Skip to main content

neoralabDiscovering molecules against antimicrobial resistance.

Bacteria evolve. Discovery must evolve faster.

Antimicrobial resistance was directly attributable to 1.27M deaths in 2019, and associated with 4.95M deaths overall — driven by pathogens that keep defeating conventional treatment paths.

Dotted-globe visualization of bacteria driving antimicrobial resistance worldwide
Scanning electron micrograph of a bacterial colony with a single resistant cell highlighted in green
  • MRSA (S. aureus)

    A persistent hospital-acquired threat, especially when severe infections turn systemic.

  • Pseudomonas aeruginosa

    A difficult ICU pathogen with resistance patterns that constrain standard treatment options.

  • Acinetobacter baumannii

    A recurrent source of bloodstream and respiratory infections in vulnerable patients.

We start where resistance hurts most — MRSA first.

Structure-based small-molecule optimization against priority pathogens, with several more on the list. We lead with MRSA because it combines:

  • Urgent, unmet clinical need
  • Rich structural data our workflow can exploit
  • A straightforward path to experimental validation
Coloured scanning electron micrograph of Staphylococcus aureus (MRSA) cell clusters

Three forces make structure-based AI discovery viable now.

Billions spent, decades lost.

Traditional discovery is slow, costly and fragmented — molecular discovery still runs on trial and error.

The AI stack is production-ready.

Agentic AI, docking and molecular dynamics now run as reproducible, chained workflows.

Pharma needs cost & time out.

R&D teams are under pressure to design candidates against high, unmet medical need.

Drug discovery is slow, costly, and fragmented.

Our agents turn biological targets into testable small-molecule candidates.

We build and use proprietary AI agents to coordinate literature, structural data, molecular design, docking, and validation in traceable workflows. Every research program expands a reusable scientific memory and sharpens the next discovery cycle.

Small-molecule drug candidate bound inside a protein binding pocket during structure-based docking

How our discovery approach compounds knowledge

  1. Scientific memory layer

    A second brain — every project builds reusable, searchable knowledge.

  2. Agentic workflow engine

    Multi-agent systems coordinate literature, structures, tools and reporting.

  3. Explainable discovery

    Rationale, risks, analogs, sources and next experiments — every scientific decision stored.

  4. Closed-loop learning

    Experimental feedback refines ranking and decisions with each completed project.

Small Molecule Design

Generative design of novel small molecules optimized for a chosen biological target.

AMR Discovery

Antibiotic candidate discovery against resistant pathogens, from target to lead.

Agentic Discovery

Purpose-built agents coordinate literature, structures, docking, and molecular dynamics.

Translational Prioritization

Explainable scoring turns computational evidence into candidates ready for experimental validation.

Projects Portfolio

Selected neoralab research programs in antimicrobial resistance and small-molecule drug discovery, powered by our internal agents from target selection to candidate prioritization.

Antibiotics discovery mood image

Antibiotics Discovery

We design small molecules to tackle antimicrobial resistance. Our internal agentic workflows combine generative models, structure-based docking, and in-silico validation to accelerate early discovery and prioritize compounds with real translational potential.

Docking simulation mood image

Agent-Driven Target-Oriented Small Molecule Design

Specialized AI agents move from a biological target to candidate molecules, coordinating generative design, structure-aware evaluation, and iterative refinement.

Research & News

Publications, research updates, and perspectives from across our work in biotechnology, AI, and drug discovery.

Open research

Opening discovery to everyone.

We openly publish the data, benchmarks, and validations behind our discoveries so anyone can inspect, reproduce, and build on the work.

Explore our open research
neoralab logo

Why neoralab

We unite biotechnology, agentic AI, and a multidisciplinary team around a clear vision: discover better antibiotics faster and turn computational insight into experimentally testable candidates.

Who We Are

We are a biotech team of scientists, AI engineers, and builders focused on discovering new therapies against antimicrobial resistance.

Fabio Bove

Fabio Bove

Chief Executive Officer

AI Engineer, Multi-Agent Systems in Drug Discovery

Marco Ferrarini

Marco Ferrarini

Chief Scientific Officer

Master Degree in Medical Biotechnology

Elena Addis

Elena Addis

Scientific Advisor

Clinical Study Coordinator, Microbiology Area

Riccardo Cecchetto

Riccardo Cecchetto

Scientific Advisor

Bioinformatician & Data Analyst with focus on Microbiology

Giovanni Caccialupi

Giovanni Caccialupi

Scientific Advisor

PhD in Genomics, Bioinformatician

Federico Pratissoli

Federico Pratissoli

Strategic Advisor

PhD in AI Engineering & Robotics

Valentino Pisi

Valentino Pisi

Strategic Advisor

Data Analyst and Entrepreneur

Alfredo Boracchini

Alfredo Boracchini

Strategic Advisor

Entrepreneur

Let's advance antibiotic discovery.

We welcome conversations with biotech and pharma teams, research partners, and investors working to overcome antimicrobial resistance.

[email protected]

By submitting, you agree that we may contact you about this request.