Back

DALSO: domain ALS ontology

Podsiadly-Marczykowska, T.; Andersen, P. M.; Silva, M. G.; Grosskreutz, J.; Kuzma-Kozakiewicz, M.; Petri-Mals, S.; Szacka, K.; Uysal, H.; de Carvalho, M.; Piotrkiewicz, M.

2024-06-03 neurology
10.1101/2024.06.01.24308128 medRxiv
Show abstract

Amyotrophic lateral sclerosis (ALS) is an incurable, rapidly progressive neurodegenerative disease. During the course of ALS, virtually all skeletal muscles are gradually affected, including the respiratory muscles, and the disease is usually fatal within 2-5 years of symptom onset. Unequivocal and conclusive tests for ALS do not exist, its disease etiology is still unknown, and therapeutic options are limited. This paper presents the ALS domain ontology (DALSO), model containing formalized, semantic descriptions of a wide range of modeled disease related notions such as patient demographics, clinical findings and history, disease clinical features and diagnostic classifications, risk factors, genetics and pathophysiological mechanisms of motor neuron degeneration. The DALSOs aim and information scope, design assumption, structure and implementation details are also described. DALSO covers the broad range of significant biomedical concepts ranging from clinical to molecular feature of the modeled disease, it represents a comprehensive, structured knowledge source for the ALS disease domain. To the best of authors knowledge, the DALSO is the first attempt to develop a formal, computational model representing knowledge of this fatal motor neuron disease. It provides the means for integrating and annotating clinical and research data, not only at the generic domain knowledge level, but also at the level of individual patient case studies. The DALSO is expressed in OWL2 language, contains 910 classes, is consistent and free of logical errors. Its syntactic correctness was validated by the Fact++ reasoner.

Matching journals

The top 12 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.