Review

A comprehensive review from Cell envisioning 'AI scientists' as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents integrating AI models and biomedical tools with expert human oversight. Covers the landscape of AI agents for biomedical discovery, including virtual laboratories, autonomous experimentation, and human-AI collaboration frameworks.

We envision 'AI scientists' as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents that integrate AI models and biomedical tools with expert human oversight. This review covers the landscape of AI agents for biomedical discovery, including virtual laboratories, autonomous experimentation, and human-AI collaboration frameworks.

A comprehensive review from Nature Reviews Cancer examining how AI agents (beyond traditional ML classifiers) are transforming cancer research and oncology. Covers LLM-powered agents for clinical decision support, drug discovery, treatment planning, and patient care, including agentic systems capable of logical reasoning, multi-step planning, and tool use in oncology contexts.

Since 2022, artificial intelligence (AI) methods have progressed far beyond their established capabilities of data classification and prediction. Large language models (LLMs) can perform logical reasoning, multi-step planning, and tool use, enabling a new paradigm of AI agents for cancer research and oncology. This review examines how AI agents are transforming clinical decision support, drug discovery, treatment planning, and patient care in oncology.

A comprehensive survey of deep learning approaches for polygenic risk scores (PRS). Reviews how neural networks can model non-linear relationships between genetic variants and disease risk, going beyond traditional linear PRS methods, and assesses their performance across different traits and architectures. Published in Briefings in Bioinformatics.

Polygenic risk scores (PRS) combine the effects of multiple genetic variants to predict an individual's genetic predisposition to a disease. PRS typically rely on linear models, which assume that all genetic variants act independently. There is growing interest in applying deep learning neural networks to model PRS given their ability to model non-linear relationships. We conducted a survey of the literature to investigate how neural networks are being applied to PRS.

A comprehensive review of imaging-derived phenotypes (IDPs) for genetic analysis. Covers MRI, CT, X-ray, OCT, and other imaging modalities; traditional (FSL, FreeSurfer) and deep learning (U-Net, nnU-Net, self-supervised contrastive learning) pipelines for IDP extraction; biobank-scale cohorts (UK Biobank, All of Us); GWAS of brain, cardiac, retinal, abdominal, and skeletal IDPs; Mendelian randomization for causal inference linking organ structure to disease; and emerging challenges in multi-organ phenomics, longitudinal imaging, and clinical translation of IDP-based PRS.

Imaging-derived phenotypes (IDPs) developed from medical imaging data, such as magnetic resonance imaging, computed tomography and X-ray scans, are traits that provide quantitative information on anatomical and functional properties of organs and tissues. IDPs are powerful tools for identifying biomarkers and studying disease mechanisms. When coupled with genetic data, IDPs can be analysed as heritable phenotypes using modern gene mapping methods to uncover genotype-phenotype relationships. The field of imaging genomics is rapidly maturing, with the emergence of high-quality imaging datasets collected in biobank-scale cohorts and sophisticated computational methods for extracting IDPs from imaging data, including tools that leverage machine learning. Here we review common imaging modalities and analytical approaches for developing IDPs, discuss biological insights gleaned from the large-scale genetic analysis of imaging traits and highlight emerging areas and remaining challenges that must be overcome to realize the full potential of IDPs for genetic analysis.

Review of the FANTOM projects and their paradigm-shifting contributions to genomics, including the transition from cDNA-based transcript annotation to CAGE-based promoter/expression analysis, and the discovery of widespread non-coding RNA transcription.