New machine learning algorithm improves estimation and integration of single-cell data

Like a game of Wheel of Fortune, where you have to fill in missing letters to guess the hidden phrase, analyzing data sometimes requires estimating missing data points by relying on available information in order to get the full picture of what’s being studied.

Electronic records pin broad set of health risks on genetic premutation

It was long believed the FMR1 premutation — an excessive number of trinucleotide repeats in the FMR1 gene — had no direct effect on the people who carry it. Until recently, the only recognized effect on the carriers of the flawed gene was the risk of having offspring with fragile X syndrome, a rare but serious form of developmental disability.

Lauren Bishop-Fitzpatrick, PhD – Slide of the Week

As a large wave of individuals with autism spectrum disorder (ASD) diagnosed in the 1990s enters adulthood and middle age, knowledge about the patterning of lifetime health problems will become increasingly important for prevention efforts. We retrospectively analyzed diagnostic codes associated with de-identified electronic health records using a machine learning algorithm to characterize diagnostic patterns in decedents with ASD and matched decedent community controls.