Joram Matthias Posma

Relation Extraction for Diet, Non-Communicable Disease and Biomarker Associations (RECoDe): A CoDiet study

The paper introduces RECoDe, a relation extraction dataset for diet, disease, and biomarker associations, and benchmarks NLP models on it, achieving high classification performance.

Microbial Named Entity Recognition and Normalisation for AI-assisted Literature Review and Meta-Analysis

The paper develops deep learning models for microbial named entity recognition and normalization to accelerate literature review and meta-analysis of microbiome studies.

A META-ANALYSIS OF GUT MICROBIOME RESEARCH IN MALNOURISHED AFRICAN POPULATIONS: A NATURAL LANGUAGE PROCESSING APPROACH

This paper uses NLP to analyze gut microbiome studies in malnourished African children, identifying microbial signatures and associations with malnutrition.

Biomedical text corpora for multi-entity recognition in diet-related metabolic syndrome research

The paper introduces five biomedical corpora for multi-entity recognition in metabolic syndrome research, including human-annotated and machine-annotated datasets with diverse entity categories.

Topological embedding and directional feature importance in ensemble classifiers for multi-class classification

The paper introduces a directional feature importance metric for decision tree classifiers and evaluates its performance on cancer proteomics data using multiple algorithms.

Vocabulary Matters: An Annotation Pipeline and Two Deep Learning Algorithms for Enzyme Named Entity Recognition

This paper develops an annotation pipeline and two deep learning models for enzyme named entity recognition, achieving high performance with SciBERT-BiLSTM outperforming BioBERT-BiLSTM.

LAVASET: Latent Variable Stochastic Ensemble of Trees. A novel ensemble method for correlated datasets.

LAVASET improves feature importance estimation in correlated datasets by incorporating correlation factors, achieving non-inferior prediction accuracy compared to Random Forests.

MetaboListem and TABoLiSTM: Two Deep Learning Algorithms for Metabolite Named Entity Recognition

This paper introduces two deep learning models for metabolite named entity recognition and provides a corpus for metabolomics text-mining tasks.

Auto-CORPus: A Natural Language Processing Tool for Standardising and Reusing Biomedical Literature

Auto-CORPus converts biomedical publication HTML and tables to standardized formats for text analytics.

A network-based data-mining approach to investigate indole-related microbiota-host co-metabolism

The paper identifies prokaryotes involved in indole metabolism using KEGG and BLAST integration, and provides resources for further validation.