Research ResourceGENETIC DIAGNOSIS

AMELIE speeds Mendelian diagnosis by matching patient phenotype and genotype to primary literature

See allHide authors and affiliations

Science Translational Medicine  20 May 2020:
Vol. 12, Issue 544, eaau9113
DOI: 10.1126/scitranslmed.aau9113

You are currently viewing the editor's summary.

View Full Text

Log in to view the full text

Log in through your institution

Log in through your institution

Finding a gene in the stacks

Genetic disease diagnosis can be time-consuming because of the extensive literature searching required. To speed this process, Birgmeier et al. developed AMELIE (Automatic Mendelian Literature Evaluation), an end-to-end machine learning approach with web interface that finds relevant literature supporting the disease causality of genetic variants and their association with different clinical presentations. The pipeline also parses the literature to rank the most likely candidate causative genes that best explain a given patient’s symptoms and outperformed similar algorithms when compared side by side. AMELIE could help clinicians narrow the field of possible causative genes, shortening the time required for expert diagnosis of Mendelian diseases.

View Full Text

Stay Connected to Science Translational Medicine