Scientists from the Cambridge Baker Systems Genomics Initiative have used machine learning to create genetic predictors of blood cell traits, such as white blood cell counts, that are linked to chronic disease. The research, published today in the journal Cell Genomics, identified shared genetic architecture between blood cell traits and various common diseases, including coronary artery disease. Senior author Professor Michael Inouye, Munz Chair of Cardiovascular Prediction and Prevention at the Baker Institute, said the findings could pave the way for novel, personalized methods to better predict, prevent and treat a variety of conditions, including heart disease, the world's biggest killer. Blood cells play essential roles in a variety of biological processes that keep our bodies working well. Blood cell traits--such as the number of cells and the proportions of different types--are among the most common tests in healthcare.

We construct risk predictors using polygenic scores (PGS) computed from common Single Nucleotide Polymorphisms (SNPs) for a number of complex disease conditions, using L1-penalized regression (also known as LASSO) on case-control data from UK Biobank. Among the disease conditions studied are Hypothyroidism, (Resistant) Hypertension, Type 1 and 2 Diabetes, Breast Cancer, Prostate Cancer, Testicular Cancer, Gallstones, Glaucoma, Gout, Atrial Fibrillation, High Cholesterol, Asthma, Basal Cell Carcinoma, Malignant Melanoma, and Heart Attack. We obtain values for the area under the receiver operating characteristic curves (AUC) in the range 0.58–0.71 Substantially higher predictor AUCs are obtained when incorporating additional variables such as age and sex. Some SNP predictors alone are sufficient to identify outliers (e.g., in the 99th percentile of polygenic score, or PGS) with 3–8 times higher risk than typical individuals.

We've all seen the stark headlines: "Being Rich and Successful Is in Your DNA" (Guardian, July 12); "A New Genetic Test Could Help Determine Children's Success" (Newsweek, July 10); "Our Fortunetelling Genes" make us (Wall Street Journal, Nov. 16); and so on. The problem is, many of these headlines are not discussing real genes at all, but a crude statistical model of them, involving dozens of unlikely assumptions. Now, slowly but surely, that whole conceptual model of the gene is being challenged. We have reached peak gene, and passed it. It is, of course, an impressive story. Today, most people know about Gregor Mendel's breeding experiments with pea plants in the 1850s.

Ready for a world in which a $50 DNA test can predict your odds of earning a PhD or forecast which toddler gets into a selective preschool? Robert Plomin, a behavioral geneticist, says that's exactly what's coming. For decades genetic researchers have sought the hereditary factors behind intelligence, with little luck. But now gene studies have finally gotten big enough--and hence powerful enough--to zero in on genetic differences linked to IQ. A year ago, no gene had ever been tied to performance on an IQ test. Since then, more than 500 have, thanks to gene studies involving more than 200,000 test takers.

Race does not stand up scientifically, period. To begin with, if race categories were meant primarily to capture differences in genetics, they are doing an abysmal job. The genetic distance between some groups within Africa is as great as the genetic distance between many "racially divergent" groups in the rest of the world. The genetic distance between East Asians and Europeans is shorter than the divergence between Hazda in north-central Tanzania to the Fulani shepherds of West Africa (who live in present-day Mali, Niger, Burkina Faso, and Guinea). Armed with this knowledge, many investigators in the biological sciences have replaced the term "race" with the term "continental ancestry." This in part reflects a rejection of "race" as a biological classification. Every so-called race has the same protein-coding genes, and there is no clear genetic dividing line that subdivides the human species.

They account for around one per cent of the population and much of their success has been put down to dedication and perseverance. But new studies are now challenging the notion that extremely intelligent children earn their achievements through hard work. Instead, they suggest that they may have a genetic advantage from birth, and that success is built on this early head-start. Johns Hopkins University in Maryland runs a talent programme for adolescents who scored in the top one per cent in maths and English. Alumni include Mark Zuckerburg (pictured).

A child's performance at school is widely considered to be a complex combination of inherited ability, the way they were brought up, the quality of teaching they received and a bit of luck. But a new study has suggested it may be possible to predict a person's academic achievement by looking at their DNA alone. Researchers have developed a new genetic scoring technique that explains almost 10 per cent of the differences between children's educational attainment by the age of 16-years-old. A DNA test could soon be used to predict how a child will do when they are at school after researchers found they can explain 10 per cent of a person's academic achievement by the age of 16-years-old by creating what is known as a polygenic score based on 74 genetic variants thought to play a role in educational performance The IQ test has long been dismissed as an inaccurate way to discern how intelligent a person really is - but now scientists may have found a better way. Researchers at the University of Warwick say MRI scans can measure human intelligence, and define exactly what it is.