Silverstein, J. | bioRxiv Science

bioRxiv2026

BiomarkerKB: FAIR and Integrated Biomarker Knowledge Connecting Biomolecular and Clinical Data Types

Biomarkers are essential tools for disease detection, risk assessment, therapeutic monitoring, and precision medicine. However, biomarker data are dispersed across heterogeneous resources, inconsistently reported in the literature, and rarely standardized for computational use. This fragmentation limits reproducibility, cross-study integration, and the discovery of novel biomarker and disease relationships. We developed BiomarkerKB, a knowledgebase designed to harmonize and integrate biomarker information under a standardized data model. The model follows the FDA-NIH BEST biomarker definition and captures both core fields (biomarker entity, disease/condition, exposure agent) and contextual metadata (specimen, biomarker role, evidence, provenance). Biomarker data and related annotations were either curated from publications or collected from public resources (e.g., OpenTargets, GWAS Catalog, ClinVar, CIViC, OncoMX) and were also contributed by the Common Fund Data Coordinating Centers and the Early Detection Research Network (EDRN). Standardization was achieved using ontologies and reference resources such as Disease Ontology, UBERON, UniProtKB, and HUGO Gene Nomenclature Committee (HGNC) gene symbols. BiomarkerKB data were ingested into a Neo4j-based knowledge graph and integrated with the Common Fund Data Ecosystem (CFDE) Knowledge Graph. The initial release of BiomarkerKB contains over 200,000 biomarker-disease associations spanning genes, proteins, metabolites, glycans, and chemical elements. The knowledge graph comprises more than 300,000 nodes and 1.2 million edges, enabling structured exploration of biomarker relationships within CFDE data as demonstrated through the knowledge graph query-based use cases presented in this study. A publicly accessible web portal (https://biomarkerkb.org) provides keyword search, filtering, data downloads, and access to graph visualization to support both researchers and computational analyses. BiomarkerKB addresses a critical gap in biomarker informatics by providing an integrated, FAIR (Findable, Accessible, Interoperable, and Reusable), and unified framework for biomarker knowledge exploration and discovery.

bioinformatics↗

bioRxiv2018

Predicting response to motor therapy in chronic stroke patients using Machine Learning

Accurate predictions of motor improvement resulting from intensive therapy in chronic stroke patients is a difficult task for clinicians, but is key in prescribing appropriate therapeutic strategies. Statistical methods, including machine learning, are a highly promising avenue with which to improve prediction accuracy in clinical practice. The first main objective of this study was to use machine learning methods to predict a chronic stroke individuals motor function improvement after 6 weeks of intervention using pre-intervention demographic, clinical, neurophysiological and imaging data. The second main objective was to identify which data elements were most important in predicting chronic stroke patients impairment after 6 weeks of intervention. Data from one hundred and two patients (Female: 31%, age 61{+/-}11 years) who suffered first ischemic stroke 3-12 months prior were included in this study. After enrollment, patients underwent 6 weeks of intensive motor and transcranial magnetic stimulation therapy. Age, gender, handedness, time since stroke, pre-intervention Fugl-Meyer Assessment, stroke lateralization, the difference in motor threshold between the unaffected and affected hemispheres, absence or presence of motor evoked potential in the affected hemisphere and various imaging metrics were used as predictors of post-intervention Fugl-Meyer Assessment. Five machine learning methods, including Elastic-Net, Support Vector Machines, Artificial Neural Networks, Classification and Regression Trees, and Random Forest, were used to predict post-intervention Fugl-Meyer Assessment based on either demographic, clinical and neurophysiological data alone or in combination with the imaging metrics. Cross-validated R-squared and root of mean squared error were used to assess the prediction accuracy and compare the performance of methods. Elastic-Net performed significantly better than the other methods for the model containing pre-intervention Fugl-Meyer Assessment, demographic, clinical and neurophysiological data as predictors of post-intervention Fugl-Meyer Assessment ([Formula]). Pre-intervention Fugl-Meyer Assessment and difference in motor threshold between affected and unaffected hemispheres were commonly found as the strongest two predictors in the clinical model. The difference in motor threshold had greater importance than the absence or presence of motor evoked potential in the affected hemisphere. The various imaging metrics, including lesion overlap with the spinal cord, largely did not improve the model performance. The approach implemented here may enable clinicians to more accurately predict a chronic stroke patients individual response to intervention. The predictive models used in this study could assist clinicians in making treatment decisions and improve the accuracy of prognosis in chronic stroke patients.

neuroscience↗