A new deep learning-based inverse design method allows for the optimization of complex acoustic metamaterials, reducing noise pollution while maintaining ventilation. The approach enables ultra-broadband sound attenuation across various peak frequencies.
Researchers, including Assistant Professor James Lewis, are studying the evolution of butterfly wing color patterns as a model for understanding population adaptation to environmental changes. The study aims to understand why some Heliconiine butterflies lose their mimicry phenotype and how this affects their survival.
A new study by a global consortium provides insight into how tumors evolve, shedding light on the intricate processes underlying cancer evolution. The findings define optimal algorithms to analyze tumor evolution, enhancing diagnostic accuracy and treatment planning.
A new study found that higher lifestyle scores associated with better heart health can lead to a younger biological age and lower risk of heart disease and stroke. The study used DNA methylation levels as a biomarker to estimate biological age.
A new AI algorithm developed by Penn State researchers may lead to better predictions and novel therapies for autoimmune diseases. The algorithm analyzes genetic code to identify additional genes of risk and outperforms existing methodologies, identifying 26% more novel gene and trait associations.
Climate change threatens freshwater habitats, disrupting microbial communities essential for nutrient cycling and water quality maintenance. Many abundant freshwater bacteria with small genomes experience extended periods of adaptive standstill, limiting their ability to adapt to changing environmental conditions.
Researchers at EPFL have developed a genetic learning algorithm to identify optimal pitch profiles for VAWT blades, increasing turbine efficiency by 200% and reducing vibrations by 77%. This innovation addresses the engineering problem of air flow control and has the potential to bring efficient VAWT technology to maturity.
Researchers reconstructed the entire evolutionary history of birds using advanced algorithms and genomic data from over 60,000 regions. The new family tree reveals patterns in avian diversification following the mass extinction event that wiped out dinosaurs.
Researchers developed a single-assay approach using exome sequencing data to detect large-scale pathogenic mutations, detecting 91 previously undetectable mutations. This shift could enable earlier diagnoses and save the NHS vital resources.
Researchers developed an AI framework that combines dimension reduction techniques with a new clustering algorithm to quickly identify groups of viral genomes at risk. This enables proactive response measures like tailored vaccine development, potentially eliminating emerging variants before they spread.
Researchers identified a mechanism of 'copy-paste' genetics in Plasmodium falciparum that increases genetic diversity of surface proteins, potentially evading the human immune system. This discovery offers valuable insights for vaccine design and could help inform new approaches to preventing malaria.
A new study found that many professional medical societies are taking steps to eliminate the use of harmful race-based algorithms that misuse race as a proxy for biology. This shift aims to address racial health inequities by implementing anti-racist algorithms and reparative approaches.
Researchers at Johns Hopkins Kimmel Cancer Center and University School of Medicine developed an algorithm, REAL-FAST, to identify high-risk precancerous lesions on the fallopian tubes. The test accurately detected cancer 95.8% of the time and correctly ruled out cancer 97.1% of the time.
Scientists explored desiccation tolerance in mosses, tracing 450 million years of plant evolution. They found closely related species use similar pathways to coordinate dehydration but differ in rehydration management.
A new study has identified a genetic marker that can predict which patients are likely to respond to immunotherapy in various types of cancer. Tumors with high intragenic rearrangement (IGR) burden, which indicates cryptic structural rearrangements of the genetic code, may respond better to immunotherapy.
Researchers discovered 50 genetic changes underlying the switch from egg-laying to live-bearing in marine snails, which evolved within the past 100,000 years. The findings provide insights into the evolutionary process and potential benefits of live-bearing, including increased reproductive success in new habitats.
A team of researchers successfully synthesized a 1.5-million-year-old antibiotic called paleomycin, which displays potent properties against human pathogens. By tracing the evolutionary path of glycopeptide antibiotics, the team gained insights into the development of new drugs and uncovered a common precursor molecule.
A Lancaster University academic argues that AI and algorithms contribute to polarization, radicalism, and political violence, posing a threat to national security. The paper examines how AI has been securitized throughout its history, highlighting the need for better understanding and management of its risks.
Researchers have identified a group of babies born to mothers who used fentanyl during pregnancy with similar facial and musculoskeletal abnormalities. The study suggests the emergence of a novel syndrome, which may be caused by fentanyl exposure or another contaminant.
Researchers have developed STARVar, an artificial intelligence-powered method that leverages diverse data sources to identify genetic variants associated with diseases. The tool prioritizes genomic variants based on real-world patient symptoms, providing a more nuanced understanding of clinical presentations.
Osaka University researchers have developed an AI-driven algorithm to control indoor heating and cooling systems, achieving significant energy savings of up to 30%. The system learns the symbolic relationships between variables, including power consumption, based on a large dataset, ensuring comfortable temperatures despite winter cond...
A team of researchers at Northwestern University developed an AI capable of intelligently designing robots from scratch, compressing evolution into lightning speed. The AI designed a successfully walking robot in mere seconds, with a novel structure and three legs, fins along its back, and a flat face.
A new AI method leverages causal relationships in genome regulation to efficiently identify optimal genetic perturbations for cellular reprogramming. The technique reduces experimental costs by prioritizing the most informative interventions, leading to faster convergence and more effective results.
A new algorithm developed by Johns Hopkins researchers can assess genetic risks for major diseases across diverse ancestry populations. The CT-SLEB method uses machine learning and Bayesian statistical modeling to generate genetic scores for 13 traits in five different ancestry categories.
A new computational approach removes movement in heart cell and tissue images, allowing direct monitoring of electro-mechanical coupling. The algorithm mimics a drug's action, giving insight into heart diseases.
A groundbreaking analysis of historical DNA links tens of thousands of living individuals to enslaved and free African Americans at Catoctin Furnace. The study provides a new way to complement genealogical efforts and restore ancestral histories for African American communities.
A study reveals that specific bacteria drive the evolution of antimicrobial peptides in Drosophila, providing insights into how host immune systems adapt to new ecological niches. The findings also suggest a new model for AMP-microbiome evolution.
A study by Kyoto University found that Daphnia's phenotypic plasticity is strongly related to its body size and the type of predator. Medium-sized Daphnia are more vulnerable to predation by both Chaoborus larvae and fish, which prefer larger prey.
A new study from Aarhus University has found that applying AI predictions of protein structures enhances the CRISPR technology, making the cuts in a patient's DNA more precise. This discovery may lead to better treatments for patients with genetic disorders and potentially develop cures for various genetic diseases.
Two closely related butterfly species have evolved distinct adaptations to cope with changing seasons. The small white butterfly is a 'summer specialist,' reproducing well but struggling in winter, while the green-veined white butterfly is a 'winter specialist,' thriving in cold conditions.
Researchers developed a method using artificial intelligence to track changes in brain synapses, enabling better understanding of how connections change with learning, aging, injury and disease. Machine learning was leveraged to enhance image quality, allowing for detection and tracking of individual synapses.
Researchers used machine learning to identify 'synthetic extreme' DNA sequences that are active in humans but not fruit flies. These rare sequences have potential practical applications in biotechnology and biomedical research.
A recent study published in Nature challenges traditional views on human origins in Africa, proposing that modern humans emerged from the interaction of multiple populations across the continent. By analyzing genomic data from diverse African groups, researchers found evidence of gene flow and mixing over hundreds of thousands of years.
Researchers have developed a new method called EvoAug that uses artificial DNA sequences inspired by evolution to train deep neural networks for genome analysis. This approach enables the model to recognize regulatory motifs more accurately, leading to better performance and potential breakthroughs in understanding human health.
A new AI tool, CLEAN, can predict enzyme functions based on amino acid sequences, outperforming leading state-of-the-art tools in accuracy and reliability. The tool was developed using contrastive learning and verified experimentally with both computational and in vitro experiments.
A team of researchers used a genetic algorithm to discover an organic catalyst for the Morita–Baylis–Hillman reaction, which outperformed traditional catalysts. The computational method suggested new molecular structures that were not present in the initial population, leading to a novel discovery.
SourceWiley·JournalAngewandte Chemie International Edition·TypeExperimental study·DateMar 23, 2023
A novel deep learning-based forecasting model predicts uncertain parameters related to renewable energy sources, their energy demand, and market prices. The model demonstrates improved prediction accuracy and efficiency compared to existing methods.
Researchers found no relationship between growth rate and body size in theropod dinosaurs, with some giants growing slowly and smaller ones rapidly. This study opens the door to future investigations into how animals regulate their growth.
Scientists have created a novel approach to produce phase-pure quasi-2D Ruddlesden–Popper perovskites, enabling highly efficient and spectrally stable deep-blue-emissive perovskite LEDs. The rapid crystallization method yields high-performance devices with an emission wavelength centered at 437 nm.
A team of researchers from the University of Pennsylvania has developed a new algorithm, metadynamics, that can navigate high-dimensional energy landscapes to find low-energy configurations. This breakthrough has the potential to revolutionize fields such as protein folding and machine learning.
A new AI evaluation framework, GOPHER, has been developed to assess the efficiency of genome analysis algorithms. The tool judges programs on their ability to learn genomic biology, predict patterns, handle noise, and provide interpretable decisions.
A new Northwestern Medicine study identifies common and rare gene mutations that impact radiation resistance and sensitivity. This information will allow clinicians to better calibrate radiation doses based on genetic mutations, improving treatment efficacy while reducing toxicity.
Researchers at Drexel University have developed a computer model that uses machine learning algorithms to analyze the genetic sequence of the COVID-19 virus and predict the severity of new variants. The model provides an early warning system for public health officials, allowing them to prepare accordingly.
Researchers propose a surrogate-assisted evolutionary algorithm with restart strategy to optimize electronic component layout in space engineering. The algorithm reduces the cost of thermodynamic simulations, improving convergence speed and solution quality.
A new algorithm can analyze thousands of genomic variants to estimate a person's risk of developing chronic kidney disease, with the highest scores indicating tripled risk compared to the general population. Early detection may prevent many cases of kidney failure and reduce the need for transplant or dialysis.
Researchers developed an AI system using swarm learning to predict cancer from medical images of tissue samples without accessing patient data. The technique improved the detection of genetic changes in colon tumors with high accuracy.
Researchers created a comprehensive genomic regulatory map of a 24-hour-old zebrafish embryo, identifying millions of regulatory segments that control gene transcription. The study used single-cell technologies and machine learning algorithms to analyze genome data from over 23,000 nuclei.
The Nutrition for Precision Health study will use data from 10,000 participants to develop algorithms predicting individual responses to food and dietary routines. The goal is to create more personalized nutrition recommendations and reduce health disparities.
Researchers at Brigham and Women's Hospital conducted a scoping review of 78 articles to identify key use cases for AI in preventing or mitigating adverse drug events (ADEs). Genetic information is thought to be critical in improving AI algorithm performance, but systematic evaluations are necessary to generate evidence for this field.
Researchers at the University of Bern have developed an approach called 'evolving-to-learn' (E2L) that enables computers to discover mechanisms of synaptic plasticity, leading to improved learning capabilities. The algorithm was tested in three scenarios and successfully solved new tasks by mimicking biological evolution.
A new computer program called Codetta can analyze the genome sequences of over 250,000 bacteria and archaea to identify alternative genetic codes. This could help scientists understand how genetic codes evolve and change.
A new study tracked the spread of a genetic mutation that causes young-onset heart arrhythmia across continents over centuries. The research found that the mutation was passed down from Northern Europe to other parts of the world through migration, and identified a specific gene, KCNQ1, as the cause of the disease.
Researchers identified 23 genes contributing to congenital heart disease, including 12 previously unknown, using a new algorithm called M-DATA. This method combines genetic data from people with related conditions, increasing the power to identify risk factors and potentially leading to improved treatments.
SourcePLOS·JournalPLOS Genetics·TypeComputational simulation/modeling·DateNov 4, 2021
Researchers used machine learning and genomics to identify molecular markers of resistance to sugarcane yellow leaf disease in over 97 sugarcane genotypes. The study found that energy cane varieties with higher fiber content are more resistant to the disease, paving the way for commercial launches.
The AI optimization improves the motor's power factor, reducing disruptions to the power grid. The optimized motor shows excellent performance, with improved efficiency and increased torque while drawing less current.
A new AI-powered algorithm, GEM, has been developed to quickly identify genetic causes of serious disease in newborns. The technology leverages machine learning and natural language processing to analyze vast amounts of genomic data and clinical records, achieving an accuracy rate of 92% compared to existing tools.
Researchers developed VarSAn, a computational tool that analyzes SNPs to predict disease pathways, including breast and prostate cancer. The tool uses network analysis to identify perturbed pathways, offering a new approach to understanding genetic variation.
A team of Harvard researchers created an integrated pipeline, STAMPScreen, to help genetic engineers identify target genes and perform screening studies. The protocol combines computational tools with lab experiments to quickly and efficiently test gene function in living cells.
Researchers developed a new framework using machine learning that improves the accuracy of interatomic potentials for designing new nanomaterials. The findings suggest a positive correlation between the complexity and number of parameters and the accuracy of interatomic potential.
Yaochu Jin will lead a new working group on Nature-Inspired Computing and Engineering at Bielefeld University's Faculty of Technology. His research focuses on evolutionary algorithms for multi-objective optimization, applicable to various fields like robotics, medicine, and machine learning.