the National Center for Biotechnology Information’s (NCBI) genome database. While the NCBI database offered about 720,000 bacterial strains, it wasn’t enough to accommodate the rapid mutation of bacterial DNA.

Biofy turned to Llama 3.2 90B to create synthetic genetic data. After fine-tuning the model with the NCBI database, Llama created over 150,000 additional data points, equipping the solution for more reliable and effective treatment proposals.

In production, Abby runs on Oracle Cloud Infrastructure (OCI). It uses Nanopore MinION technology to sequence bacterial data and then vectorizes it for storage in Oracle Autonomous Database. Oracle AI Vector Search picks out patterns in genetic material, enabling fast bacterial classification and diagnosis — including novel bacteria that have evolved beyond the data in Abby’s knowledge base

their solution graphic

Abby’s data ingestion and treatment recommendation workflow vectorizes bacterial genomes to enable AI-powered analysis.

THEIR SUCCESS

Saving lives with AI-powered diagnoses and treatment of infectious diseases

With Abby, hospitals can quickly identify bacterial infections, determine antibiotic resistance and develop precise treatments. By cutting diagnostic time from days to just four hours, Abby helps physicians treat more patients more effectively. In a single year, Abby prevented an estimated 2,000 deaths.

their solution graphic

Abby enables faster, more accurate diagnoses so providers can deliver better care to more patients

    • 4 hours for a diagnosis instead of the typical 5 days

    • 96.7% reduction in time per diagnostic

    • 2,000 estimated lives saved in the first year

*All results are self-reported and not identifiably repeatable. Generally expected individual results will differ.
We used Llama to generate thousands of synthetic data points capturing bacterial DNA variations that Abby could consult for more accurate diagnoses and recommendations.
"We used Llama to generate thousands of synthetic data points capturing bacterial DNA variations that Abby could consult for more accurate diagnoses and recommendations."

Paulo Perez - CEO, Biofy Technologies

Start building

Create generative AI applications for business with open-source large language models that bring unmatched control, customization and flexibility.
Download Llama
Horizon banner image

Stay up-to-date

Our latest updates delivered to your inbox

Subscribe to our newsletter to keep up with the latest Llama updates, releases and more.