Articles tagged with Gene Prediction
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.
A new machine-learning model using serum fusion-gene levels predicts HCC with an accuracy of 83-91%, significantly improving upon current biomarkers like serum alpha-fetal protein. This breakthrough tool may help identify patients at risk and monitor cancer recurrence, leading to improved survival rates.
Mayo Clinic researchers have invented a new class of artificial intelligence (AI) algorithms called hypothesis-driven AI, which can help discover the complex causes of diseases like cancer and improve treatment strategies. This emerging class of AI offers an innovative way to use massive datasets to guide individualized medicine.
Researchers developed a prediction tool to classify proteins based on their potential to bind RNA G-quadruplexes, showing high protein disorder and hydrophilicity. This discovery provides insights into gene expression and phase-separation into membrane-less organelles.
A new genetic test has identified patients with triple negative early-stage breast cancer who are unlikely to respond to immunotherapy drugs. The test, called ImPrintTN, can predict a patient's likelihood of responding to these treatments and help avoid severe side effects.
Researchers developed chronological age prediction models by analyzing gene expression changes in the prefrontal cortex, identifying genes associated with aging and potential mechanisms. The models showed high correlation with age and demonstrated female and male-specific differences.
Researchers developed an oxidative stress-based prognostic model for bladder cancer, identifying distinct molecular subtypes and predicting patient outcomes. The model shows promise in tailoring personalized treatment approaches, particularly for patients with low-risk profiles.
PandaOmics uses advanced AI algorithms to process vast quantities of diverse data, performing gene and pathway analysis and target predictions. The platform has been extensively validated in multiple therapeutic areas, including oncology, inflammation, and immunology.
A new genetic signature of 140 genes may predict enhanced disease-free survival in patients with non-small cell lung cancer treated with immunotherapy and low-dose radiation. The signature is associated with aggressive tumor growth but also increased immunity and tissue repair after treatment.
Researchers at UCSF used clinical data and a precision medicine approach to identify early risk factors for Alzheimer’s disease, predicting its onset with 72% accuracy. High cholesterol, osteoporosis, and erectile dysfunction were found to be predictive factors in both men and women.
The tawny owl's pale grey plumage is linked to crucial functions aiding survival in cold environments, including energy homeostasis and fat deposition. Genetic analysis reveals a 70-100% accuracy in predicting grey coloration through specific genetic variants.
Researchers develop a novel genomic classification system that categorizes patients into 12 distinct groups based on their underlying genomic profiles. The individualized risk model, IRMMa, uses advanced statistical methodologies to generate tailored predictions of patient response to different therapies.
Scientists have identified a vulnerability in our genomes that can cause developmental defects, such as extra fingers and heart disorders. By analyzing genomic sequences and enhancer variants, researchers found that single-letter changes to the DNA within our genomes can dramatically affect gene expression.
Researchers developed a molecular predictor of radiation response using cell line data and machine learning-based approaches, capturing a wider range of biological processes. The new gene signature has the potential to aid decision-making, personalize treatments, and improve outcomes for various types of cancers.
A machine learning technique called LASSO was used to analyze blood samples from six countries, identifying seven genes that can predict the risk of developing a secondary respiratory bacterial infection. The findings aim to guide clinicians in making more informed decisions about antibiotic use.
A new study has found that evolution is influenced by a genome's evolutionary history, allowing scientists to predict gene interactions and tackle real-world issues like antibiotic resistance. This discovery opens the door to new possibilities in synthetic biology, medicine, and environmental science.
A study of first-year college students reveals that pandemic stress triggers a rise in clinical depression, even among those with genetic factors that previously shielded them. The research identifies potential predictors of psychological resilience and provides a tool to identify at-risk students for targeted support.
Researchers at West Virginia University are using artificial intelligence to analyze habanero peppers and develop new methods for predicting genetic traits. The goal is to improve crop yields and prevent genetic diseases, with potential applications in human health.
Researchers have successfully mapped the entire HLA class II landscape, predicting how pathogens are displayed on cell surfaces. The mapping reveals that multiple HLA variants play essential roles in autoimmune disorders and organ rejection, highlighting their potential for developing immunotherapy treatments.
The study used a machine learning approach called FUN-PROSE to predict how fungi react to different environmental conditions. The model was able to accurately predict the expression of genes in baker's yeast and two less studied fungi, with limitations noted for organisms with more complex gene regulation.
Researchers discuss a new approach integrating genomic, epigenomic, transcriptomic, and machine learning methods to identify functional genetic variants and characterize their mode of action in regulating target genes. This method aims to improve understanding of disease etiology and prioritize causative inherited genetic variants.
Researchers at Purdue University developed a new tool to visualize neural network decisions, making it easier to identify errors in image recognition. The tool uses graph-topological data analysis to provide a bird's-eye view of all images in a database, revealing areas where the network struggles to distinguish between classifications.
Researchers developed an AI model using epigenetic factors to predict patient outcomes across multiple cancer types. The model successfully divided patients into two groups with different survival chances, and its genes were found to have a significant overlap with cluster-defining signature genes.
Researchers at Oak Ridge National Laboratory used quantum biology and artificial intelligence to sharpen the CRISPR Cas9 genome editing tool, improving its efficiency on microbes. The new model revealed key features about nucleotides that enable better guide RNA selection.
A new study suggests that analyzing genetic material from nearby healthy tissue may help predict lung cancer's return after treatment. The study analyzed RNA from tumor cells and adjacent, seemingly normal lung tissue and found that the expression of genes associated with inflammation was especially useful for making predictions.
Researchers found that certain combinations of gene mutations resulted in predictable effects on tomato size, while others yielded random outcomes. The study suggests the role of background mutations demands reassessment for genome editing applications. This new interpretation may help humanity adapt crops to meet evolving societal needs.
A new study doubles the number of protein families known up until now and identifies many novel structure predictions using a massive analysis of 1.3 billion proteins. The researchers leveraged AI methodologies to unravel the roles of previously unknown protein sequences, expanding the horizons of potential functions.
A research team led by HKUST developed an AI-powered model to predict glioma patients' prognosis and identify early predictors of tumor evolution under therapy. The model, CELLO2, uses genomic and transcriptomic data from 544 glioma patients to accurately predict treatment-induced hypermutation and grade progression.
A study has identified genetic markers that can predict whether rheumatoid arthritis will improve or worsen during pregnancy. These markers were found in white blood cells and genes related to B cells, and may help women plan their treatment and avoid unnecessary medication exposure.
A new AI-based predictive tool called PARMESAN helps scientists discover potential treatments for genetic disorders by analyzing public biomedical literature databases. The tool assigns weighted scores to gene-protein interactions, identifying promising drugs and accelerating research speed.
Insilico Medicine has identified 9 potential dual-purpose targets against aging and 14 major age-related diseases using Microsoft BioGPT. The proposed genes include CCR5 and PTH, which have not been previously correlated to the aging process.
A study published in eBioMedicine identified 9 sets of biomarkers, both metagenomic and transcriptomic, associated with 30-day mortality in patients with severe community-acquired pneumonia. The biomarkers were validated with an accuracy of 85%, significantly higher than existing clinical prediction models.
A new study from Uppsala University has found that women with a high genetic predisposition for blood clots are six times more likely to develop a blood clot during the first two years of using contraceptive pills. This knowledge could be used to identify women at risk and counsel them on alternative methods of contraception.
A Geisinger-led study found that knowing the genetic cause of high cholesterol increases heart disease risk more than having high cholesterol levels alone. The study used UK Biobank data and observed distinct differences in heart disease rates among participants with different genetic causes.
A recent study has successfully predicted potential drug outcomes and side effects by analyzing the discrepancy in gene perturbation effects between cells and humans. Researchers used machine learning to forecast drug approvals, improving reliability over conventional methods that only consider chemical properties.
Researchers at Gladstone Institutes create Gaussian Process Spatial Alignment (GPSA) to analyze 2D data from tissue slices and generate a 3D 'atlas' of the tissue. This allows for deeper understanding of biological tissue samples, enabling more precise predictions of gene expression and treatment outcomes.
A large-scale international collaborative study has identified new genes associated with breast cancer, which could lead to better risk prediction and improved clinical management. The study found evidence for at least four new breast cancer risk genes, with many others showing suggestive evidence.
A research group at Kyoto University has successfully developed a self-fertile buckwheat variety and a new type of the crop with a sticky texture. This breakthrough could contribute to the efficient breeding of less-common orphan crops, addressing the world's growing food demands.
Researchers developed an AI model called OncoNPC that can analyze genetic data to predict cancer type and origin. The model accurately classified at least 40% of tumors with unknown origin, leading to a 2.2-fold increase in eligible patients for targeted treatments.
The 'survival of the accessible' model provides an alternative explanation for evolutionary changes in flu viruses, highlighting the importance of mutational bias and variant accessibility. The research reveals how specific mutations can gain or lose function, influencing protein activity and potentially driving pandemics.
A new study uses machine learning to analyze data from DrugAge, a database of chemical compounds modulating lifespan in model organisms. The researchers create four types of datasets to predict whether or not a compound extends the lifespan of C. elegans, using features such as compound-protein interactions and Gene Ontology terms.
Researchers found significant relationships between the cows' genetic merit and their calves' performance. The genomic prediction tool allowed farmers to make informed decisions that enhance sustainable profitability.
Researchers used proteomics and small RNA sequencing to analyze 103 human blood plasma samples, identifying 21 proteins and 315 small RNAs associated with aging. Combining protein and miRNA data improved age predictions (R2 = 0.70 ± 0.01), suggesting a broader range of age-related physiological changes.
Researchers at MD Anderson Cancer Center have engineered a new model of aggressive renal cell carcinoma, highlighting molecular targets and genomic events that trigger chromosomal instability. The loss of interferon receptor genes plays a pivotal role in allowing cancer cells to become tolerant of chromosomal instability.
Researchers developed a polygenic scoring system to predict ALS disease risk, improving case status prediction in Michigan and Spain. The system takes into account common genetic variants and explains 4.1% of ALS cases caused by genetic factors.
Researchers developed Precious1GPT, a multimodal transformer-based approach for aging clock development and feature importance analysis. The model utilizes methylation and transcriptomic data to predict biological age and identify disease-related genes, providing a pathway for therapeutic drug discovery.
Researchers developed CrossDome, a tool that uses genetic and biochemical information to predict T-cell immunotherapy's impact on healthy cells. The tool identified high-risk candidates in cases where treatments mistakenly attacked heart cells.
Researchers developed an AI system, Geneformer, to predict how disruptions in human gene connections cause disease. The model, trained on data from thousands of genes, can identify potential drug targets for diseases like heart disease and cancer.
Large structural changes in human ancestors' genomes may have sparked smaller changes that set human brains apart from other primates. Researchers found that many enhancers, which regulate brain development, are located near these regions, suggesting a link between DNA folding and brain evolution.
A machine learning framework predicts and quantifies chromosome synthesis difficulties, providing guidance for optimizing design and synthesis processes. The model achieved high accuracy and predictive ability, enabling the development of a Synthesis difficulty Index to explain causes of synthesis difficulties.
Researchers developed a gene signature called CisSig to predict cancer patients' response to cisplatin. The approach aims to overcome the obstacle of interpreting gene signatures in the human body and has been validated in muscle-invasive bladder cancer patients.
Researchers have developed a new method for downregulating gene translation in plants using upstream open reading frames (uORFs). The study, published in Nature Biotechnology, demonstrates the potential for precise and incremental regulation of gene expression.
Bielefeld University researchers developed an AI method using Capsule Networks to analyze genotype profiles of 3,000 ALS patients, achieving 87% accuracy in predicting whether or not people will develop ALS. The study reveals over 900 genes that play a role in identifying the disease.
Researchers at Rutgers University used artificial intelligence to analyze genes associated with cardiovascular disease, identifying key factors such as age, gender, and race. The study aims to accelerate early diagnosis and treatment of conditions like atrial fibrillation and heart failure.
A new study links genetic changes in kidney cancer to patient outcomes, identifying four groups of patients based on mutation presence. This research may lead to more effective prediction of recurrence risk and personalized treatment for thousands of patients annually.
A decade-long international study has linked genetic changes in kidney cancer to patient outcomes, identifying four groups of patients based on specific genes. The findings suggest that tumour DNA sequencing may provide a more effective way to predict patient risk of kidney cancer recurrence.
A new machine learning model combines fusion gene profiling, serum PSA level, and Gleason score to predict prostate cancer recurrence with improved accuracy. The model outperformed clinical data alone and provided valuable insights into the mechanism of disease progression.
Researchers developed a computer software called CellOracle that can predict the role of individual genes in early embryonic development. The tool helps scientists identify key genes involved in development but may have been missed by older methods, providing new insights into birth defects and cancer.
A study of 184 grade I and II meningiomas found associations between specific tumor mutations and increased or decreased recurrence rates. Mutations in ATM and CREBBP were linked to accelerated recurrence, while POLE mutations showed protective effects, highlighting potential targets for intervention.