Genetics

RegEvol: detection of directional selection in regulatory sequences through phenotypic predictions and phenotype-to-fitness functions

Regulatory DNA controls when and where genes are expressed, making it a key driver of phenotypic evolution. Yet detecting selection in non-coding regions remains difficult, as most approaches rely on sequence conservation or changes in substitution rate rather than molecular effects. RegEvol bridges this gap by linking machine learning-based predictions of transcription factor binding to explicit ...

Deep learning predicts haematopoietic stem cell ageing from 3D chromatin images

The functional decline of the haematopoietic system during ageing propagates detrimental effects on the whole organism, ultimately eroding life and healthspan. Quantifying haematopoietic ageing holds great scientific and clinical relevance. Alterations in chromatin architecture are a well-established hallmark of ageing that encode rich and informative signatures of the ageing process, yet they rem...

Template-based RNA structure prediction advanced through a blind code competition

Automatically predicting RNA 3D structure from sequence remains an unsolved challenge in biology and biotechnology. Here, we describe a Kaggle code co...

Multimodal AI for Single cfDNA Profiling and Cancer Screening

Cell-free DNA (cfDNA) serves as a non-invasive biomarker for cancer detection, but conventional methods face challenges due to the ultra-low abundance...

Interpretable Aging Signatures in Human Retinal Cell Types Revealed by Single-Cell RNA Sequencing and Sparse Logistic Regression

To characterize cell type specific transcriptional changes during human retinal aging and develop machine learning model for cellular age discriminati...

Multiparametric MRI Along with Machine Learning Informs on Molecular Underpinnings, Prognosis, and Treatment Response in Pediatric Low-Grade Glioma

In this study, we present a comprehensive radiogenomic analysis of pediatric low-grade gliomas (pLGGs), combining treatment-naïve multiparametric MRI ...

Quantitative AI based on evolutionary computation and information theory combined with mathematical functions yields algorithmic RNA biomarkers from a randomized rheumatoid arthritis clinical trial, accurately predicting individual patient responses to anti-TNF treatment, to enable precision medicine

The routine derivation of novel biomarkers from therapeutic clinical trials to accurately predict individual patient’s responses, would be a significa...

Automated imaging-based tumor burden and pre-treatment circulating tumor DNA in HPV-associated oropharynx cancer

Artificial intelligence (AI)-based imaging analysis has applications for the diagnosis of head and neck malignancies, and serum circulating tumor-asso...

Deep Learning Chest X-Ray Age, Epigenetic Aging Clocks and Associations with Age-Related Subclinical Disease in the Project Baseline Health Study

Chronological age is a cornerstone of medical decision-making but is limited because individuals age at different rates. We recently released an open-...

The Inherited Retinal Disease Pathway in the United Kingdom: a Patient Perspective and the Potential of AI

Inherited Retinal Diseases (IRDs) are the leading cause of blindness in young people in the UK. Despite significant improvements in genomics medicine,...

Enhancing Rare Disease Education through AI-Driven Podcast Generation

Rare diseases, including many rare genetic epilepsies and neurodevelopmental disorders, present significant challenges in timely diagnosis, treatment,...

Combining Clinical Embeddings with Multi-Omic Features for Improved Patient Classification and Interpretability in Parkinson’s Disease

This study demonstrates the integration of Large Language Model (LLM)-derived clinical text embeddings from the Movement Disorder Society Unified Park...

The genetics of TDP43-Type-C neurodegeneration: a whole genome sequencing study

Frontotemporal lobar degeneration-TDP Type C (TDP-C) is a unique neurodegenerative disease that starts by attacking the anterior temporal lobe leading...

Personalized circulating tumor DNA dynamics predict survival and response to immune checkpoint blockade in recurrent/metastatic head and neck cancer

Recurrent/metastatic head and neck squamous cell carcinoma (R/M HNSCC) is an aggressive cancer with a median overall survival of only 12 months. Exist...

An Interpretable Sparse Graph Contrastive Learning Approach for Identifying Breast Cancer Risk Variants

Genome-wide association studies (GWASs) have identified over 2,400 genetic variants associated to breast cancer. Conventional GWASs methods that analy...

AI-Powered Exploration of IGF2BP3 as a Prognostic Biomarker in Chronic Myeloid Leukemia Progression and Disease Stratification

Chronic Myeloid Leukemia (CML) progresses through chronic, accelerated, and blast crisis phases, making disease stratification and therapeutic respons...

Identification of novel vertebral development factors through UK Biobank driven genetic and body imaging analysis reveals markers for back pain

Numerical variations and transitional anatomy in the human vertebral column, observed in up to 36% of individuals, represent a significant yet underst...

Integration of CA attention and KAN algorithm to predict EGFR mutation status in lung cancer

Epidermal Growth Factor Receptor (EGFR) mutations are critical biomarkers for targeted therapies in non-small cell lung cancer (NSCLC). However, conve...

Leveraging hierarchical structures for genetic block interaction studies using the hierarchical transformer

Initially introduced in 1909 by William Bateson, classic epistasis (genetic variant interaction) refers to the phenomenon that one variant prevents an...

The impact of systematized generation, evaluation, and incorporation of machine learning algorithms for clinical variant classification

Variants of uncertain significance (VUS) pose a significant challenge for those undergoing genetic testing, leading to prolonged uncertainty and inapp...