Articles tagged with Gene Prediction
A new clinical trial will investigate whether adding the oral medication vorasidenib to standard chemotherapy improves progression-free survival for people with newly-diagnosed, grade 3 IDH-mutant astrocytoma. The study aims to recruit 400 individuals with this type of brain cancer and evaluate the safety and side-effect profile of the...
Researchers have created a comprehensive map of the DNA sequences that control gene expression in human cells, identifying 2.37 million potential regulatory elements. This registry reveals previously unrecognized classes of elements and illuminates how noncoding genetic variation contributes to cell type-specific traits.
Researchers used genetic data from house sparrows to develop a statistical model that can predict traits in other species. The study found that making predictions across different populations works less well than within populations, but provided new insights for improving the technique.
Researchers developed a new suite of statistical methods to pinpoint DNA changes responsible for important traits in livestock. The work addresses challenges in fine-mapping, especially in populations with closely related animals, and introduces tools that incorporate 'relatedness-adjusted' genomic correlations.
A study compares five DNA foundation language models across 57 diverse datasets to identify their strengths and weaknesses in predicting gene expression, identifying genomic components, and detecting harmful mutations. The findings highlight the importance of selecting appropriate models based on specific genomic tasks.
A new resource identifies genetic variants associated with elevated 'bad' cholesterol, a major contributor to heart disease. Clinicians can now predict patient risk for heart attacks and strokes, allowing for prevention and early treatment.
The Global Pathogen Analysis Platform (GPAP) will enable low- and middle-income countries to conduct research and surveillance of infectious diseases independently. The platform aims to prevent disease outbreaks from developing into pandemics by detecting genetic sequences of potential pathogens.
Researchers developed a strategy to predict multiple traits at once based on the whole genome, increasing predictive ability by 2-10 times. This method, called multi-trait genomic selection (MT-GS), combines genetic markers with known trait links for more accurate predictions, making it a promising tool for efficient and cost-effective...
A large Danish study shows that children with a high genetic risk for ADHD are more likely to experience severe neglect and childhood maltreatment. This risk is also influenced by parental mental illness, with girls generally exposed to more maltreatment than boys.
A study found that genetic predisposition to higher muscle strength is associated with lower all-cause and cardiovascular mortality in aging men. The association remained significant even after adjusting for lifestyle factors such as smoking and body mass index.
Researchers discovered a 'brinkmanship' game between rival genes in mammals that could explain why many fertilized eggs don't result in a new life. The study found that the stakes are raised, resulting in either the boldest gene triumphant or mutual self-destruction.
Mass General Brigham researchers developed a machine learning algorithm, PAMmla, to predict properties of genome editing enzymes. The approach helps reduce off-target effects and improves editing safety and efficiency, enabling customized enzymes for new therapeutic targets.
A study by Baylor College of Medicine researchers identifies 123 genes associated with increased AD risk in humans, including MTCH2, which shows promise as a potential therapeutic target. The team also found that reversing the alterations in these genes has a neuroprotective effect in living organisms.
A new machine learning model accurately predicts the fitness of AAV capsids based on their amino acid sequence, enabling more efficient and cost-effective gene therapies. The model's robustness and generalizability have been demonstrated through tests on independent datasets, offering a promising tool for capsid engineering.
A novel approach combines large language models and quantum computing to predict Salmonella antimicrobial resistance. The SARPLLM algorithm outperforms other models in prediction accuracy.
Researchers at the University of Maryland discovered a way to predict treatment success for cutaneous leishmaniasis, a devastating skin infection. By analyzing a patient's immune system, they identified a distinctive pattern that distinguishes responders from non-responders, with 90% accuracy.
A UCLA study validates the predictive power of PROSTOX, a genetic test that uses microRNAs to identify patients at higher risk of developing long-lasting urinary side effects from radiation therapy. The test helps doctors and patients choose safer treatment options, reducing the burden of long-term complications.
Researchers developed new AI models, InstaNovo and InstaNovo+, to vastly improve accuracy and discovery in protein science. These models excel in tasks such as de novo peptide sequencing, identifying microorganisms, and discovering novel peptides, with implications for personalized medicine, cancer immunology, and beyond.
Researchers at Weill Cornell Medicine developed a new AI model that harnesses whole-slide tumor imaging data and gene expression analyses to predict how patients with muscle-invasive bladder cancer will respond to chemotherapy. The model outperforms previous models using a single data type, identifying key genes and tumor characteristi...
A study published in Biological Psychiatry identified the Shisa7 gene as a key driver of heroin addiction. The research team used machine learning to analyze brain tissue from human opioid users and found that modulating this gene's expression influenced heroin-seeking behavior and cognitive flexibility.
Scientists at CSHL and global collaborators have sequenced complete genomes for the Solanum genus, including tomatoes, potatoes, and eggplants. The study reveals the importance of understanding paralog genes in predicting genome editing outcomes.
Researchers at MD Anderson Cancer Center have identified biomarkers for predicting treatment response in metastatic breast cancer and found a potential target for tumor progression in pancreatic cancer. Additionally, they discovered that abnormal chromosome changes predict survival in patients with secondary acute myeloid leukemia.
Researchers developed an AI approach to identify genes contributing to neurodevelopmental disorders like autism spectrum disorder, epilepsy, and developmental delay. The tool enhances gene discovery by predicting additional genes involved in these conditions.
A recent study reveals genes that may help predict prostate cancer outcomes, including androgen receptor AR-V7 and p160 gene family. The research suggests these genes could serve as potential prognostic biomarkers for prostate cancer, highlighting the importance of androgen signaling in disease progression.
Researchers found a biomarker, RNA Polymerase II (RNAPII), associated with tumor aggressiveness and recurrence in meningioma and breast cancers. The study developed a novel profiling technology, Cleavage Under Targeted Accessible Chromatin (CUTAC), to measure gene transcription activity from DNA, which predicted cancer outcomes.
A new 3D bioprinted gastric cancer model successfully replicates the unique characteristics of individual patients' tissues, predicting drug responses and prognosis with high accuracy. This innovative platform enables rapid evaluation within two weeks, contributing to personalized cancer treatment development.
A novel diagnostic system called TwinDemic Detection offers simultaneous and rapid detection of SARS-CoV-2 and influenza A virus. The system has a detection limit of 0.46 picomolar for CoV and 0.39 pM for IAV, correctly predicting positive and negative samples in high percentages.
A recent study found that a genetic test for opioid use disorder (OUD) had high rates of both false positive and false negative results, questioning its usefulness. The testing could lead to patients receiving opioids despite low risk or being denied effective pain relief due to high risk.
Researchers at Columbia University Irving Medical Center have developed an AI method that can accurately predict the activity of genes within any human cell, revealing the cell's inner mechanisms. The system can also uncover hidden biology of diseased cells and explore the role of genome's 'dark matter' in cancer and other diseases.
A six-year study examining 38 clinical isolates of Cryptococcus found genes and gene alleles associated with disease severity. The research aims to develop new treatments targeting these genetic variations, predicting disease outcomes and improving patient care.
A new DNA sequencing test called AR-ctDETECT has been found to distinguish between patients with poor and favorable prognoses in advanced prostate cancer. The test identified circulating tumor DNA in 59% of patients and showed that detectable ctDNA was associated with worse overall survival.
The study revealed a comprehensive functional network of 10,525 genes constructed using supervised machine learning that integrates protein datasets and RNA sequencing data from 11 cancer types. The approach identified protein modules and a hierarchical modular organization linked to cancer hallmarks and clinical characteristics.
A novel study found that the TPMT∗8 allele is associated with reduced metabolism of thiopurine drugs, which can lead to toxicity. The research emphasizes the importance of understanding the function of TPMT∗8 to ensure effective pharmacogenomic testing across all ancestries.
A new framework developed by UCLA researchers suggests that genetic data from large libraries of sequenced human genomes can improve the predictive power of genetics in determining how well a patient will respond to commonly prescribed medications and the severity of any side effects. The study, which analyzed data from over 342,000 pe...
A new study from UCLA Health Jonsson Comprehensive Cancer Center introduces a combined genetic and functional profiling approach to predict how glioblastoma will respond to therapy. The approach helps identify new ways to target and treat the tumors more effectively, including using an experimental drug called ABBV-155.
A new AI-powered tool can predict the activity of thousands of genes within tumor cells based on standard microscopy images of biopsy samples. The tool showed a high correlation with real gene activity data, particularly for certain cancer types.
A new study from Iowa State University aims to increase emphasis on phenotypic plasticity in improving crop performance. Researchers linked crop traits, genetics and weather conditions using a quantitative framework, predicting flowering time and yield component traits with high accuracy.
Researchers developed a 36-gene predictive score that surpasses conventional methods in predicting tamoxifen treatment resistance. The polygenic score UAB36 has potential as a tool for personalized medicine, helping identify patients at higher risk of poor survival and suggesting alternative treatment strategies.
Researchers identified three long noncoding RNAs associated with worse outcomes in colorectal cancer patients, potentially serving as prognostic markers. The study's findings could enable doctors to separate high-risk patients from those at low risk of disease recurrence, leading to more effective treatment strategies.
Researchers have identified a genetic signature that can predict neonatal sepsis in newborns before symptoms appear, allowing for earlier recognition and life-saving treatment. The discovery has the potential to improve healthcare outcomes in lower- and middle-income countries where neonatal sepsis is most prevalent.
A new AI-based system, BELA, accurately assesses IVF embryo quality by analyzing time-lapse video images and maternal age. The system generates a predictive score for euploidy or aneuploidy, offering an objective measure of embryo quality.
A team of scientists developed an advanced computational technique to predict gene architecture through nucleosome position, combining experimental approaches with machine learning techniques. The study demonstrates that nucleosomal architecture is greatly influenced by DNA sequence information and physical signals.
Researchers at Lehigh University are developing predictive models for gene editing with CRISPR to improve outcomes and expand medical applications. The team is using AI and advanced computer models to simulate the effects of altering a single gene on the entire genome, enabling them to predict and avoid unintended consequences.
A new individualized risk prediction tool has been developed to predict the severity of heart disease in people suffering from Long QT syndrome. The test analyzes genetic mutations associated with the condition and can identify those at high risk of sudden cardiac death, allowing for tailored treatment.
Researchers have developed a risk assessment tool using deep learning to decipher rare genetic variants. The method, called DeepRVAT, predicts gene impairment and potential impact on health, improving disease diagnosis and personalized medicine.
Purdue researchers have developed an AI model that can predict maize yield using remote sensing data and environmental factors. The model, which combines hyperspectral cameras, LiDAR instruments, and genetic markers, can categorize healthy and stressed crops before farmers or scouts can spot a difference.
A new study reveals that non-cognitive skills, such as motivation and self-regulation, are crucial for academic achievement. The research found that genetic factors play a significant role in shaping these skills, which become increasingly influential throughout childhood.
A recent study published in PNAS explores how plants combine clock signals with environmental cues under naturally fluctuating conditions. The research team developed statistical models that accurately predict gene expression activity under control of circadian clock responses to environmental signals.
Researchers are working on a new approach to breeding corn that incorporates genomic selection and gene expression analysis to improve climate resilience. They aim to develop high-accuracy prediction models that can identify suitable genotypes for specific locations and future climates, reducing the need for trial-and-error approaches.
Researchers at Weill Cornell Medicine have discovered a connection between DNA markers and the aging process. The study found that specific retroelements in the human genome can act as epigenetic clocks predicting chronological age and may be involved in aging.
A recent study published in Frontiers in Immunology highlights the crucial role of tissue-resident memory T cells in non-small cell lung cancer. The research found that these cells can significantly impact patient outcomes and guide personalized treatment strategies, particularly those involving immunotherapy.
A study identifies a 10-gene biomarker that can predict whether stage II or III colon cancer patients will benefit from adjuvant chemotherapy. The gene signature also has the potential to predict which patients may respond to immunotherapy.
Researchers found specific gene variants associated with behavioral health outcomes after a stroke. The study suggests that genetic differences may predict stroke recovery trajectory, enabling personalized medicine approaches for individualized treatment.
Researchers investigate chemical modifications to genetic regulation mechanisms, finding that Set8 controls gene activity through a mechanism other than histone modification. This study refines our understanding of genetic regulation relevant to human diseases like cancer.
A UAV-based method was developed to accurately predict sugar beet root weight and sugar content, improving breeding efficiency and cultivar development. The approach achieved significant correlation coefficients (R^2 = 0.89 for RW and 0.83 for SC) using canopy coverage and height data.
Researchers developed a machine learning approach to identify potential subtypes in diseases, significantly enhancing disease classification and treatment strategies. The model uncovered 515 previously unannotated disease subtypes.
Researchers at Linköping University created a tool to predict risk of persistent side effects in breast cancer patients treated with taxane drugs. The model uses genetic characteristics to forecast the risk of nerve damage, which can be used to adapt treatment and improve patient outcomes.
Researchers combined DNA markers from two genotyping systems to improve genomic predictions and GWAS for 24 fruit traits. The results showed increased accuracy and detection power when using combined datasets, suggesting benefits to leveraging historical data.
Researchers at Weill Cornell Medicine have identified cellular and molecular markers that can predict when pancreatic cancer will spread to the liver or other organs. The study found that patients with early-stage pancreatic cancer who showed signs of immune exhaustion were more likely to develop liver metastases.
Researchers found that pentraxin 3 is a non-invasive biomarker for severe fibrosis and increased carotid intima-media thickness in patients with MAFLD. Elevated PTX3 levels were associated with advanced fibrosis and larger CIMT values.