A research article recently published in npi Precision Oncology describes how AI is able to analyze cfDNA End Motif to perform liquid biopsies, thereby distinguishing between patients who have cancer and individuals who are cancer-free. Yet, despite tremendous strides in cancer detection and treatment, there is still the urgency to create more reliable, accurate, and non-invasive as well as cost effective methods.
About Cell Free DNA (cfDNA)
cfDNa are DNA fragments that are released into body fluids including blood plasma or cerebrospinal fluid. cfDNA has been used as a biomarker when treating cardiovascular diseases, but could potentially be an indicator of certain types of cancer.
Scientists know that cells release cfDNA into the bloodstream when they die. However oncology studies examining the role cancer plays in releasing cfDNA into the bloodstream are new and require stronger evidence. Additional information provided by Inside Precision Medicine is available here.
End-Motif Inspection via transformer (EMIT)
EMIT was developed by researchers at the Tianjin Medical University. It is a deep learning model that was created by using several thousand samples taken from studies which involved cfDNA sequencing covering four types of cancer. The sequencing data covered both non-cancer patients and lung cancer. Test results demonstrated that an end motif — a short terminal nucleotide sequence of cell-free DNA (cfDNA) — can be used as a biomarker to distinguish cancerous samples from healthy samples. End motifs also contain information about the tissue of origin of the cfDNA, strong classification capabilities.
Improving Early Cancer Detection
In order to improve early detection, the four co-leaders created a deep-learning method to simplify cfDNA analysis. EMIT was developed by using information from 4,606 plasma cfDNA samples and various methods of sequencing. EMIT was applied to six datasets using various methods of sequencing. The results were deemed as excellent classification performance detecting cancer.
You can read more about this important technology over at Inside Precision Medicine.
Editor’s Note: Get Involved
Cancer doesn’t discriminate. WHATNEXT and its partners are interested in amplifying the voices of those from all identities and backgrounds. If you have a cancer journey to share, reach out here to learn more about how your voice can help spread awareness and inspire individuals from all walks of life.
AI cancer cancer research diagnosis
Last modified: August 14, 2024
