Platform

Pangea is enabling a deeper understanding of how a tumor would respond to therapy. ENLIGHT looks beyond actionable genomic abnormalities by examining the molecular context in which targeted therapies operate. It does so by considering expression abnormalities, which are orders of magnitude more common than actionable mutations - the current staple of precision oncology. The ENLIGHT platform uncovers several types of functional genetic interactions, building “gene social networks” that reveal tumor vulnerabilities. Our analysis uses multiple measures of activity, including expression, epigenetics, proteomics, and more. Combining these with the tumor vulnerability maps, ENLIGHT uncovers many more clinically relevant insights than approaches based solely on genomic alterations.


Biotech/pharma companies and research groups are already using the platform’s broad applicability to open up multiple new opportunities in drug development and treatment nomination. The platform’s accuracy and efficacy have been demonstrated by published evidence and proven successful for patients who would otherwise not qualify for precision cancer care.

ENLIGHT consists of two main modules:

The Inference Engine

This engine processes multiple big-data repositories in order to infer which gene pairs are likely to be related by certain functional relationships, termed Genetic Interactions (GI). Each gene pair is assigned an “Interaction Score” which ranks how likely it is to represent a clinically-relevant GI.

The output of the Inference Engine is a set of GI Maps, showing genes connected by high-scoring GIs. These maps are generated both on a pan-cancer level and for specific cancer indications.

The Predictive Engine

This engine combines the GI Maps produced by the Inference Engine with information on drugs, biological pathways, and patient-specific multi-omics data, in order to derive personalized predictions of response to cancer. Based on these predictions, ENLIGHT screens and ranks dozens of potential treatments for each patient, complementing standard genomic matching biomarkers.

ENLIGHT enables:

  • Actionable treatment nomination for most patients
  • Identification of novel drug targets
  • Identification of drug combinations that optimize clinical outcome
  • Improved biomarkers for drug trials
  • Drug indication expansion
enables
mail

We are always open for collaboration

contact us for collaboration opportunities arrow
arrow

Publications

Our publications reflect the latest developments and findings at the intersection of precision oncology and artificial intelligence, as well as our commitment to promoting research for the benefit of those battling cancer.
rer
November 2022

Clinically oriented prediction of patient response to targeted and immunotherapies from the tumor transcriptome (in press)

This work presents Pangea’s proprietary ENLIGHT platform, a GI-based algorithm that extends and improves upon SELECT. ENLIGHT was developed by Pangea for prediction of patient response to targeted therapies and ICB in multiple scenarios. The manuscript presents a comprehensive retrospective validation for ENLIGHT’s applicability to precision oncology and clinical trial design.

Read More arrow arrow
rer
June 2022

Synthetic lethality-based prediction of cancer treatment response from histopathology images

With this work, we demonstrate for the first time the ability to leverage common histopathology images for accurate transcriptome-based prediction of response to precision oncology treatments, bypassing the need for lengthy and costly NGS. The ENLIGHT-DeepPT technology (ENLIGHT-DP for short) can have far-reaching implications, as it can make precision profiling and treatment-matching feasible in situations where NGS is not – for lack of resources, time, or sufficient biopsy material. Furthermore, it can serve as a very fast and inexpensive screening test, to determine which patients should be referred for more accurate comprehensive molecular profiling.

Read More arrow arrow
rer
April 2021

Synthetic lethality-mediated precision oncology via the tumor transcriptome

This work presents SELECT, a GI-based approach for response prediction in the oncology realm. This work extends upon ISLE with an emphasis on a more comprehensive retrospective validation on targeted therapies and immunotherapies

Read More arrow arrow
rer
August 2020

Synthetic lethal combination targeting BET uncovered intrinsic susceptibility of TNBC to ferroptosis

This work uses the SELECT pipeline to identify multiple potential therapy combinations for a variety of Triple Negative Breast Cancer (TNBC) sub-types. In particular, two powerful combinations targeting the BET complex and two synthetic-lethal targets of it were identified and validated.

Read More arrow arrow
rer
November 2019

Translational reprogramming marks adaptation to asparagine restriction in cancer

Another demonstration of the utility of the approach for drug target identification. In this case in Pancreatic Cancer and Melanoma.

Read More arrow arrow
rer
September 2019

A Platform of Synthetic Lethal Gene Interaction Networks Reveals that the GNAQ Uveal Melanoma Oncogene Controls the Hippo Pathway through FAK

This work demonstrates the applicability of the SELECT GI-based approach to drug development. Specifically, a novel target for Uveal Melanoma was discovered here for the first time based on a computational analysis done by SELECT and was validated prospectively in in-vitro and in-vivo models. This target is currently being validated in a clinical trial.

Read More arrow arrow
rer
September 2019

Genome-wide prediction of synthetic rescue mediators of resistance to targeted and immunotherapy

This work presents INCISOR, an algorithm for inferring Synthetic Rescuer genes, and using them to predict resistance to targeted and immunotherapies.

Read More arrow arrow
rer
July 2019

Beyond Synthetic Lethality: Charting the Landscape of Pairwise Gene Expression States Associated with Survival in Cancer

Generalization of Synthetic Lethality to a notion of gene-pair expression states which correlate with survival.

Read More arrow arrow
rer
June 2018

Harnessing synthetic lethality to predict the response to cancer treatment

This work presents ISLE, the first algorithm for the identification of clinically relevant GI networks developed in Ruppin’s lab. The work presents some validations on in-vitro, in-vivo and patient data.

Read More arrow arrow
rer
August 2014

Predicting Cancer-Specific Vulnerability via Data-Driven Detection of Synthetic Lethality

This work presents DAISY, the first algorithm for SL and SDL interaction identification by the Ruppin lab. Relayed heavily on in-vitro data. DAISY became the main information source of SynLethDB – the largest database of experimentally and computationally-derived synthetic lethal interactions at that time.

Read More arrow arrow