Researchers have long known that the chemical structure of the molecules we inhale influences what we smell. But in most cases, no one can figure out exactly how. Scientists have deciphered a few specific rules that govern how the nose and brain perceive an airborne molecule based on its characteristics. It has become clear that we quickly recognize some sulfur-containing compounds as the scent of garlic, for example, and certain ammonia-derived amines as a fishy odor. It turns out that structurally unrelated molecules can have similar scents.

Standing on the outskirts of Oakland, California, Attila Toth takes in the nearby forested hills. The CEO looks out on what locals call "The Town" and, in the distance, San Francisco, or "The City." Close by, Toth sees tangles of redwood, eucalyptus and oak trees – and the wildfire risk they pose. This "wildland-urban interface" isn't far from the site of the 1991 Oakland Hills Fire, which flared up suddenly in a heavily residential area. Over four days, 3,000 thousand homes were destroyed in one of the city's wealthiest neighborhoods, causing an estimated $1.5 billion in damages ($3.2 billion in today's dollars).

Predicting how old someone is based only on how they look is incredibly hard to get right, especially in those awkward early teen years. And yet bouncers, liquor store owners, and other age-restricted goods gatekeepers make that quick estimation all the time. This story originally appeared on WIRED UK. Their predictions are often wrong. Now London-based digital identity company Yoti believes its AI-powered age estimation can predict how old someone is if they're aged anywhere from 6 to 60. For the first time, it claims, it can accurately determine whether children are under or over 13, the minimum age many social media firms require their users to be.

A University of Glasgow study developed machine learning models that could potentially identify animal viruses capable of infecting humans and classify how much of a risk they pose to humans by analyzing the genomes of viruses. The model outperformed models based on phylogenetic relatedness of specific viruses to other viruses known to infect humans according to the study, published in the peer-reviewed PLOS Biology. The model could have predicted SARS-CoV-2 as a high-risk coronavirus strain, said researchers. Analyses of the model show that there could be generalizable features of viral genomes that may make viruses preadapt to infect humans. These features are independent of the virus taxonomic relationships.

Most of the emerging infectious diseases that threaten humans – including coronaviruses – are zoonotic, meaning they originate in another animal species. And as population sizes soar and urbanisation expands, encounters with creatures harbouring potentially dangerous diseases are becoming ever more likely. Identifying these viruses early, then, is becoming vitally important. A new study out today in PLOS Biology from a team of researchers at the University of Glasgow, UK, has identified a novel way to do this kind of viral detective work, using machine learning to predict the likelihood of a virus jumping to humans. According to the researchers, a major stumbling block for understanding zoonotic disease has been that scientists tend to prioritise well-known zoonotic virus families based on their common features.

The typical ingredient-tetris bottleneck played between guest and server while dining out has amplified during COVID-19. Growth in online ordering and takeout has prompted customers with dietary needs to search online for dietary answers more than ever before.1 With over 52% of Americans following at least one diet, and less than 10% of restaurants labeling dietary information (typically not exhaustive), the information gap has never been wider. Prompted by an Ulcerative Colitis health scare for co-founder Tamir Barzilai, Honeycomb.ai is set on eliminating the frustrating process of manual menu parsing by creating a portal for anyone with dietary needs to find suitable food to eat. "After my personal diagnosis, I realized how many others struggle with finding food to eat due to a variety of reasons. The lack of ubiquitous dietary and ingredient transparency didn't make sense from both consumer and business perspectives," says Barzilai.

Viruses lead a rather repetitive existence. They enter a cell, hijack its machinery to turn it into a viral copy machine, and those copies head on to other cells armed with instructions to do the same. So it goes, over and over again. But somewhat often, amidst this repeated copy-pasting, things get mixed up. Mutations arise in the copies.

Espoo: A team of researchers have developed a machine learning model that accurately predicts how combinations of different cancer drugs kill various types of cancer cells. The new AI model was trained with a large set of data obtained from previous studies, which had investigated the association between drugs and cancer cells. 'The model learned by the machine is actually a polynomial function familiar from school mathematics, but a very complex one,' says Professor Juho Rousu from Aalto University. The study was led by researchers at Aalto University, the University of Helsinki, and the University of Turku in Finland. The research results were published in the prestigious journal Nature Communications.

The outcome of the 2020 US Presidential election is becoming less and less predictable by the day. Will a vaccine be available by November? How many people will (be able to) vote? There's not even agreement on how many swing states there are -- 6, 10, 11, perhaps 12 or more? There are many opinionated arguments to be made, but there's hardly a rigorous way to analyze how unprecedented current events will impact voting habits.

Machines have already conquered many aspects of finance, from prediction markets to high frequency trading. Could algorithms also do a better job of picking and trading volatile cryptocurrencies, the way some software already surpasses experienced stock traders? So far, experts remain skeptical. Nvidia deep learning consultant Michelle Gill told International Business Times current machine learning tools aren't a great way to predict cryptocurrency markets because this new phenomena is full of infrequent events. AI is only as good as the data sets we feed it.