Deliver Your News to the World

New Published Findings in Med Establish Efficacy of Pangea Biomed’s ENLIGHT Platform

The findings on Pangea’s ENLIGHT platform, which applies unsupervised learning techniques to transcriptomic data, are published in Med.

Patients on ENLIGHT-matched treatment courses have markedly better response rates than other patients.

By excluding non-responders, ENLIGHT can enhance clinical trial success and achieve more than 90% the response rate attainable under an optimal exclusion strategy.


Pangea Biomed today announced that new findings establishing the efficacy of its novel ENLIGHT platform have been published in Med. The study, co-led by Pangea CTO Ranit Aharonov and Eytan Ruppin, Chief of the Cancer Data Science Lab at the NCI, reveals that ENLIGHT demonstrably enhances the ability to predict therapeutic response across multiple cancer types from the bulk tumor transcriptome.

With precision oncology’s advancement into mainstream clinical practice, drug approvals for therapies aimed at specific oncogenes have surged. Since these molecularly derived therapies are matched to individual targets, patients must possess one or more biomarkers to be eligible for the drug.

“Many emerging therapeutic options are essentially going to waste since current biomarker approaches used to determine whether a patient will benefit from a therapy are excluding people who will respond positively,” said Pangea CEO Tuvik Beker. “ENLIGHT bridges this eligibility gap.”

ENLIGHT is an algorithmic platform that leverages synthetic lethality and rescue interactions to predict response to targeted therapies and immunotherapies. The approach leverages large-scale data in cancer to infer Genetic Interaction networks associated with drug targets on a whole genome scale, and then uses the activation patterns of the genes comprising these networks, as measured in the tumor, to generate a matching score for each possible treatment.

Clinically oriented prediction of patient response to targeted and immunotherapies from the tumor transcriptome” evaluated ENLIGHT’s value in two clinically-relevant scenarios: personalized oncology, matching the best treatment to a patient based on a fixed decision threshold, and clinical trial design, excluding non-responding patients in the best possible manner.

  • Personalized Oncology – Tested on 21 blinded clinical cohorts, patients with ENLIGHT-matched treatments have markedly better odds of response than the others. Overall, for nearly 700 patient cases analyzed, ENLIGHT-matched treatments had 2.6 times higher response rates than unmatched treatments. For 161 cases treated with immune checkpoint therapy, a combination of ENLIGHT and a prognostic transcriptomic marker (IFN-γ signature), achieved an odds ratio higher than 4 in predicting response to therapy.
  • Clinical Trial Design – Achieving more than 90% of the response rate attainable under an optimal exclusion strategy, ENLIGHT has the potential to enhance clinical trial success for immunotherapies and other monoclonal antibodies by accurately excluding non-responders.

ENLIGHT greatly improved upon SELECT – an algorithm previously published by the same team – and multiple other prognostic and response prediction approaches, achieving the highest response odds ratio. Moreover, where SELECT could build genetic interaction networks for 70 of 105 FDA approved targeted and immunotherapies, ENLIGHT extends to all 105 therapies tested. Although ENLIGHT is a broad pan-cancer, pan-treatment approach which does not require treatment-specific data, it performed comparably to classifiers developed using supervised learning, trained and tested on very narrow and specific tasks.

“In the real world, training sets are often small or entirely unavailable,” said Gal Dinstag, Pangea Head of Research. “ENLIGHT’s pan-cancer pan-treatment approach doesn’t require any treatment-specific training data and therefore has the potential to widely expand the patient populations for precision oncology therapies.”

ENLIGHT has already informed the life-saving treatment regimen of a young woman with a rare liver cancer.

In addition to Dinstag, Beker, Ruppin and Aharonov, the manuscript’s authors include Eldad D. Shulman, Efrat Elis, Doreen S. Ben-Zvi, Omer Tirosh, Eden Maimon, Isaac Meilijson, Emmanuel Elalouf, Boris Temkin, Philipp Vitkovsky, and Eyal Schiff of Pangea Biomed, and a lineup of collaborators from leading cancer research institutions, including the National Cancer Institute, Massachusetts General Hospital, Sheba Hospital and more. The study was supported in part by the Intramural Research Program, National Institutes of Health, and the Israeli Innovation Authority.

To learn more about Pangea’s ENLIGHT platform, please visit:

About Pangea Biomed
Founded in 2018, Pangea Biomed developed ENLIGHT – the world’s most advanced multi-cancer, multi-therapy response predictor. By combining machine learning and deep RNA analysis, the company is mapping tumor molecular signatures to dynamically and adaptively personalize cancer care for a healthier world. Pangea aims to bring effective precision oncology to cancer patients, improve oncology drug development and empower oncologists to treat patients with success. Pangea is backed by NFX, and its technology has been published in leading journals, including Cell, Med, Science Advances, Cancer Cell, Journal for ImmunoTherapy of Cancer and Nature Communications.


 Pangea Biomed
 Published Findings

This news content may be integrated into any legitimate news gathering and publishing effort. Linking is permitted.

News Release Distribution and Press Release Distribution Services Provided by WebWire.