Biology subjects

Schor, J.

Publications and source records attributed to Schor, J..

4 recordsLinked to original sources

bioRxiv2025

AI-Driven Science Communication: Leveraging LLMs and Knowledge Graphs for Seamless Knowledge Exchange

PurposeScientific knowledge is increasingly captured in structured formats, such as knowledge graphs, yet it remains largely inaccessible to non-technical users. We present EcoToxFred, a prototype conversational AI agent that enables intuitive, natural language access to curated environmental toxicology data. Designed to support users without programming expertise, EcoToxFred facilitates the exploration of complex datasets, such as chemical exposures and species-specific hazard information in European surface waters. MethodsEcoToxFred integrates a large language model (LLM) with a Neo4j graph database via a retrieval-augmented generation (RAG) architecture. The system employs a decision-making agent to interpret user queries, invoke appropriate tools, and translate natural language input into formal graph queries. Outputs are validated and returned in multiple formats, like text, tables, and interactive maps, and are grounded in structured, curated monitoring and hazard data. ResultsThe agent bridges the gap between human intent and formal data retrieval, enabling researchers, policy advisors, and stakeholders to pose complex, multi-step queries without prior training in query languages. By grounding LLM outputs in structured data, we demonstrate the systems ability to respond to diverse question types and deliver transparent, accurate, and context-aware results. EcoToxFred successfully answers broad and highly specific queries, bridging natural language input with formal data retrieval. ConclusionEcoToxFred represents a scalable and transferable framework for human-AI interaction in domain-specific contexts, combining natural language interfaces with structured data. By lowering access barriers to scientific knowledge, the system supports evidence-based decision-making and fosters responsible, human-centered AI use in environmental science and beyond.

pharmacology and toxicology↗

bioRxiv2025

From Toxicogenomics Data to Cumulative Assessment Groups: A Mechanistic Framework for Chemical Grouping

The grouping of chemicals based on shared properties or molecular mechanisms of action is pivotal for advancing regulatory toxicology, reducing data gaps, and enabling cumulative risk assessments. This study introduces a novel framework usingChemical-Gene-Phenotype-Disease (CGPD) tetramers derived from the Comparative Toxicogenomics Database (CTDbase). Our approach integrates toxicogenomics data to identify and cluster chemicals with similar molecular and phenotypic effects across diverse categories, including pesticides, pharmaceuticals, and industrial chemicals such as bisphenols and per- and poly-fluoroalkyl substances (PFAS). We validated our method by comparing CGPD Tetramer-based clusters with cumulative assessment groups (CAGs) for pesticides, demonstrating strong overlap with established groupings while identifying additional compounds relevant for risk assessment. Key examples include clusters associated with endocrine disruption and metabolic disorders.By bridging omics-derived molecular data with phenotypic and disease endpoints, this framework provides a comprehensive tool for chemical grouping and supports evidence-based regulatory decision-making, facilitating the transition to next-generation risk assessment methodologies.

pharmacology and toxicology↗

bioRxiv2021

AI for predicting chemical-effect associations at the universe level - deepFPlearn

Many chemicals are out there in our environment, and all living species are exposed. However, numerous chemicals pose risks, such as developing severe diseases, if they occur at the wrong time in the wrong place. For the majority of the chemicals, these risks are not known. Chemical risk assessment and subsequent regulation of use require efficient and systematic strategies. Lab-based methods - even if high throughput - are too slow to keep up with the pace of chemical innovation. Existing computational approaches are designed for specific chemical classes or sub-problems but not usable on a large scale. Further, the application range of these approaches is limited by the low amount of available labeled training data. We present the ready-to-use and stand-alone program deepFPlearn that predicts the association between chemical structures and effects on the gene/pathway level using a combined deep learning approach. deepFPlearn uses a deep autoencoder for feature reduction before training a deep feedforward neural network to predict the target association. We received good prediction qualities and showed that our feature compression preserves relevant chemical structural information. Using a vast chemical inventory (unlabeled data) as input for the autoencoder did not reduce our prediction quality but allowed capturing a much more comprehensive range of chemical structures. We predict meaningful - experimentally verified-associations of chemicals and effects on unseen data. deepFPlearn classifies hundreds of thousands of chemicals in seconds. We provide deepFPlearn as an open-source and flexible tool that can be easily retrained and customized to different application settings at https://github.com/yigbt/deepFPlearn. Supplementary informationSupplementary data are available at bioRxiv online. Contactjana.schor@ufz.de

bioinformatics↗

bioRxiv2019

uap: Reproducible and Robust HTS Data Analysis

BackgroundA lack of reproducibility has been repeatedly criticized in computational research. High throughput sequencing (HTS) data analysis is a complex multi-step process. For most of the steps a range of bioinformatic tools is available and for most tools manifold parameters need to be set. Due to this complexity, HTS data analysis is particularly prone to reproducibility and consistency issues. We have defined four criteria that in our opinion ensure a minimal degree of reproducible research for HTS data analysis. A series of workflow management systems is available for assisting complex multi-step data analyses. However, to the best of our knowledge, none of the currently available work flow management systems satisfies all four criteria for reproducible HTS analysis.\n\nResultsHere we present uap, a workflow management system dedicated to robust, consistent, and reproducible HTS data analysis. uap is optimized for the application to omics data, but can be easily extended to other complex analyses. It is available under the GNU GPL v3 license at https://github.com/yigbt/uap.\n\nConclusionsuap is a freely available tool that enables researchers to easily adhere to reproducible research principles for HTS data analyses.

bioinformatics↗