Pre-training machine learning models on molecular properties has proven effective for generating robust and generalizable representations, which is critical for advancements in drug discovery and materials science. While recent work has primarily focused on data-driven approaches, the KANO model introduces a novel paradigm by incorporating knowledge-enhanced pre-training. In this work, we expand upon KANO by integrating the large-scale ChEBI knowledge graph, which includes 2,840 functional groups -- significantly more than the original 82 used in KANO. We explore two approaches, Replace and Integrate, to incorporate this extensive knowledge into the KANO framework. Our results demonstrate that including ChEBI leads to improved performance on 9 out of 14 molecular property prediction datasets. This highlights the importance of utilizing a larger and more diverse set of functional groups to enhance molecular representations for property predictions. Code: github.com/Yasir-Ghunaim/KANO-ChEBI

Welcome to TechCrunch's 2019 Holiday Gift Guide! Need help with gift ideas? We'll be rolling out gift guides from now through the end of December, so check back regularly. We've refreshed our annual STEM toy gift guide with the latest wares clamoring to entice and inspire kids with coding tricks and electronic wizardry. But lean in to this market and you'll find a number of STEM toy makers have winked out of existence since this time last year, or else been folded into others' empires. Such as littleBits selling to Sphero this fall, or Root Robotics being picked up by robot vac giant iRobot in June.

Like so many Harry Potter fans, I've dreamed of attending Hogwarts and learning magic with a wand, cauldron and bulging bag full of quills, ink and parchment. In the absence of real witchcraft and wizardry, I've visited movie sets and played countless video games of varying quality. These spells rarely feels earned, however, because they don't require much practice or knowledge to pull off in-game. That's why I was intrigued by the Harry Potter coding kit developed by Kano. The app forces you to construct each spell with logic-based pieces before waving a plastic wand in the air.

The power and affordability of the Raspberry Pi has given rise to a new type of computer. One that goes beyond the credit-sized board, with colorful shells and displays that make it feel like a normal laptop or PC. The latest is the all-new Pi-Top, a modular laptop with a unique sliding keyboard. Pull it toward you and a large tray is revealed underneath with a Raspberry Pi 3 board and space for additional parts. The idea is to tweak and upgrade its innards for different coding projects designed by the Pi-Top team, thereby learning about code and electronics simultaneously. Pi-Top has experimented with this concept before.

We all know the importance of code. It's the backbone of computing, the internet and so much else we come into contact with on a daily basis. But learning to code is still a tricky and poorly defined pursuit. I've booted up Codecademy a few times, only to try a couple of courses and realise I have no idea what I'm doing. For people like me -- of which I suspect there are many -- what's the next step?

Schoolgirl Chloe Bridgewater melted hearts around the world when she sent a handwritten letter to Google asking for a job for when she grows up. Google CEO Sundar Pichai replied telling Chloe that he looks'forward to receiving' her job application and encouraged the young girl to follow her dreams. But now the seven-year-old has bagged her first job as a product tester for children's computing company Kano. Chloe, who lives in Hereford, was inspired to write the letter after seeing images of Google offices filled with comfy bean-bags, go-karts and slides. Now Chloe and her five-year-old sister Hollie have been asked to become product testers for Kano, a company that makes DIY computer kits for children.

The nightmare of robot babies continues apace in Japan, a rapidly aging society where human babies are going out of style. Babyloid is the latest cyber-tot to spring from the minds of engineers with little apparent regard for how scary their progeny are. Creator Masayoshi Kano of Nagoya's Chukyo University and Ifbot fame has been showing off Babyloid, developed two years ago, in presentations sponsored by the local government. He recently explained the robot in a talk at the Artificial Intelligence Research Promotion Foundation. Inspired by a baby beluga whale, Babyloid is designed to be a therapeutic robot for depressed seniors, similar to Takanori Shibata's robot seal Paro.

How you see the world may be very different than how someone else sees it. And recognizing that has long been thought to be a uniquely human ability. But when it comes to understanding others' perspectives, humans might not be alone. "Reading others' minds is not our special skill," says Fumihiro Kano, a comparative psychologist at Kyoto University in Japan. Nonhuman apes can do it, too, according to Dr. Kano's research, published Thursday in the journal Science, a finding that could further blur the line between the cognitive capacities of humans and nonhuman apes.

How you see the world may be very different than how someone else sees it. And recognizing that has long been thought to be a uniquely human ability. But when it comes to understanding others' perspectives, humans might not be alone. "Reading others' mind is not our special skill," says Fumihiro Kano, a comparative psychologist at Kyoto University in Japan. Nonhuman apes can do it, too, according to Dr. Kano's research, published Thursday in the journal Science, a finding that could further blur the line between the cognitive capacities of humans and nonhuman apes.

Learning to code isn't as easy as snapping a photo, but Alex Klein is betting that the two are more closely connected than you might think. Klein is the co-founder of Kano (the British company that developed the cleverly designed DIY computer kit that teaches kids to code), and on a recent fall day he's sitting in front of me with a transparent camera in his hand, showing me how to build my own photo filter. On his laptop, Klein drags and drops a block of code using the Kano operating system, chooses a color, and presses the camera's shutter button. He does it again, this time choosing a line of code that turns the frames into a kaleidoscopic image. "This generation is so used to communicating with photography, Klein says. "They're snapping a picture and they're using a pre-packaged alteration made by some genius at Instagram and Snapchat.