Dr. Joseph Geraci reports

NETRAMARK ANNOUNCES STRATEGIC ONCOLOGY RESEARCH COLLABORATION WITH FONDAZIONE PER LA MEDICINA PERSONALIZZATA TO ANALYZE LANDMARK ROME TRIAL DATASET

Netramark Holdings Inc. has formed a strategic research collaboration with Fondazione per la Medicina Personalizzata (FMP) to analyze its landmark ROME phase II oncology trial data set (NCT04591431) using Netramark's proprietary NetraAI platform, with the objective of identifying clinically actionable insights that may inform future precision-oncology strategies and clinical trial design.

"NetraAI was built to reveal clinically meaningful structure within complex trial data sets by identifying compact, interpretable patient subpopulations where treatment effects become detectable," said Dr. Joseph Geraci, founder, chief scientific and technology officer of Netramark. "We are pleased to collaborate with FMP on the ROME program and apply this methodology to potentially produce insights that can be communicated clearly to clinical stakeholders and those responsible for translating findings into trial design, regulatory strategy and patient care."

The ROME trial

The ROME trial, reported in Nature Medicine, is a multicentre, randomized, open-label phase 2 study comparing tailored treatment to standard of care. The study evaluated patients with advanced solid tumours progressing after one or two prior lines of therapy, guided by comprehensive genomic profiling on tissue and blood and evaluated through a molecular tumour board process.

In the intention-to-treat population (n equals 400 randomized), the trial reported improvements in overall response rate and progression-free survival for tailored treatment versus standard of care, while overall survival was similar in the context of a high crossover rate. Safety outcomes were broadly comparable between arms.

Strategic and clinical value of the collaboration

Through this collaboration, Netramark will apply its proprietary NetraAI platform to analyze the ROME dataset and other oncology data sets made available by FMP, with the goal of uncovering clinically meaningful patient subpopulations and biomarker-anchored treatment patterns. The overall goal will be to focus on identifying model-derived subgroups (MDS), which are compact, clinically interpretable patient characterizations defined by small combinations of variables that may reveal underlying disease structure and treatment-response dynamics. Analyses are expected to evaluate differential benefit between tailored treatment strategies and standard of care across key clinical endpoints including progression-free survival, overall response rate, overall survival, time to treatment failure and time to next treatment, as well as selected safety and tolerability measures where data are available.

The initial phase of the collaboration will focus on discovering and validating high-signal patient subgroups within the ROME dataset. Subsequent phases may include tumour-specific analyses, line-of-therapy evaluations and safety-profile insights across treatment modalities such as immunotherapy, targeted therapy and combination approaches, subject to data availability and joint governance decisions.

The collaboration is expected to generate long-term value by combining FMP's oncology data sets with NetraAI's advanced analytical capabilities to uncover clinically actionable insights for the ROME program. The collaboration is also expected to enable Netramark to advance and refine its platform, expand its library of transferable disease-stratification insights, and strengthen its ability to support future clinical trial design, biomarker development and responder-enrichment strategies across new sponsor engagements. This work may also inform prospective patient stratification strategies in future clinical studies.

"ROME was designed to generate high-quality evidence for genomically informed therapeutic strategies across diverse tumour types," said Prof. Paolo Marchetti, president of FMP. "We are pleased to collaborate with Netramark to evaluate how advanced, explainable analytics can help identify patient subgroups most likely to benefit from tailored approaches and support the evolution of precision-oncology decision frameworks."

"This collaboration represents an opportunity to apply NetraAI to a rigorously conducted, randomized, precision-oncology data set and to explore whether explainable, compact patient characterizations can add actionable insight beyond standard analyses," said Prof. Luca Pani, chief innovation and regulatory officer of Netramark. "The ROME trial represents a significant effort in tumour-agnostic precision oncology, and we look forward to working with FMP to deepen our shared understanding of treatment response across cancer types, while maintaining scientific rigor and clinical interpretability."

The collaboration is also expected to support Netramark's broader objective of refining and validating NetraAI using complex oncology data sets, with the aim of improving drug development outcomes through more precise patient stratification and trial design.

About NetraAI

In contrast to other artificial-intelligence-based methods, NetraAI is uniquely engineered to include focus mechanisms that separate small data sets into explainable and unexplainable subsets. Unexplainable subsets are collections of patients that can lead to suboptimal overfit models and inaccurate insights due to poor correlations with the variables involved. NetraAI uses explainable subsets to derive insights and hypotheses (including factors that influence treatment and placebo responses and adverse events), potentially increasing the likelihood of a clinical trial's success. Many other AI methods lack these focus mechanisms and assign every patient to a class, often leading to overfitting, which drowns out critical information that could have been used to improve a trial's chance of success.

About Netramark Holdings Inc.

Netramark is a company focused on being a leader in the development of generative artificial intelligence (Gen AI)/machine learning (ML) solutions targeted at the pharmaceutical industry. Its product offering uses a novel topology-based algorithm that has the ability to parse patient data sets into subsets of people that are strongly related according to several variables simultaneously. This allows Netramark to use a variety of ML methods, depending on the character and size of the data, to transform the data into powerfully intelligent data that activates traditional AI/ML methods. The result is that Netramark can work with much smaller data sets and accurately segment diseases into different types, as well as accurately classify patients for sensitivity to drugs and/or efficacy of treatment.

We seek Safe Harbor.