Automated Extraction of Protein Mutation Impacts from the Biomedical Literature

Mutations as sources of evolution have long been the focus of attention in the
\nbiomedical literature. Accessing the mutational information and their impacts
\non protein properties facilitates research in various domains, such as
\nenzymology and pharmacology. However, manually reading through the rich and fast growing repository
\nof biomedical literature is expensive and time-consuming. A number of manually curated
\ndatabases, such as BRENDA (http://www.brenda-enzymes.org), try to index and provide this
\ninformation; yet the provided data seems to be incomplete. Thus, there is a
\ngrowing need for automated approaches to extract this information.
\nIn this work, we present a system to automatically extract and summarize impact
\ninformation from protein mutations.
\nOur system extraction module is split into subtasks: organism analysis,
\nmutation detection, protein property extraction and impact
\nanalysis. Organisms, as sources of proteins, are required to be extracted to
\nhelp disambiguation of genes and proteins. Thus, our system extracts and
\ngrounds organisms to NCBI. We detect mutation series to correctly ground our detected
\nimpacts. Our system also extracts the affected protein properties as well as the magnitude of the
\neffects.
\nThe output of our system is populated to an OWL-DL ontology, which can then be queried to provide structured information. The performance
\n of the system is evaluated on both external and internal corpora and
\n databases. The results show the reliability of the approaches. Our Organism
\n extraction system achieves a precision and recall of 95%
\nand 94% and a grounding accuracy of 97.5% on the OT corpus. On the manually
\nannotated corpus of Linneaus-100, the results show a precision and recall of
\n99% and 97% and grounding with an accuracy of 97.4%.
\nIn the impact detection task, our system achieves a precision and recall of
\n70.4%-71.8% and 71.2%-71.3% on a manually annotated documents. Our system grounds the detected
\nimpacts with an accuracy of 70.1%-71.7% on the manually annotated documents
\nand a precision and recall of 57%-57.5% and 82.5%-84.2% against the BRENDA data.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.