Aristotelis Tsirigos

A developmentally regulated long-range enhancer-promoter contact mediates human neural development

The paper identifies a developmentally regulated long-range enhancer-promoter contact that is critical for SOX2 expression and neuroectodermal differentiation in human neural development.

Vision-Language Models for Image-Based Dietary Assessment: A Benchmark of Accuracy, Cost, and Prompt Strategies Across Ten Models

This study benchmarks ten vision-language models for automated food recognition, weight, and calorie estimation using the Nutrition5k dataset, finding Gemini 3.0 Flash and 3.1 Flash Lite as top performers.

Multicenter self-supervised computational pathology identifies prognostic histomorphological phenotypes in colorectal cancer

This paper develops a self-supervised computational pathology framework to identify prognostic histomorphological phenotypes in colorectal cancer using H&E images and tile embeddings.

Hi-C for genome-wide detection of enhancer-hijacking rearrangements in routine lymphoid cancer biopsies

This study uses FFPE-compatible Hi-C to detect enhancer-hijacking rearrangements in lymphoid cancers, identifying clinically relevant drivers missed by standard methods.

TASC: A transcriptome-driven machine learning classifier to explore molecular heterogeneity and relapse-associated programs in T-cell Acute Lymphoblastic Leukemia

This paper introduces a transcriptome-driven machine learning classifier to predict molecular subtypes in T-cell Acute Lymphoblastic Leukemia and reveals subtype-specific relapse patterns.

High-throughput in silico screen uncovers key regulators of 3D genome architecture

The paper identifies ZNF654 and JMJD6 as novel factors defining TAD boundaries through in silico screens and experimental validation.

Multiomic characterization, early detection, and therapeutic targeting of myeloid sarcoma

This study characterizes myeloid sarcoma through multi-omic profiling, identifies RAS pathway activation as a hallmark, and shows RAS inhibition reduces tumor burden in mouse models.

Islands of Signal and Transcriptomic Sequencing: A Foundation Model for Mutation and Lineage Prediction based on DNAMethylation and RNA-seq

This paper develops a multiomic foundation model that combines DNA methylation and RNA-seq data to predict mutations and lineage across cancers.

Regulating white blood cell activity through the novel Universal Receptive System

This study demonstrates that targeting newly discovered surface-bound DNA and RNA receptors on leukocytes with Leukocyte-Tells enhances immune cell functions, showing significantly higher antimicrobial and anticancer activities than control leukocytes.

Cross-species analysis identifies genotype-driven vulnerabilities in lung adenocarcinoma

This study identifies genotype-specific immune and metabolic vulnerabilities in lung adenocarcinoma through cross-species analysis of human and mouse tumors.

Non-segmented unsupervised learning of multispectral whole slide images for robust analysis of tissue repair and regeneration

This paper introduces a segmentation-free method for analyzing multispectral whole slide images to study tissue repair and regeneration, revealing tissue compartments and dynamics without prior labels.

Decoding the gene regulatory landscape through multimodal learning of protein-DNA interactions

Chromnitron predicts protein-DNA binding landscapes across cell types and proteins using multimodal learning, revealing new regulators of T cell exhaustion and dynamic shifts during neurogenesis.

CRISPR-inhibition screen for lncRNAs linked to melanoma growth and metastasis

The paper identifies lncRNAs involved in melanoma growth and metastasis using CRISPR-inhibition screens and validates their functional roles.

Binding domain mutations provide insight into CTCF's relationship with chromatin and its contribution to gene regulation

The paper investigates how CTCF mutations affect chromatin accessibility, cohesin binding, and gene regulation through multivariate modeling and mutant perturbations.

Self-Supervised Learning Reveals Clinically Relevant Histomorphological Patterns for Therapeutic Strategies in Colon Cancer

This paper uses self-supervised learning to identify histomorphological patterns in colon cancer WSIs, revealing clinically relevant clusters associated with survival and treatment responses.

A multi-scale segmentation-free self-supervised AI model to characterize the heterogeneity of the brain tumor microenvironment

This paper introduces a segmentation-free self-supervised AI model to analyze brain tumor microenvironments, identifying a novel tumor-associated B cell subset linked to improved survival.

Characterization of tumor heterogeneity through segmentation-free representation learning

The paper introduces a segmentation-free vision transformer, CANVAS, to discover and characterize tumor microenvironment signatures from high-dimensional multiplexed images, identifying a monocytic signature linked to poor prognosis.

Clonal Heterogeneity in Human Pancreatic Ductal Adenocarcinoma and Its Impact on Tumor Progression

This study analyzes clonal heterogeneity in human pancreatic ductal adenocarcinoma using single-cell and spatial transcriptomics, revealing transcriptional continua, clonal transitions, and spatially dispersed clones associated with metastasis.

Universal Receptive System as a novel regulator of transcriptomic activity of Staphylococcus aureus

The paper investigates the regulatory role of TezRs in Staphylococcus aureus gene transcription and identifies differentially expressed genes and pathways following TezR destruction.

The Universal Receptive System acts as a novel regulator in the production of antimicrobial and anticancer bioactive compounds by white blood cells

The paper shows that inactivating Teazeled receptors in human leukocytes increases production of antimicrobial and anticancer compounds, with enhanced activity and stability.

Members of an array of zinc finger proteins specify distinct Hox chromatin boundaries

The paper identifies zinc finger proteins that establish distinct chromatin boundaries at Hox clusters during development, working with cohesin to regulate cell fate.

Previously unknown regulatory role of extracellular RNA on bacterial directional migration

The paper shows extracellular RNA regulates bacterial directional migration, and its destruction triggers 'panic state' migration in biofilms.

Systematic mapping and modeling of 3D enhancer-promoter interactions in early mouse embryonic lineages reveal regulatory principles that determine the levels and cell-type specificity of gene expression

Inflammation in the tumor-adjacent lung as a predictor of clinical outcome in lung adenocarcinoma

This study identifies inflammation in tumor-adjacent lung tissue as a predictor of clinical outcome in lung adenocarcinoma using multi-omic analysis of 143 stage I cases.

Cell type-specific prediction of 3D chromatin organization enables high-throughput in silico genetic screening

This study introduces C.Origami, a deep learning model that predicts cell type-specific 3D chromatin organization, enabling in silico genetic screening to identify genomic regions affecting chromatin structure.

Single cell RNA-seq identifies developing corneal cell fates in the human cornea organoid

This study uses single-cell RNA-seq to map cell fates in human cornea organoids and identifies developmental states of corneal cell types.

A bipartite element with allele-specific functions safeguards DNA methylation imprints at the Dlk1-Dio3 locus

The paper identifies a bipartite imprinting control region at the Dlk1-Dio3 locus that maintains imprint stability through allele-specific regulation of DNA methylation and chromatin structure.

Mitotic retention of H3K27 acetylation promotes rapid topological and transcriptional resetting of stem cell-related genes and enhancers upon G1 entry

This study shows that H3K27 acetylation retention during mitosis accelerates transcriptional and topological resetting of stem cell genes in mouse pluripotent stem cells upon G1 entry.

A Machine Learning approach for assessing drug development risk

This paper proposes a machine learning approach to estimate drug development risk more accurately than traditional models.

Defining the relative and combined contribution of CTCF and CTCFL to genomic regulation

The paper investigates the distinct and combined roles of CTCF and CTCFL in chromosome organization and transcription by analyzing their binding sites and functional domains.