Unigen™

A proprietary, validated AI/ML powered platform for novel target discovery and development of potential first-in-class cancer immunotherapies

Advancing immuno-oncology with an AI/ML powered platform

Immuno-oncology represents a paradigm shift in cancer treatment. Although current biological drugs can extend life expectancy for certain cancer types and patient populations, the potential of immuno-oncology remains largely untapped, with success rates of only 20-30% in specific cancer indications. We believe that the identification of novel drugs and biological pathways hold the potential to broaden the reach of cancer immunotherapies to more cancer patients

Compugen has been the at the forefront of decoding of cancer biology, revolutionizing immuno-oncology therapies with its computational discovery platform, Unigen™. This innovative platform combines proprietary AI/ML technology-agnostic cloud-based tools with vast human expertise, enabling the agile discovery of novel drug targets and the continuous development of first-in-class drugs

The Unigen™ edge

Integrating AI/ML with human expertise in a continuously enriched flexible-loop platform

Unigen™ combines Compugen’s deep scientific knowledge, AI/ML predictive algorithms and a cloud-based, technology-agnostic platform integrating a variety of biological datasets to enable discovery of novel drug targets and potential first-in-class cancer immunotherapies

AI/ML-powered process

A predictive computational platform supported by multiple AI/ML algorithms and proprietary analysis tools to enhance the entire process

Flexible-loop development

Covers the full cycle, from hypothesis generation and database creation to target discovery and clinical validation, enriching the database for new hypothesis generation

Integrative methodology

across our multidisciplinary team of experts in computational modeling, AI/ML, biology, and clinical development

A flexible-loop platform for novel IO drug target discovery & development

Validated, predictive discovery of novel immuno-oncology drug targets

Discovering drug targets demands an integrative, multi-dimensional approach that relies on a sophisticated toolkit to achieve optimal results; this, together with the scientific intricacies of biology requires us to develop a system that isn’t bound to any specific technology

Technology-agnostic approach

We generate, collect and analyze the necessary data type (i.e., multi-omics, scRNA, RNASeq, and spatial omics), augment and upload it to the cloud for automated unified curation and annotation. This enables us to create a consistent and vast database for hypothesis generation and target discovery

Vast proprietary knowledge

Unigen™ scans and labels diverse biological data across multiple tumor types to form multiple proprietary datasets, including multi-omics and spatially resolved transcriptomics modalities

Proven target validation

We conduct a swift and accurate validation process to confirm that the discovered target functions as predicted

First-in-class-drug target candidate selection

An experimental validation phase to assess the accuracy of our in-silico predictions and gain a deeper scientific understanding of the newly identified drug targets and biological pathways; this data enhances our computational platform

icon - target -Fast preclinical validation

Fast
validation

A rapid validation step is executed to ensure that the identified target is worth pursuing for first-in-class drug development

Collaborative approach

Relying on our multidisciplinary approach to optimize results

Database enrichment

based on our preclinical and clinical studies outcomes providing insights for new hypothesis generation, thus completing the loop

Biomarker driven strategy

Leveraging our newly discovered biological pathways, we identify the tumors and subtypes most likely to respond to the novel pathway modulation. Following the indication selection, we aim to identify new biomarkers to more accurately forecast patient responsiveness to our novel therapies. This long-term approach also seeks to improve the probability of success of our clinical studies

Database generation

We are collecting patient tissue samples to enhance our database with insights into tumor physiology, both pre-treatment and during treatment, aiding in future breakthroughs

AI/ML-powered biomarker discovery

Our AI/ML algorithms, supported by a robust cloud-based platform, analyze multi-omics patient data to identify novel biomarkers. This translational work validates and refines our hypothesized drug mechanisms of action

Patient selection or stratification

Our aim is to identify predictive biomarkers that inform patient selection, to enhance treatment efficacy by focusing on patients most likely to respond to our therapies