The CDC says right now, there is no routine screening or early diagnostic test for ovarian cancer. But that’s something that researchers like Jeffrey Skolnick and John McDonald at Georgia Tech's School of Biological Sciences are hoping to change. The researchers are developing a new test they say detects ovarian cancer with a 93% success rate. Skolnick explained that after patients give a blood sample, artificial intelligence scans the metabolic profile to determine the probability that someone does or does not have cancer. (The study was also covered at Diagnostics World and Clinical Research News.)

Atlanta News First

A major bottleneck in early detection is the molecular heterogeneity between ovarian cancer (OC) patients, which limits the likelihood of identifying individual biomarkers that are shared among patients. In a new study “A personalized probabilistic approach to ovarian cancer diagnostics,” published in Gynecologic Oncology, researchers from Georgia Tech have addressed this challenge by applying machine learning (ML) on patient metabolic profiles to identify biomarker patterns for personalized OC diagnosis. The Georgia Tech researchers include John McDonald, Professor Emeritus, School of Biological Sciences; Dongjo Ban, a Bioinformatics Ph.D. student in McDonald’s lab; Research Scientists Stephen N. Housley, Lilya V. Matyunina, and L.DeEtte (Walker) McDonald; and Regents’ Professor Jeffrey Skolnick, who also serves as Mary and Maisie Gibson Chair in the School of Biological Sciences and Georgia Research Alliance Eminent Scholar in Computational Systems Biology. (The study was also covered at The New York Post, Technology Networks, Medical Xpress, News-Medical.net, Medscape and Diagnostics World.)

Inside Precision Medicine

Coral reefs play a crucial role in the region’s biodiversity, food security, employment, tourism, and medical research, but many reefs are suffering degradation due to pollution, ocean warming and overfishing. Growing sea cucumbers in underwater nurseries could be a way of restoring their services as “vacuum cleaners” of the ocean to protect the Asia-Pacific’s declining coral reefs, Biological Sciences Researchers Mark Hay and Cody Clements suggest in their recently released study. (This was also covered at New Atlas, Gizmodo Japan and The Good Men Project.)

SciDev.Net

A surge in tools that generate text is allowing research papers to be summarized for a broad audience, and in any language. But some scientists feel that improvements are needed before we can rely on AI to describe studies accurately. Will Ratcliff, an associate professor at the School of Biological Sciences, argues that no tool can produce better text than can professional writers. Although researchers have different writing abilities, he invariably prefers reading scientific material produced by study authors over those generated by AI. “I like to see what the authors wrote. They put craft into it, and I find their abstract to be more informative,” he says.

Nature Index

Recent studies show nearly half of the world’s species are on the move because of the changing climate and habitat disruption. Apart from slowing fossil fuel production and prioritizing carbon storage, a direct solution for species inching north as temperatures rise is improving climate connectivity, a term likely coined by researchers from the Georgia Institute of Technology in a 2016 study. The idea builds on the established science of wildlife corridors and land conservation that supports the migration of animals. School of Earth and Atmospheric Sciences Assistant Professor Jenny McGuire, who worked on the study, said this kind of movement differs from traditional migration patterns. Instead of departing annually and returning, species are permanently moving to areas they’re finding more hospitable. “They’re moving in such a way that they’re tracking the climates they’re suited to live in or able to live in, and then staying in those places,” McGuire said.

Adirondack Explorer