Martin Hofmann‐Apitius

Leveraging Multimodal Large Language Models to Extract Mechanistic Insights from Biomedical Visuals: A Case Study on COVID-19 and Neurodegenerative Diseases

This paper uses GPT-4o to extract mechanistic insights from biomedical images related to COVID-19 and neurodegenerative diseases, revealing both established and novel biological connections.

An Interactive Brain Atlas of Knowledge

The paper develops TVBase, a platform that projects biomedical knowledge onto a 3D brain atlas to support neuroimaging analysis and hypothesis generation.

CBM KG: A Comorbidity-Centric Knowledge Graph Uncovering Causal Pathomechanisms Between COVID-19 and Neurodegenerative Diseases

The paper introduces CBM KG, a knowledge graph linking COVID-19 and neurodegenerative diseases through causal mechanisms, integrating 2,800 relationships from 63 studies.

Unraveling the Co-Morbidity between COVID-19 and Neurodegenerative Diseases Through Multi-scale Graph Analysis: A Systematic Investigation of Biological Databases and Text Mining

SynDRep: A Knowledge Graph-Enhanced Tool based on Synergistic Partner Prediction for Drug Repurposing

SynDRep predicts synergistic drug partners for disease repurposing using knowledge graphs and machine learning, achieving 84.58% true predictions with HolE and 0.796 ROC-AUC with random forest.

Medicinal chemistry lens on patent data in SureChEMBL

The paper analyzes patent data from SureChEMBL to assess the drug-likeness and clinical development stage of compounds, providing insights into their relevance for pharmaceutical discovery.

Semantic harmonization of Alzheimer's disease datasets using AD-Mapper

This paper introduces AD-Mapper, a tool for semantic harmonization of Alzheimer's disease datasets, which outperforms a string-matching baseline.

Exploring the intricacies and pitfalls of the ATN framework: An assessment across cohorts and thresholding methodologies

This paper evaluates how different thresholding methods affect ATN profiles across AD cohorts, finding high variability and limited generalizability of results.

Integrative analysis to identify shared mechanisms between schizophrenia and bipolar disorder and their comorbidities

This study identifies shared genetic and biological mechanisms between schizophrenia, bipolar disorder, and type 2 diabetes mellitus using integrative analysis of gene expression datasets.

PEMT: A patent enrichment tool for drug discovery

PEMT extracts patent information linked to chemical structures and gene names from public databases to support drug discovery and research.

Elucidating gene expression patterns across multiple biological contexts through a large-scale investigation of transcriptomic datasets

This work analyzes transcriptomic data across multiple biological contexts to identify unique and shared gene expression patterns using co-expression networks and pathway analysis.

STonKGs: A Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs

The paper introduces STonKGs, a Transformer model trained on biomedical text and knowledge graphs, which outperforms single-modality models in classification tasks.

DecoPath: A web application for decoding pathway enrichment analysis

DecoPath is a web tool that helps interpret pathway enrichment analysis results by comparing across databases and methods, highlighting consensus and discrepancies.

Towards a global investigation of transcriptomic signatures through co-expression networks and pathway knowledge for the identification of disease mechanisms

This paper investigates transcriptomic signatures across diseases by integrating co-expression networks and pathway knowledge to identify disease mechanisms.

Virtual connectomic datasets in Alzheimer's Disease and aging using whole-brain network dynamics modelling

The paper introduces virtual connectomic datasets by simulating missing connectivity features from existing neuroimaging data, enabling machine learning classification comparable to empirical data.

CLEP: A Hybrid Data- and Knowledge- Driven Framework for Generating Patient Representations

CLEP generates patient representations by integrating prior biological knowledge with patient data, improving classification performance compared to using raw transcriptomics data.

MultiPaths: a Python framework for analyzing multi-layer biological networks using diffusion algorithms

The paper introduces MultiPaths, a Python framework for analyzing multi-layer biological networks using diffusion algorithms, showing improved predictive performance through integrated multi-omics data.

Using predictive machine learning models for drug response simulation by calibrating patient-specific pathway signatures

This paper uses predictive machine learning models to simulate drug responses by calibrating patient-specific pathway signatures, identifying potential drugs and mechanisms for three cancers.

Drug2ways: Reasoning over causal paths in biological networks for drug discovery

Drug2ways predicts drug candidates by analyzing causal paths in biological networks for disease treatment and drug repositioning.

The COVID-19 PHARMACOME: A method for the rational selection of drug repurposing candidates from multimodal knowledge harmonization

The paper presents a drug-target-mechanism graph to identify synergistic drug combinations for SARS-CoV-2 treatment, validated through experimental testing.

COVID-19 Knowledge Graph: a computable, multi-modal, cause-and-effect knowledge model of COVID-19 pathophysiology

The paper constructs a cause-and-effect knowledge graph of COVID-19 pathophysiology from scientific literature and provides it as a public resource.

GuiltyTargets: Prioritization of Novel Therapeutic Targets with Deep Network Representation Learning

GuiltyTargets prioritizes therapeutic targets using deep learning on protein interaction networks, achieving high accuracy in disease-specific target ranking and showing potential for target repositioning.

Unravelling the debate on heme effects in COVID-19 infections

The paper investigates the potential link between heme levels and COVID-19 pathogenesis by analyzing protein interactions and common pathways.

Variational Autoencoder Modular Bayesian Networks (VAMBN) for Simulation of Heterogeneous Clinical Study Data

This paper introduces VAMBN, a variational autoencoder modular Bayesian network for simulating realistic clinical study data while ensuring privacy and enabling counterfactual scenarios.

A computational approach for mapping heme biology in the context of hemolytic disorders

The paper develops an ontology and knowledge graph to model heme biology and investigates its role in Toll-like receptor signaling.

The Impact of Pathway Database Choice on Statistical Enrichment Analysis and Predictive Modeling

This study benchmarks the impact of pathway database choice on enrichment analysis and predictive modeling, showing that using multiple or integrative databases improves consistency and performance.

PathMe: Merging and exploring mechanistic pathway knowledge

PathMe harmonizes three pathway databases into a unified schema to enable comprehensive exploration of pathway crosstalk and consensus.

Integration of Structured Biological Data Sources using Biological Expression Language

The paper introduces Bio2BEL, a set of Python packages that convert multi-modal biological data into Biological Expression Language for integration and analysis.

Re-curation and Rational Enrichment of Knowledge Graphs in Biological Expression Language

The paper develops workflows to re-curate and enrich knowledge graphs encoded in Biological Expression Language using automated and manual methods.

PTSD Biomarker Database: Deep Dive Meta-database for PTSD Biomarkers, Visualizations, and Analysis Tools

The PTSD Biomarker Database compiles over 900 PTSD biomarkers from 109 studies to enable exploration and comparison of biomarker findings through interactive visualizations.