🦞🌯 Lobster Roll

Researchers have developed a protein design software using reinforcement learning, demonstrating its ability to create useful molecules with potential applications in developing potent vaccines and other therapies. This breakthrough could lead to a new era in protein design, with implications in can...

Stanford machine learning algorithm predicts biological structures more accurately than ever before. Stanford researchers develop machine learning methods that accurately predict the 3D shapes of drug targets and other important biological molecules, even when only limited data is available. Determi...

A study from UC Berkeley shows that machine learning outperforms traditional methods in modeling the secreted proteins of the fungal pathogen M. oryzae. The research reveals structural similarities among effectors, offering new insights into pathogen evolution. Recently published work by scientists ...

Previous studies of a genetic on/off switch may have been confounded by contamination, but Mount Sinai scientists have created a new tool for accurately determining whether it plays a role in human disease. A tiny team of cutting-edge medical experts has been examining a biochemical, DNA tagging mec...

Machine learning tool estimates extinction risk for species previously unprioritized for conservation. Species at risk of extinction are identified in the iconic Red List of Threatened Species, published by the International Union for Conservation of Nature (IUCN). A new study presents a novel machi...

Research found that children learn faster than adults due to increased GABA levels during training, which helps stabilize new learning. If you’ve ever thought your children in elementary school were “smarter” than you, or at least quicker at taking up new skills and knowledge, new ...

Study at the University of Bonn elucidates previously unknown mechanism for spatial learning. There are two fundamentally different cell types in the brain, neurons, and glial cells. One purpose of the latter is to insulate the “wiring” of nerve cells or guarantee optimal working conditi...

Researchers at Carnegie Mellon University have developed SPICEMIX, a machine learning tool that enhances spatial transcriptomics research by identifying complex gene expression patterns in tissues. This innovation offers improved insights into cell types and biological processes, especially in brain...

A machine learning approach can predict bacteria’s pH preferences from their genomes. This breakthrough could enhance ecological restoration, agriculture, and the development of probiotics, as well as expedite the process of bacterial culturing. Researchers have figured out a way to predict ba...

Neuroscientists at the University of Pittsburgh have created a machine learning model to understand how brains recognize communication sounds. The model, tested on guinea pigs, accurately predicted brain activity in response to different sound categories. The research also revealed that guinea pigs ...

NIH-funded study shows preliminary results that could lead to new pain treatments. In a pioneering study, scientists have used machine learning tools to record and analyze brain data from chronic pain patients, identifying a specific brain region and biomarkers linked to chronic pain. The research, ...

The act of pretending to be an art thief supercharges people’s memory of paintings, thanks to their heightened curiosity. Adopting a curious mindset over a high-pressure one can enhance memory, according to recent research from Duke University. The study showed that participants who envisioned...

The Findings Could Explain How Memories Form Throughout the Day Scientists have long believed that rewards such as food or money stimulate learning by triggering the release of dopamine, a hormone associated with pleasure and positive reinforcement. However, a recent rodent study suggests that learn...

Jellyfish Learning Abilities: Challenging Neuroscientific Notions Even without a central brain, jellyfish can learn from past experiences like humans, mice, and flies, scientists report for the first time on September 22 in the journal Current Biology. They trained Caribbean box jellyfish (Tripedali...

Two MIT studies find “self-supervised learning” models, which learn about their environment from unlabeled data, can show activity patterns similar to those of the mammalian brain. To make our way through the world, our brain must develop an intuitive understanding of the physical world around us, w...

Brainless brittle stars are capable of learning through experience, as demonstrated in new research. They exhibit classical conditioning by associating darkness with feeding, a significant discovery in understanding learning processes in brainless marine creatures. We humans are fixated on big brain...

Identifying and characterizing repeated DNA sequences, sometimes called “junk DNA” or “dark matter” within chromosomes, which may play a role in cancer or other diseases, has proven to be difficult. Now, investigators at the Johns Hopkins Kimmel Cancer Center have developed a...

A new MIT-developed method combines Raman spectroscopy with machine learning to noninvasively track gene expression in cells over time. This technique enables detailed study of cellular differentiation and has potential applications in cancer research, developmental biology, and diagnostics. Sequenc...

A gene previously associated with intellectual disability has been discovered to control learning and memory in mice. The gene, called KDM5B has previously been linked to some intellectual disability disorders and autism. In the general population, some variants are also associated with reduced brai...

The AnoxyGen project, led by Christian Hertweck and funded by the ERC Advanced Grant, explores the potential of anaerobic bacteria in biotechnology, medicine, and ecology, aiming to discover new bioactive compounds. The earth was populated with numerous organisms long before photosynthesis brought f...

  Researchers used AI model ESM3 to simulate 500 million years of evolution and create a novel fluorescent protein, revolutionizing protein engineering. Using a multimodal generative language model called ESM3, Thomas Hayes and colleagues designed and synthesized a novel bright fluorescent prot...

For Gabrielle Finear, a senior studying computer science, working on two startup ideas in MIT Sandbox provided hands-on learning to complement her coursework. As senior Gabrielle Finear was pursuing a major in computer science, economics, and data science, she wanted to find a way to apply what she ...

In a discovery that challenges long-held dogma in biology, researchers show that mammalian cells can convert RNA sequences back into DNA, a feat more common in viruses than eukaryotic cells. Cells contain machinery that duplicates DNA into a new set that goes into a newly formed cell. That same clas...

Intestinal microbes like Bifidobacteria could be key allies in the fight against COVID-19. Researchers from Yonsei University in South Korea have found that certain commensal bacteria that reside in the human intestine produce compounds that inhibit SARS-CoV-2. The research will be presented on June...

The venom of a caterpillar, native to South East Queensland, shows promise for use in medicines and pest control, Institute for Molecular Bioscience researchers say. The Doratifera vulnerans is common to large parts of Queensland’s south-east and is routinely found in Toohey Forest Park on Brisbane’...

PhD student Sarah Nyquist applies computational methods to understudied areas of reproductive health, such as the cellular composition of breast milk. Sarah Nyquist got her first introduction to biology during high school, when she took an online MIT course taught by genomics pioneer Eric Lander. In...

New AI-powered imaging has exposed how cells use energy during movement and revealed a hidden glucose receptor, offering potential breakthroughs in treating cancer and vascular disease. Understanding cellular metabolism – how a cell uses energy – could be key to treating a wide array of diseases, in...

Reevaluating Handwriting in a Digital World Though writing by hand is increasingly being eclipsed by the ease of computers, a new study finds we shouldn’t be so quick to throw away the pencils and paper: handwriting helps people learn certain skills surprisingly faster and significantly better...