Skip to main content
An official website of the United States government
Email

Predicting Cancer Treatment Responses with AI Tool PERCEPTION

If you’re a cancer researcher looking to build artificial intelligence (AI) models that predict cancer treatment response, there’s a new resource available! A team led by Dr. Eytan Ruppin and Dr. Alejandro Schäffer developed an AI-driven tool called PERsonalized single-Cell Expression-based Planning for Treatments in ONcology (PERCEPTION).

You can access the tool and guides for using it via GitHub.

You can use PERCEPTION to predict:

  • the success of targeted cancer drug treatments against cultured and patient-derived cell lines.
  • cancer drug treatment response in patients with either breast, myeloma, or lung cancer.
  • the development of resistance to treatment.

Although PERCEPTION studies didn’t show perfect accuracy, the findings show that the tool works better than earlier methods. Researchers also say the accuracy of the technique will improve as single-cell RNA sequencing data becomes more widely available.

< Older Post

Seeking a Better Biopsy? NCI-Funded Researchers Are Using Machine Learning to Identify Exosome Biomarkers

Newer Post >

Comment on NIH’s Draft Public Access Policy by August 19

If you would like to reproduce some or all of this content, see Reuse of NCI Information for guidance about copyright and permissions. In the case of permitted digital reproduction, please credit the National Cancer Institute as the source and link to the original NCI product using the original product's title; e.g., “Predicting Cancer Treatment Responses with AI Tool PERCEPTION was originally published by the National Cancer Institute.”

Archive

Email