All Artificial Intelligence & Machine Learning articles – Page 2
-
NewsGut microbiome could hold important clues as to how IBD develops and progresses
The gut microbiome could hold important clues as to how IBD develops and progresses – and which treatment is best suited to individual patients.
-
NewsBlack box: Using AI to tackle global superbug crisis
The development of new antibiotics could be sped up thanks to a new tool that tests the reliability of AI. Researchers designed a framework to address the global threat of antimicrobial resistance, testing whether AI can provide reliable reasoning during antibiotic development.
-
NewsResearcher wins $5.6M NIH Avant Garde Award to prevent HIV, Hepatitis C and overdose
An innovative project will use AI-powered “digital twins” to help public health agencies better prevent HIV, hepatitis C and overdose among people who use drugs.
-
NewsAI reveals unexpected source of antibiotic candidates in prion proteins
Prion and prion-like proteins may hide short peptides, named “prionins,” that can kill bacteria, suggesting proteins best known for their role in neurodegeneration may contain molecular features linked to immune defense, according to new research.
-
NewsAI unlocks the secrets of viruses: Birth of large protein structures for vaccine delivery
An international research team has succeeded in designing large-scale protein structures that faithfully replicate the self-assembly principles found in naturally occurring viruses, using artificial intelligence (AI).
-
NewsMachine-learning how to overcome antibiotic-resistant gonorrhea
An AI-enabled antibiotic discovery proves effective at identifying new chemical structures and targets in the constant fight against antibiotic-resistant gonorrhea.
-
NewsYoung frogs “play it safe” when disease strikes
New research shows that young frogs prioritize growing quickly even when infected with a deadly pathogen, shifting energy toward immune defense only when infections become severe.
-
NewsGlobal map of mycorrhizal fungi reveals true scale of underground networks
Researchers have produced the first global maps visualising the distribution and mass of the Earth’s arbuscular mycorrhizal fungal networks, revealing the true scale of this underground fungal infrastructure.
-
NewsResearch forecasts global antimicrobial resistance threats for the next two decades
New research has analysed antimicrobial resistance (AMR) on a global scale to predict how resistance patterns could evolve by the year 2050, identifying around 210 resistance traits that could pose the greatest future risk.
-
NewsTesting AI against public health’s existing tools
A new study found that AI chatbots made vaccine-hesitant parents more likely to say they would vaccinate their children against HPV, but did not outperform materials from government health agencies, whose effects also lasted longer.
-
NewsTime for an AI checkup: Flaw found in machine learning for sepsis treatment
Researchers found a flaw in many peer-reviewed studies using the AI method known as reinforcement learning as a theoretical guide for the treatment of sepsis. If these flawed systems for sepsis treatment were deployed in a healthcare setting, they would recommend either overtreatment or undertreatment in nearly half of patient states.
-
NewsGladstone launches Center for PhAIge Therapy to harness AI in the fight against drug-resistant infections
Gladstone Institutes has received funding to establish the Center for PhAIge Therapy, a research center that will develop new phage-based treatments for antibiotic-resistant bacterial infections. The five-year grant makes Gladstone one of three institutions across the country selected to lead this coordinated effort.
-
NewsScientists map the ocean’s invisible workforce
A new study identifies a small set of “metabolic niches” — or functional roles — that help explain how marine microbes grow, compete for resources and recycle carbon around the globe. The microbes are incredibly diverse, but their behavior can be grouped into a manageable number of strategies.
-
NewsLong Covid burden continues to grow, doubling current surveillance estimates, multi-hospital study shows
Investigators using a novel AI algorithm to comb through medical records of patients with COVID-19 in U.S. hospitals, found around one in six developed long COVID. These rates are twofold higher than current estimates.
-
NewsScientists identify nearly two dozen antiviral compounds that could treat Ebola virus
Recent advances in artificial intelligence have enabled scientists to identify nearly two dozen antiviral compounds that could potentially treat a rare species of Ebola virus (Bundibugyo virus) currently affecting the Democratic Republic of Congo.
-
NewsInsect wing identifying app to tackle tropical disease threat
A mobile app that identifies disease-carrying insects from their wing patterns is being developed as part of a project using AI to help diagnose tropical diseases.
-
NewsSoil science: How AI could help scientists secure a vital global resource
A new paper outlines how AI tools can accelerate soil science by speeding up early-stage work, improving predictions to support decisions on land-use, carbon, and climate adaptation, handling complex data, and freeing scientists to focus on questions that require expert judgment.
-
NewsAI and supercomputer simulations reveal how a bacterial energy-converting enzyme pumps sodium ions
The Na+-NQR enzyme is vital for energy production in pathogenic bacteria, making it a highly promising target for new antibiotics. Researchers combined modified artificial intelligence techniques with extensive supercomputer simulations to visualize the hidden, dynamic movements of this enzyme during sodium transport.
-
NewsResearchers develop experimentally validated AI model to predict the virulence of tomato yellow leaf curl virus
A research team has developed DeepTYLCV, an accurate and interpretable artificial intelligence model for predicting the virulence of Tomato Yellow Leaf Curl Virus (TYLCV). DeepTYLCV uses viral genome-derived sequence information, enabling the model to identify mild and severe strains before symptom-based confirmation.
-
NewsPenn researchers create AI tool to speed antibiotic discovery
Researchers have developed a novel, AI-powered method for turning promising but imperfect antibiotic candidates into more potent ones. ApexGO starts with a small number of imperfect candidates and improves them step by step, using a predictive algorithm to evaluate each modification and guide the next.