Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2021.02.12.430944

FORUM: Building a Knowledge Graph from public databases and scientific literature to extract associations between chemicals and diseases

Delmas, M.·Filangi, O.·Paulhe, N.·Vinson, F.·Duperier, C.·Garrier, W.·Saunier, P.- E.·Pitarch, Y.·Jourdan, F.·Giacomoni, F.·Frainay, C.
View original source ↗Export metadata ↓

Abstract

Metabolomics studies aim at reporting a metabolic signature (list of metabolites) related to a particular experimental condition. These signatures are instrumental in the identification of biomarkers or classification of individuals, however their biological and physiological interpretation remains a challenge. Overcoming this challenge is critical when aiming to associate metabolic signatures with potential pathological outcomes. To support this task, we introduce FORUM: a Knowledge Graph (KG) providing a semantic representation of relations between chemicals and biomedical concepts, built from a federation of life science databases and scientific literature repositories. An important number of scientific articles discuss relations between chemical compounds and biomedical concepts in various contexts, from biomarkers to therapeutic uses. The extraction of these statements and their interconnection in a graph structure can thus allow us to identify and explore relations strongly supported in the scientific literature. The use of a Semantic Web framework on biological data allows us to apply ontological based reasoning to infer new relations between entities. We show that these new relations provide different levels of abstraction and could open the path to new hypotheses. We estimate the statistical relevance of each extracted relation, explicit or inferred, using an enrichment analysis, and instantiate them as new knowledge in the KG to support results interpretation/further inquiries. Beyond this result, FORUM can also provide insights into complex biological questions and the extracted information could then be used for further developments. Containing more than 8 billion triples and providing more than 8 million relations, FORUM leverages the increasing availability of linked datasets in life science and is built in agreement with FAIR principles. A web interface to browse and download the extracted relations, as well as a SPARQL endpoint to directly probe the whole FORUM knowledge graph, are available at https://forum-webapp.semantic-metabolomics.fr. The code needed to reproduce the triplestore is available at https://github.com/eMetaboHUB/Forum-DiseasesChem.

Source connections

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Delmas, M., Filangi, O., Paulhe, N., Vinson, F., Duperier, C., Garrier, W., Saunier, P.- E., Pitarch, Y., Jourdan, F., Giacomoni, F., Frainay, C.. 2021-02-16. FORUM: Building a Knowledge Graph from public databases and scientific literature to extract associations between chemicals and diseases. https://doi.org/10.1101/2021.02.12.430944

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

RoDPAA: A Robust Dissimilarity-Based Principal Angle Analysis Framework for Multi-View Microbiome Data Integration

Multiview microbiome studies profile the same participants across body sites or molecular layers, but integration is hampered by sparse, compositional data, modest sample sizes and methods that recognize only exact sharing. We present RoDPAA (Robust Dissimilarity-based Principal Angle Analysis), a framework that represents each view through any data-appropriate dissimilarity, such as Bray--Curtis, without log-ratio transformation or likelihood assumptions. RoDPAA aligns view-specific signal subspaces through principal angles, captures complete and partial sharing, and tests by permutation how many components are shared, using only eigendecomposition and little tuning. In Gaussian simulations, RoDPAA matched JIVE and MOFA given true ranks, ran faster and alone recovered the shared dimension in every replicate. In two inflammatory bowel disease (IBD) cohorts with sparse, zero-inflated data, Bray--Curtis-based RoDPAA recovered shared structure that was stable to prevalence filtering, whereas log-ratio-based alternatives were not. Its leading microbiome--metabolome factors, learned without disease labels, were the only ones associated with IBD.

bioinformatics↗
bioRxiv2026

Deducing splicing events from transcript sets with splicelogic

Long-read RNA sequencing captures a greater proportion of full-length transcripts, enabling more accurate isoform identification, discovery of novel isoforms, and more precise differential transcript usage analysis. However, comparing transcripts, whether between conditions or between sets such as novel and annotated isoforms, yields complex isoform changes that are hard to manipulate, summarize, and visualize. This is compounded by vertical integration of some tools, where downstream analysis depends on the specific output of a particular upstream tool. To address this gap, we have developed splicelogic, an R/Bioconductor package that makes transcript-set comparisons biologically interpretable by turning them into discrete splicing events, such as exon skipping, alternative splice sites, intron retention, and alternative transcription start and end sites. We designed splicelogic to integrate easily with existing RNA-seq workflows and tools. The splicelogic functions are modular, readable, and extensible, making it easy for users to adapt core logic to their own custom scientific questions or novel splicing definitions. By obtaining interpretable splicing events from transcript changes, splicelogic enables downstream analyses, including annotation of RNA-binding protein recognition sites, alongside summary statistics and visualization. The splicelogic package is publicly available and distributed through Bioconductor.

bioinformatics↗
bioRxiv2026

Contrastive Learning Improves Generalization on M2OR Olfactory Binding Dataset

Olfaction-based biosensors stand to have profound impacts in fields such as medical diagnostics, national security, and drug discovery. A promising mode of vapor phase biodetection mimics volatile organic compound-olfactory receptor (VOC-OR) interactions with target-specific protein or peptide probes; however, lack of experimental coverage remains a core bottleneck. Current computational approaches aim to improve prediction of VOC-OR binding to reduce experimental burden, and current machine learning approaches fail to demonstrate a level of generalization that addresses current engineering challenges. Here, using the Molecular to Olfactory Dataset (M2OR) and Insect Olfactory Binding Protein Database (iOBPdb) datasets, data partitioning methods and their performance are evaluated on a neural network and contrastive learning framework on such VOC-OR binding datasets, varying: model training, architecture, and structure of the input data distribution. It was found that holding out certain chemical or proteomic motifs from the training data diminished model performance with a two layer neural network model. The model was able to generalize to state of the art performance (0.88 AUCROC) on every data split by applying a contrastive learning objective defined by shared molecular constituents and a stochastic sampler. This suggests the contrastive objective provides a strong inductive bias for neural networks to predict novel VOC-OR pairs. These findings highlight that model performance on pairwise biological interaction datasets can be inflated through identity leakage from constituent overlap, and emphasize the need for more robust evaluation protocols. Furthermore, we show contrastive regularization mitigates dataset degeneracy through enforcement of compatibility in the models latent geometry that may extend to other binder target-datasets where identity leakage confounds evaluation.

bioinformatics↗