From 37462716d1ef2b08f2835ece8b0c037fc1e71d72 Mon Sep 17 00:00:00 2001 From: aquaskyline Date: Wed, 5 Jul 2017 21:16:44 -0400 Subject: [PATCH] Update 04_study.md Modification in 04_study from '642 features' to '62 features' according to the reference Torracinta2016, by reader Ruibang Luo (Github: aquakskyline) --- sections/04_study.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sections/04_study.md b/sections/04_study.md index effdfe8..ecc48e2 100644 --- a/sections/04_study.md +++ b/sections/04_study.md @@ -703,7 +703,7 @@ from the reference as the alpha value. The neural network outputs genotype probabilities for each candidate variant. They were able to achieve better performance than GATK, a leading genotype caller, even when GATK was given information about population variation for each candidate variant. Another -method, still in its infancy, hand-developed 642 features for each candidate +method, still in its infancy, hand-developed 62 features for each candidate variant and fed these vectors into a fully connected deep neural network [@tag:Torracinta2016_deep_snp]. Unfortunately, this feature set required at least 15 iterations of software development to fine-tune, which suggests that