Prediction of Drosophila melanogaster gene function using Support Vector Machines

Mitsakakis, Nicholas; Razak, Zak; Escobar, Michael; Westwood, J Timothy

doi:10.1186/1756-0381-6-8

BioData Mining

Table 2 Gene Lists and Fluorescent In Situ Hybridization (FISH) analysis for DNA‐dependent DNA replication GO‐BP category

From: Prediction of Drosophila melanogaster gene function using Support Vector Machines

GeneID	Sample	FISH	Gene	Prob.	GeneID	Sample	FISH	Gene	Prob.
		match	prec.	score			match	prec.	score
CG5924	LD38710		0.923	0.705	CG1109	LD26389		0.798	0.592
CG1109	LD27350		0.923	0.736	CG8290	LD37351	+	0.798	0.575
CG7663	LD46979	+	0.923	0.724	CG2910	GH11110		0.798	0.598
CG7384	LD46023		0.923	0.76	CG10364	LD32040	-	0.798	0.58
CG14464	LD29015		0.923	0.707	CG5877	LD29352		0.79	0.572
CG16892	LD26813	+	0.923	0.728	CG10625	LD39545	-	0.79	0.568
CG1578	LD28359	+	0.923	0.755	CG17509	GH12788		0.787	0.568
CG16892	LD42637		0.923	0.739	CG11409	LD40802		0.787	0.607
CG11122	LD29040		0.86	0.644	CG30007	LD29335		0.787	0.58
CG9300	LD21924		0.86	0.666	CG17681	LD30009		0.787	0.573
CG3287	SD03445		0.86	0.643	CG18622	LD26416		0.787	0.539
CG1960	GH21591		0.86	0.66	CG31152	LD29477	+	0.787	0.545
CG1024	LD28076		0.86	0.652	CG11990	LD47989	+	0.787	0.549
CG13096	SD03546		0.86	0.664	CG6724	LD40657		0.783	0.589
CG11596	LD45925		0.86	0.682	CG32069	LD47413		0.783	0.565
CG4857	LD29423	+	0.86	0.638	CG2962	LD27487		0.783	0.578
CG4949	LD46305	+	0.86	0.669	CG6049	LD27763		0.776	0.558
CG11943	SD04935		0.86	0.703	CG2260	LD30339		0.772	0.563
CG2469	LD30285	+	0.86	0.677	CG3735	LD35854		0.771	0.553
CG11596	LD42227	+	0.839	0.66	CG7110	LD39933	-	0.771	0.577
CG12785	LD27528		0.839	0.616	CG12202	LD30511	+	0.771	0.584
CG11329	LD26217		0.839	0.619	CG9591	LD26057	+	0.771	0.554
CG6066	LD27582		0.839	0.621	CG12340	LD26050		0.771	0.552
CG17050	LD35611		0.839	0.647	CG30020	LD40262		0.771	0.549
CG18004	LD27741		0.839	0.662	CG12050	LD30416	+	0.771	0.561
CG1647	LD30287		0.839	0.591	CG6151	LD28933		0.766	0.567
CG31697	SD02518		0.839	0.618	CG14657	LD28447		0.766	0.556
CG15736	LD33780	+	0.83	0.619	CG4203	LD29184		0.761	0.537
CG2691	LD46946		0.829	0.61	CG4281	SD03946		0.76	0.548
CG7728	LD39680	+	0.812	0.592	CG14005	LD30293		0.76	0.566
CG31163	SD09611	+	0.812	0.598	CG9028	LD27194	+	0.76	0.555
CG3680	LD27862		0.81	0.63	CG7824	LD26655		0.76	0.542
CG3362	LD28544		0.81	0.595	CG7407	LD29166	-	0.758	0.548
NA ^∗	LD42550		0.81	0.612	CG3338	LD27356	+	0.756	0.524
CG11906	LD27134		0.798	0.566

^∗CG number not known
DNA‐dependent DNA replication GO‐BP category (along with oxidative phosphorylation) was selected for further biological validation using fluorescent in situ hybridization (FISH) analysis of early D. melanogaster embryos. In this table, genes that are predicted to belong to this category are shown along with information regarding their presence in the FISH database. Each of the genes (i.e. CG numbers) in the list was searched in a D. melanogaster FISH database to visually examine the spatial and temporal mRNA expression for that gene during early embryogenesis. Genes that are marked with (+) or (-) sign had images present in the database. Those that had patterns that largely matched that of known genes in the category are marked with a (+). If either their temporal or their spatial pattern did not match the known gene pattern, they are marked with (-). For each gene the “gene‐precision” score and the average probability estimate output from SVM are reported.

Back to article page

ISSN: 1756-0381

Contact us

General enquiries: journalsubmissions@springernature.com