Faster and more accurate pathogenic combination predictions with VarCoPP2.0

BMC Bioinformatics

Table 1 Set of features that were considered during the creation of VarCoPP2.0

Feature	Feature abbreviation	Feature description	PMID	Version
CADD raw score	CADD1	CADD score variant 1 of gene A	24487276	CADDv1.6
	CADD2	CADD score variant 2 of gene A
	CADD3	CADD score variant 1 of gene B
	CADD4	CADD score variant 2 of gene B
Haploinsufficiency prediction	HIPred_A	HIPred of gene A	28137713	N.A.
	HIPred_B	HIPred of gene B
	ISPP_AD_A	ISPP prediction for AD mode of inheritance for gene A	27354691	N.A.
	ISPP_AD_B	ISPP prediction for AD mode of inheritance for gene B
Inheritance mode specific	ISPP_AR_A	ISPP prediction for AR mode of inheritance for gene A
pathogenicity prediction	ISPP_AR_B	ISPP prediction for AR mode of inheritance for gene B
	ISPP_XL_A	ISPP prediction for XL mode of inheritance for gene B
	ISPP_XL_B	ISPP prediction for XL mode of inheritance for gene B
Selection Pressure (dN/dS)	dN_dS_A	Selection pressure for gene A	26896847	v99
	dN_dS_B	Selection pressure for gene B
Biological distance	Biol_Dist	Biological distance between gene A and gene B	24694260	v12.2015
Coexpression	Coexp	Coexpression value between gene A and gene B	30462320	COXPRESdbv8.0
	BP_sim	Biological Process similarity	10802651	GO release 2021-12-15
Gene ontology similarity	MF_sim	Molecular Function similarity	18460186
	CC_sim	Cellular Component similarity
Knowledge Graph distance	KG_distance	Distance between gene A and gene B in		N.A.
		an in-house developed knowledge graph

Abbreviations as used in the data files for respective features can be found in the Feature abbreviation column. The PMID column provides the PMID of the relevant citation for each feature. The version of each feature used in this work is listed in the Version column. Features that are selected in the final model are marked in bold

ISSN: 1471-2105