SHEPHERD Therapeutics Presents First Public Data at 2021 ESMO Congress Highlighting Ability of DELVE Computational Approach to Optimize Therapeutic Selection for Cancer Patients

BOSTON, September 16, 2021 – SHEPHERD Therapeutics, a company dedicated to catalyzing lifesaving treatments for cancer patients, is pleased to present an e-poster of results from a computational approach to optimizing therapeutic selection for cancer patients using the Company’s proprietary precision-oncology DELVE platform, at the European Society for Medical Oncology (ESMO) Virtual Congress 2021. In this first public presentation of a DELVE analysis, DELVE was able to predict drug efficacy on cancer models and correctly select indications for existing therapies, supporting its utility in predicting new indications for cancer therapies.

While significant progress has been made in developing new therapies for cancer patients, many patients lack treatment options that result in positive outcomes, particularly for rare cancers. Existing patient-therapy matching algorithms frequently rely on mutations and well-studied targets for which only a limited number of FDA-approved therapies exist. For drug developers, point-of-care clinicians, patients and families, this gap equates to a dearth of options, or a process of trial and error informed by little data.

In contrast, DELVE uses computational and mathematical tools informed by transcriptomic data (from the complete set of RNA transcripts that are produced by the genome) to match therapies with the models, cancers, and specific patients that will be most impacted by drug treatment, regardless of mutational status. DELVE leverages bioinformatics, chemoinformatics, proprietary algorithms, deep learning neural networks, random tree forests, and other tools to generate transcriptomic-level drug response-resistance signatures. The platform integrates over 75,000 patient samples representing 161 cancers, as well as healthy tissues, and was deployed to predict drug response and resistance across thousands of in vivo, ex vivo, and in vitro cancer models.

In this analysis highlighted in ESMO presentation 1146P, “Closing the target gap: A computational approach to optimizing therapeutic selection for cancer patients,” DELVE was able to correctly classify the highest and lowest responding drug-cell line pairs with 96% sensitivity [95% CI +/- 0.95%] and 88% specificity [95% CI +/- 1.0%]. Across published in vivo studies related to 20 FDA-approved cancer therapies, drug-model pairs that achieved a high DELVE score showed greater than or equal to 90% tumor growth inhibition in vivo 78% of the time. Drug-model pairs with low DELVE scores showed less than or equal to 60% tumor growth inhibition in vivo 77% of the time. Across 71 FDA-approved drugs, using chemical structure alone, the platform was able to predict at least one approved solid tumor indication 84% of the time. Random chance indication-therapy pairing was correct only 21% of the time. Across 10 failed therapies, the platform was able to predict failure with 82% accuracy.

“DELVE integrates novel computational tools that allow us to conduct analyses that were previously impossible with existing state of art. GCVA, one of DELVE’s core novel tools, utilizes tumor and cancer model data, which can be obtained from an individual patient or group of patients at the point of care,” said Mikhail Grushko, first author and lead DELVE algorithm developer. “The high accuracy obtained from proof-of-concept studies is indicative of the potential of DELVE to advance computational methods into established clinical trial methods and treatment protocols.”

“This analysis is the result of five years of work mapping the cancer landscape, aggregating and cleaning data, and building a completely novel computational tool,” said Katherine Arline, Chief Strategy Officer at SHEPHERD Therapeutics and DELVE architect. “Our mission has always been to bring effective therapies to the patients who need them most, and we believe DELVE reflects a massive step toward realizing the promise of truly personalized medicine. We are excited to share these outcomes with doctors and drug developers who can leverage our work to make better-informed decisions.” 

About SHEPHERD Therapeutics

SHEPHERD is committed to ensuring that no patient is left to die due to lack of access to adequate treatment options – and that every therapy finds every patient it can help. Using our precision-oncology platform, DELVE, we move beyond a single-target-based approach to drug development and instead identify the complex and interconnected mechanisms responsible for drug response and resistance revealed in the human transcriptome. DELVE can guide decision-making around the utility of new and existing therapies across dozens of forms of cancer, identify promising potential treatments for specific cancers, and help guide the clinical use of therapies for specific patients. Visit to learn more and join the fight.

Back to news