Help

LDA score

The LDA score is the raw score computed for each gene. It is calculated using the final model and the gene-specific features.
Please refer to the article for technical details.

Probability of being AD

Probability of being AD is a probability of a given gene to be associated with autosomal dominant conditions (P(AD)).

Details of the main features

STRING_Combined: the number of interactions with AD genes of the training set from the combined score of STRING, with a confidence >500 and a maximum of 8 interactions

ExAC_pRec: probability to be intolerant to homozygous but not heterozygous loss-of-function variants as extracted from ExAC

STRING_Experimental: the number of interactions with AD genes of the training set from the experimental score of STRING, with a confidence >400 and a maximum of 3 interactions

Missense_z-score: the missense Z-score from ExAC (intolerance to missenses)

PhyloP_at_5_UTR: the average PhyloP score for mammals across the transcriptional start site (TSS) (+/- 500 bp from the actual site)

STRING_Textmining: the number of interactions with AD genes of the training set using the text-mining score of STRING, with a confidence >300 and a maximum of 3 interactors

Donor/Syn.: the ratio between the number of donor site variants and synonymous variants present in ExAC

mRNA_half-life>10h: a high mRNA half-life (>10h) in mouse embryonic stem cells