Drug repurposing using the Predictive Oncology machine learning approach and proprietary biobank of frozen dissociated tumor cells (DTCs) is outlined in this new white paper.
An expedient workflow for identifying drugs that are good candidates for repurposing is demonstrated in this brand-new white paper. The Predictive Oncology machine learning approach paired with our proprietary biobank of frozen dissociated tumor cells (DTCs) offers a screening opportunity for many repurposing candidates to be assessed, with outputs from this effort reflective of both confident predictions (Machine Learning) and wet lab results.
This study was designed to evaluate a subset of drugs that were originally included in our proof-of-concept (POC), which centered in ovarian cancer. Here we describe the extension of that work across three tumor types – breast, colon, and ovary – and the addition of relevant standard of care (SOC) drugs as benchmarking compounds. Our workflow allowed for study completion in less than 12 weeks and represented experimental coverage that would have otherwise required up to 18 months of wet lab work.
By combining an expansive patient tumor sample biobank with a rich knowledge base and proprietary active learning technology, Predictive Oncology can efficiently evaluate drug efficacy and provide evidence to support drug repurposing for alternate tumor indications.
