diff --git a/Arabidopsis/Lasky2016/FullData.rds b/Arabidopsis/Lasky2016/FullData.rds
new file mode 100644
index 0000000..7d0873f
Binary files /dev/null and b/Arabidopsis/Lasky2016/FullData.rds differ
diff --git a/Arabidopsis/Lasky2016/Lasky2016Processing.R b/Arabidopsis/Lasky2016/Lasky2016Processing.R
new file mode 100644
index 0000000..d076032
--- /dev/null
+++ b/Arabidopsis/Lasky2016/Lasky2016Processing.R
@@ -0,0 +1,56 @@
+AccClim <- read.csv("~/Downloads/SOO/Lasky2012/AccessionClimateData.csv")
+AccClim$ecotype_id <- paste0("X", AccClim$ecotype_id)
+
+CommClim <- read.csv("~/Downloads/SOO/Lasky2012/CommonGard_Clim.csv")
+Pheno <- read.csv("~/Downloads/SOO/Fournier-Level.csv")
+Pheno$ecotype_id <- paste0("X", Pheno$ecotype_id)
+SNPs <- read.csv("~/Downloads/SOO/call_method_75/call_method_75_TAIR9.csv", header = T, skip = 1)
+
+AccClim <- AccClim[AccClim$ecotype_id %in% Pheno$ecotype_id ,] #114
+Pheno <- Pheno[Pheno$ecotype_id %in% AccClim$ecotype_id ,] #137 accessions
+
+SeqIndx <- which(colnames(SNPs) %in% Pheno$ecotype_id)
+SNPs <- SNPs[c(1,2, SeqIndx)]
+
+#Order the Phenotypes, Climate data and SNPs by ecotype ID
+Pheno <- Pheno[match(colnames(SNPs[3:ncol(SNPs)]), Pheno$ecotype_id) ,]
+AccClim <- AccClim[match(colnames(SNPs[3:ncol(SNPs)]), AccClim$ecotype_id) ,]
+
+dim(Pheno); dim(AccClim); dim(SNPs)
+
+
+#Recode SNPs
+SNPinfo <- SNPs[1:2]
+SNPs <- t(SNPs[3:ncol(SNPs)])
+
+#Recode ATCG with 0,1,2
+#minor allele gets coded as 0, major coded as 2
+SNPmat <- matrix(0, ncol = ncol(SNPs), nrow = nrow(SNPs))
+for (i in 1:ncol(SNPs)){
+  tmpCnts <- table(SNPs[,i])
+  MajAllele <- names(tmpCnts[which(tmpCnts == max(tmpCnts))])
+  MinAllele <- names(tmpCnts[which(tmpCnts == min(tmpCnts))])
+  SNPmat[which(SNPs[,i] %in% MajAllele),i] <- 2
+  SNPmat[which(SNPs[,i] %in% MinAllele),i] <- 0
+}
+colnames(SNPmat) <- colnames(SNPs)
+row.names(SNPmat) <- row.names(SNPs)
+
+#filter low MAF (0.1) SNPs
+freq <- colMeans(SNPmat) / 2
+maf <- ifelse(freq > 0.5, 1-freq, freq)
+maf.index <- which(maf < 0.1)
+length(maf.index)
+
+SNPmat <- SNPmat[, -maf.index] #137 x 200682
+SNPinfo <- SNPinfo[-maf.index ,] #200682 x 2
+
+dim(SNPmat); dim(SNPinfo) #114 168407
+
+FullData <- list(SNPmat = SNPmat,
+                 MAP = SNPinfo,
+                 AccessionClimData = AccClim,
+                 CommonGardenClimData = CommClim,
+                 Phenotypes = Pheno)
+
+saveRDS(FullData, "~/Downloads/SOO/FullData.rds")
diff --git a/Arabidopsis/Lasky2016/README.md b/Arabidopsis/Lasky2016/README.md
new file mode 100644
index 0000000..a5b1f87
--- /dev/null
+++ b/Arabidopsis/Lasky2016/README.md
@@ -0,0 +1,4 @@
+# Lasky 2016
+This is a dataset from Jesse Lasky's 2016 [paper](https://onlinelibrary.wiley.com/doi/abs/10.1111/1755-0998.12714) that describes an approach to synthesize data from common garden and genome–environment associations to infer SNP effects for local adaptation. The paper uses data from [Fournier-Level et al 2011](https://science.sciencemag.org/content/334/6052/86), [Handcock et al (2012)](https://science.sciencemag.org/content/334/6052/83), and [Horton et al (2012)](https://www.nature.com/articles/ng.1042). I have taken these data and selected accessions that have phenotypic information, climate data at their collection sites, and genotypic data. The .Rds file contains all these data. 
+SNPs were obtained from [here](http://bergelson.uchicago.edu/wp-content/uploads/2015/04/call_method_75.tar.gz)
+Phenotypic and climate data were accessed from [here](https://onlinelibrary.wiley.com/doi/abs/10.1111/1755-0998.12714)
diff --git a/README.md b/README.md
index d52945a..e792ec5 100644
--- a/README.md
+++ b/README.md
@@ -15,3 +15,5 @@ The directories and contents are listed below.
 	* NGR
 		* Olatoye_2018
 	
+* Arabidopsis
+  	* Lasky 2016