Netabolics | AI-Driven Biosimulation

We build virtual cell models
for drug discovery

Our AI-driven biosimulation platform transform data into mechanistic predictions of cellular behavior

OUR LATEST MODEL FEATURES

Human Genes

0 K

Molecular Species

0 K

Gene-Associated Chemical Reactions

0 K

COMPANY

Netabolics Predictive Biosimulation

Netabolics is a computational biotech company developing virtual cell models to simulate and predict cellular behavior from omics data. Our platform combines mechanistic genome-scale modeling with AI to enable causal predictions of how biological systems respond to pharmacological, genetic, and environmental perturbations.

Our technology captures thousands of molecular changes within cells, allowing rapid in silico exploration of therapeutic hypotheses. Rather than relying on purely empirical approaches, we provide a simulation-based framework to support decision-making in drug discovery, accelerating the identification and validation of promising targets.

Mauro DiNuzzo, Founder & CEO

We envision a future where drug discovery becomes a predictive, simulation-driven discipline. In this paradigm, desired cellular outcomes can be defined computationally, and optimal intervention strategies, such as targets or combinations, can be systematically identified before experimental validation.

Our mission is to accelerate the development of effective and safe therapies

We have an international network of academic, industrial, and technological partners, collaborating research laboratories, and customers that trust our technology.

We constantly seek mission-aligned partners to advance our discovery platform.

TECHNOLOGY

Where Mechanistic Modeling Meets AI

Our technology combines biophysics-based dynamical systems and data-driven methods to generate causal virtual cell models from curated biological knowledge and large-scale omics datasets, enabling the reconstruction of cellular systems at scale. Once instantiated, they can be systematically interrogated through in silico perturbations to predict system-level responses and identify key drivers of biological outcomes.

Our patented technology has been validated on large-scale perturbation datasets, demonstrating its ability to capture complex cellular responses and generate biologically meaningful predictions.

Our approach to in silico drug target selection using AI and biosimulation

Outcome-Driven

We frame drug discovery as a predictive problem: starting from a desired cellular outcome, our models enable the systematic exploration of intervention strategies, such as targets or combinations, through simulation rather than trial-and-error experimentation.

Mechanistic and Interpretable

Unlike purely data-driven approaches, our models are grounded in causal biological mechanisms. This enables interpretability and supports hypothesis generation, target validation, and biomarker identification.

Scalable and Adaptable

Our platform integrates heterogeneous data sources, including public knowledge bases and omics datasets, to construct and refine models across different cell types and conditions. This allows flexible application across diverse research contexts while maintaining a consistent mechanistic framework.

PLATFORM

In Silico Target Discovery

Our platform enables the simulation and analysis of cellular responses to perturbations. The platform combines mechanistic virtual cell models with scalable computation, allowing researchers to explore how biological systems behave under different intervention strategies and identify key control points/drivers of biological outcomes using sensitivity analysis and perturbation-based exploration.

By enabling rapid iteration across thousands of simulated conditions, our approach provides mechanistic insights that complement experimentation and reduces the need for trial-and-error.

Who We Work With

We work with pharmaceutical and biotechnology companies engaged in early-stage research and preclinical development, where understanding complex biological systems is critical to decision-making. These teams typically operate in data-rich environments but lack predictive, mechanistic tools to translate molecular data into actionable insights.

Ideal Use Cases

Our technology is particularly relevant in contexts where:

biological systems are complex and not easily reducible to single pathways
experimental exploration is costly, slow, or combinatorially large
multiple intervention strategies (e.g., targets or combinations) need to be evaluated
causal understanding is required to support decision-making

How We Engage

We support partners through flexible engagement models:

collaborative research projects
API/SaaS access for simulation workflows
private or on-premise deployments for sensitive data environments

Here we show our predictive biosimulation on selected model systems

Our models have been applied to complex systems such as cancer metabolism, demonstrating the ability to capture system-level responses and generate biologically meaningful predictions.

Mauro DiNuzzo. How artificial intelligence enables modeling and simulation of biological networks to accelerate drug discovery. Frontiers in Drug Discovery, Section In silico Methods and Artificial Intelligence for Drug Discovery, Volume 2 (2022). https://doi.org/10.3389/fddsv.2022.1019706

Mauro DiNuzzo, Alessandro Scandurra, Marco Salvatore. Biosimulation-based target deconvolution of cancer metabolism. RExPO24 Conference, 3 (2024). https://doi.org/10.58647/REXPO.24000057.v1

PROGRAMS

Combinational drug discovery & repurposing

We apply our platform to explore therapeutic strategies such as drug combination discovery and repurposing, where complex system-level interactions play a critical role. Our virtual cell models enable the systematic evaluation of how multiple perturbations interact within cellular systems, supporting the identification of synergistic targets and therapeutic strategies.

Our current work includes applications in oncology, where we use in silico simulations to explore and prioritize candidate interventions.

THERAPEUTIC AREA

TARGET

DISCOVERY

OPTIMIZATION

IND-ENABLING

CLINICAL

Oncology

Multiple Targets

These efforts are powered by in silico research and development capabilities. They serve as validation of the platform’s ability to generate actionable insights and are developed in collaboration with partners.

We actively seek collaborations to apply our technology across additional therapeutic areas.

Not sure about our discovery platform? Don't trust us. Request a demo.

Ready to see how AI-powered simulations can revolutionize drug discovery? Contact us today.

First Name

Last Name

Organization Name

Request

GDPR

By sending this request, I confirm that I have read the Privacy Policy and GDPR Information (art. 13 D.Lgs 196/2003; artt. 13 and 14 EU 679/2016) and accept the relevant terms.

* Required fields

Netabolics received funding from the European Regional Development Fund "Voucher Internazionalizzazione PMI" (Regione Lazio, POR-FESR 2021-2027, Det. N. G15825 of 26/11/2024). The aim of the projects (Prot. n. A0828-2024-089363 of 14/01/2025, approved for funding with Det. N. G03828 of 27/03/2025 published in the Official Bulletin of the Lazio Region N. 26 of 01/04/2025; grant amount of EUR 45,720) is to support the participation of the company to the following international events: BioTechX Europe (Basel, Switzerland, 6-8 October 2025), Festival of Biologics (Basel, Switzerland, 30 September-2 October 2025), World Orphan Drug Congress (Amsterdam, The Netherlands, 28-29 October 2025).

Netabolics is a proud associate member of the network.

Netabolics is a research focused deep tech-based biotechnology company. Our mission is to leverage genome scale biosimulation and AI to understand disease biology and discover novel therapeutics.

COOKIE POLICY PRIVACY POLICY TERMS OF USE

Via Cristoforo Colombo 456
00145 Rome, Italy

We build virtual cell modelsfor drug discovery