Back

PhenoScore: AI-based phenomics to quantify rare disease and genetic variation

Dingemans, A. J. M.; Hinne, M.; Truijen, K. M. G.; Goltstein, L.; van Reeuwijk, J.; de Leeuw, N.; Schuurs-Hoeijmakers, J.; Pfundt, R.; Diets, I. J. M.; den Hoed, J.; de Boer, E.; Coenen-van der Spek, J.; Jansen, S.; van Bon, B. W.; Jonis, N.; Ockeloen, C.; Vulto-van Silfhout, A. T.; Kleefstra, T.; Koolen, D. A.; Campeau, P. M.; Palmer, E. E.; Van Esch, H.; Lyon, G. J.; Alkuraya, F. S.; Rauch, A.; Marom, R.; Baralle, D.; van der Sluijs, P. J.; Santen, G. W. E.; Kooy, R. F.; van Gerven, M. A. J.; Vissers, L. E. L. M.; de Vries, B. B. A.

2022-10-26 genetic and genomic medicine
10.1101/2022.10.24.22281480 medRxiv
Show abstract

While both molecular and phenotypic data are essential when interpreting genetic variants, prediction scores (CADD, PolyPhen, and SIFT) have focused on molecular details to evaluate pathogenicity -- omitting phenotypic features. To unlock the full potential of phenotypic data, we developed PhenoScore: an open source, artificial intelligence-based phenomics framework. PhenoScore combines facial recognition technology with Human Phenotype Ontology (HPO) data analysis to quantify phenotypic similarity at both the level of individual patients as well as of cohorts. We prove PhenoScores ability to recognize distinct phenotypic entities by establishing recognizable phenotypes for 25 out of 26 investigated genetic syndromes against clinical features observed in individuals with other neurodevelopmental disorders. Moreover, PhenoScore was able to provide objective clinical evidence for two distinct ADNP-related phenotypes, that had already been established functionally, but not yet phenotypically. Hence, PhenoScore will not only be of use to unbiasedly quantify phenotypes to assist genomic variant interpretation at the individual level, such as for reclassifying variants of unknown clinical significance, but is also of importance for detailed genotype-phenotype studies.

Matching journals

The top 8 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.