Study Highlights Power of IBM Watson's AI for Genomic Sequencing

The study showed that Watson could produce actionable clinical data in 10 minutes that would ordinarily take humans 160 hours.

A new genetic sequencing study highlights IBM Watson’s potential power to enhance precision medicine.

The proof-of-concept study, which was published in the July issue of Neurology Genetics, demonstrated that Watson could analyze a tumor sample using whole genomic sequencing (WGS) and produce actionable clinical data in about 10 minutes. Comparatively, the study showed that human analysis required 160 hours to achieve similar results.

Researchers used 3 platforms to examine a tumor specimen, including a commercial targeted panel, WGS, and RNA sequencing (RNA-seq). A team of cancer oncologists and bioinformaticians scrutinized the WGS and RNA-seq data. IBM Watson Genomic Analytics (WGA) also reviewed the data from both. WGA offers an automated solution for assigning priorities to somatic variants and identifying potential therapies.

The difference between acquiring actionable data in 10 minutes versus 160 hours could mean the difference between life or death for cancer patients. This could have been the case for the study participant, the researchers noted. The study involved a glioblastoma tumor specimen from a deceased 76-year-old man. Researchers say that the participant died prior to the median survival time for his tumor type. His oncologist had recommended that he be enrolled in a clinical trial, but the 76-year-old’s condition declined, prohibiting enrollment. With more actionable clinical data available earlier in the diagnosis process, this may not have been the case.

“This highlights one of the challenges of the clinical application of precision medicine technology,” the researchers wrote. “The identification of targets and potentially useful drugs in a timely manner is only the first step. … This is critical of sequencing is to be brought out of the research out of the research arenas and into the scaled, real-world clinical realm.”

In addition to saving time, Watson was also able to identify more actionable genetic mutations than the current approach of using a targeted panel.

The research “suggests that pursuing a more extensive comparison of panel and deeper sequencing (e.g. WGS and RNA-seq) will be of interest,” the team concluded.

Watson also incorporated abstracts and full articles from PubMed to inform its analysis, according to a news release from IBM.

“This study documents the strong potential of Watson for Genomics to help clinicians scale precision oncology more broadly,” said Vanessa Michelini, Watson for Genomics Innovation Leader, IBM Watson Health. “Clinical and research leaders in cancer genomics are making tremendous progress towards bringing precision medicine to cancer patients, but genomic data interpretation is a significant obstacle, and that’s where Watson can help.”

Related

Stanford Doctors Urge Realism Toward Machine Learning

Mayo Clinic Attorney Tiptoes Through the Legal Landmines of Genomics

ResearchKit Asthma Study Highlights Pros and Cons of Mobile Research