#install.packages("matR", repo="http://dunkirk.mcs.anl.gov/~braithwaite/R", type="source")
library(matR)
#install.packages("RJSONIO")
library(RJSONIO)
setwd("/Users/metagenomics/Desktop/Ryan co-occurrence code/revision_work/")
msession$setAuth("")


body.data<-c(Sample1="4456844.3",
Sample2="4456777.3",
Sample3="4456720.3",
Sample4="4456744.3",
Sample5="4456753.3",
Sample6="4456853.3",
Sample7="4456760.3",
Sample8="4456695.3",
Sample9="4456705.3",
Sample10="4456739.3",
Sample11="4456724.3",
Sample12="4456881.3",
Sample13="4456793.3",
Sample14="4456696.3",
Sample15="4456737.3",
Sample16="4456867.3",
Sample17="4456776.3",
Sample18="4456854.3",
Sample19="4456788.3",
Sample20="4456730.3",
Sample21="4456798.3",
Sample22="4456803.3",
Sample23="4456813.3",
Sample24="4456714.3",
Sample25="4456709.3",
Sample26="4456810.3",
Sample27="4456823.3",
Sample28="4456770.3",
Sample29="4456715.3",
Sample30="4456771.3",
Sample31="4456746.3",
Sample32="4456712.3",
Sample33="4456828.3",
Sample34="4456839.3",
Sample35="4456758.3",
Sample36="4456708.3",
Sample37="4456778.3",
Sample38="4456780.3",
Sample39="4456845.3",
Sample40="4456686.3",
Sample41="4456878.3",
Sample42="4456785.3",
Sample43="4456680.3",
Sample44="4456872.3",
Sample45="4456859.3",
Sample46="4456743.3",
Sample47="4456762.3",
Sample48="4456707.3",
Sample49="4456861.3",
Sample50="4456773.3",
Sample51="4456794.3",
Sample52="4456718.3",
Sample53="4456838.3",
Sample54="4456819.3",
Sample55="4456775.3",
Sample56="4456875.3",
Sample57="4456670.3",
Sample58="4456873.3",
Sample59="4456669.3",
Sample60="4456691.3",
Sample61="4456710.3",
Sample62="4456827.3",
Sample63="4456706.3",
Sample64="4456864.3",
Sample65="4456688.3",
Sample66="4456874.3",
Sample67="4456748.3",
Sample68="4456761.3",
Sample69="4456855.3",
Sample70="4456812.3",
Sample71="4456784.3",
Sample72="4456816.3",
Sample73="4456721.3",
Sample74="4456682.3",
Sample75="4456809.3",
Sample76="4456764.3",
Sample77="4456862.3",
Sample78="4456824.3",
Sample79="4456825.3",
Sample80="4456781.3",
Sample81="4456672.3",
Sample82="4456840.3",
Sample83="4456741.3",
Sample84="4456759.3",
Sample85="4456866.3",
Sample86="4456687.3",
Sample87="4456722.3",
Sample88="4456835.3",
Sample89="4456738.3",
Sample90="4456786.3",
Sample91="4456698.3",
Sample92="4456694.3",
Sample93="4456868.3",
Sample94="4456683.3",
Sample95="4456674.3",
Sample96="4456787.3",
Sample97="4456774.3",
Sample98="4456791.3",
Sample99="4456804.3",
Sample100="4456805.3",
Sample101="4456750.3",
Sample102="4456848.3",
Sample103="4456820.3",
Sample104="4456717.3",
Sample105="4456818.3",
Sample106="4456685.3",
Sample107="4456832.3",
Sample108="4456701.3",
Sample109="4456789.3",
Sample110="4456697.3",
Sample111="4456801.3",
Sample112="4456811.3",
Sample113="4456817.3",
Sample114="4456797.3",
Sample115="4456734.3",
Sample116="4456846.3",
Sample117="4456808.3",
Sample118="4456727.3",
Sample119="4456869.3",
Sample120="4456826.3",
Sample121="4456700.3",
Sample122="4456735.3",
Sample123="4456837.3",
Sample124="4456858.3",
Sample125="4456865.3",
Sample126="4456831.3",
Sample127="4456768.3",
Sample128="4456870.3",
Sample129="4456857.3",
Sample130="4456836.3",
Sample131="4456728.3",
Sample132="4456755.3",
Sample133="4456745.3",
Sample134="4456830.3",
Sample135="4456843.3",
Sample136="4456880.3",
Sample137="4456792.3",
Sample138="4456863.3",
Sample139="4456767.3",
Sample140="4456740.3",
Sample141="4456690.3",
Sample142="4456713.3",
Sample143="4456799.3",
Sample144="4456704.3",
Sample145="4456815.3",
Sample146="4456847.3",
Sample147="4456766.3",
Sample148="4456729.3",
Sample149="4456860.3",
Sample150="4456829.3",
Sample151="4456877.3",
Sample152="4456731.3",
Sample153="4456751.3",
Sample154="4456763.3",
Sample155="4456779.3",
Sample156="4456852.3",
Sample157="4456790.3",
Sample158="4456742.3",
Sample159="4456765.3",
Sample160="4456782.3",
Sample161="4456871.3",
Sample162="4456849.3",
Sample163="4456678.3",
Sample164="4456668.3",
Sample165="4456676.3",
Sample166="4456732.3",
Sample167="4456800.3",
Sample168="4456692.3",
Sample169="4456796.3",
Sample170="4456807.3",
Sample171="4456711.3",
Sample172="4456879.3",
Sample173="4456679.3",
Sample174="4456747.3",
Sample175="4456822.3",
Sample176="4456689.3",
Sample177="4456850.3",
Sample178="4456736.3",
Sample179="4456733.3",
Sample180="4456756.3",
Sample181="4456677.3",
Sample182="4456681.3",
Sample183="4456821.3",
Sample184="4456802.3",
Sample185="4456673.3",
Sample186="4456723.3",
Sample187="4456876.3",
Sample188="4456699.3",
Sample189="4456671.3",
Sample190="4456772.3",
Sample191="4456851.3",
Sample192="4456703.3",
Sample193="4456749.3",
Sample194="4456834.3",
Sample195="4456716.3",
Sample196="4456842.3",
Sample197="4456693.3",
Sample198="4456795.3",
Sample199="4456814.3",
Sample200="4456725.3",
Sample201="4456754.3",
Sample202="4456833.3",
Sample203="4456719.3",
Sample204="4456702.3",
Sample205="4456675.3",
Sample206="4456806.3",
Sample207="4456769.3",
Sample208="4456752.3",
Sample209="4456726.3",
Sample210="4456856.3",
Sample211="4456841.3",
Sample212="4456684.3",
Sample213="4456757.3",
Sample214="4456783.3"
)
#three different pulls from MGRAST here for each level of organization
cc.order<-collection(body.data, Order=c(entry="counts",annot="organism",level="order",source="M5RNA"))
cc.family<-collection(body.data, Family=c(entry="counts",annot="organism",level="family",source="M5RNA"))
cc.genus<-collection(body.data, Genus=c(entry="counts",annot="organism",level="genus",source="M5RNA"))

#try to figure out how to pull this data more appropriately from cc.order
mm.order<-metadata(cc.order)
write.csv(as.matrix(mm.order["original_sample",bygroup=TRUE]), "body_data_sample_info1.csv")
write.csv(as.matrix(mm[.order"host_individual",bygroup=TRUE]), "body_data_sample_info2.csv")
data.body.table<-t(cc.order$Order)
head(data.body.table)

write.csv(data.body.table, "body_data_order.csv")



####lauber soils###

soil.data<-c(Sample1="mgm4455737.3",
Sample2="mgm4455738.3",
Sample3="mgm4455739.3",
Sample4="mgm4455740.3",
Sample5="mgm4455741.3",
Sample6="mgm4455742.3",
Sample7="mgm4455743.3",
Sample8="mgm4455744.3",
Sample9="mgm4455745.3",
Sample10="mgm4455746.3",
Sample11="mgm4455747.3",
Sample12="mgm4455748.3",
Sample13="mgm4455749.3",
Sample14="mgm4455750.3",
Sample15="mgm4455751.3",
Sample16="mgm4455752.3",
Sample17="mgm4455753.3",
Sample18="mgm4455754.3",
Sample19="mgm4455755.3",
Sample20="mgm4455756.3",
Sample21="mgm4455757.3",
Sample22="mgm4455758.3",
Sample23="mgm4455759.3",
Sample24="mgm4455760.3",
Sample25="mgm4455761.3",
Sample26="mgm4455762.3",
Sample27="mgm4455763.3",
Sample28="mgm4455764.3",
Sample29="mgm4455765.3",
Sample30="mgm4455766.3",
Sample31="mgm4455767.3",
Sample32="mgm4455769.3",
Sample33="mgm4455770.3",
Sample34="mgm4455771.3",
Sample35="mgm4455772.3",
Sample36="mgm4455773.3",
Sample37="mgm4455774.3",
Sample38="mgm4455775.3",
Sample39="mgm4455776.3",
Sample40="mgm4455777.3",
Sample41="mgm4455778.3",
Sample42="mgm4455779.3",
Sample43="mgm4455780.3",
Sample44="mgm4455781.3",
Sample45="mgm4455782.3",
Sample46="mgm4455783.3",
Sample47="mgm4455784.3",
Sample48="mgm4455785.3",
Sample49="mgm4455786.3",
Sample50="mgm4455787.3",
Sample51="mgm4455788.3",
Sample52="mgm4455789.3",
Sample53="mgm4455790.3",
Sample54="mgm4455791.3",
Sample55="mgm4455792.3",
Sample56="mgm4455793.3",
Sample57="mgm4455794.3",
Sample58="mgm4455795.3",
Sample59="mgm4455796.3",
Sample60="mgm4455797.3",
Sample61="mgm4455798.3",
Sample62="mgm4455799.3",
Sample63="mgm4455800.3",
Sample64="mgm4455801.3",
Sample65="mgm4455802.3",
Sample66="mgm4455803.3",
Sample67="mgm4455804.3",
Sample68="mgm4455805.3",
Sample69="mgm4455806.3",
Sample70="mgm4455807.3",
Sample71="mgm4455808.3",
Sample72="mgm4455809.3",
Sample73="mgm4455810.3",
Sample74="mgm4455811.3",
Sample75="mgm4455812.3",
Sample76="mgm4455813.3",
Sample77="mgm4455814.3",
Sample78="mgm4455815.3",
Sample79="mgm4455816.3",
Sample80="mgm4455817.3",
Sample81="mgm4455818.3",
Sample82="mgm4455819.3",
Sample83="mgm4455820.3",
Sample84="mgm4455821.3",
Sample85="mgm4455822.3",
Sample86="mgm4455823.3",
Sample87="mgm4455824.3",
Sample88="mgm4455825.3"
)

cc<-collection(soil.data, Order=c(entry="counts",annot="organism",level="order",source="M5RNA"),
	Family=c(entry="counts",annot="organism",level="family",source="M5RNA"),
	Genus=c(entry="counts",annot="organism",level="genus",source="M5RNA"))
mm<-metadata(cc)
as.matrix(mm)
data.soil.table<-t(cc$Order)
write.csv(as.matrix(mm["feature",bygroup=TRUE]), "lauber_soil_data_sample_info1.csv")
write.csv(data.soil.table, "lauber_soil_data_order.csv")


###apple data
apple.data<-c(Sample1="mgm4507292.3",
Sample2="mgm4507293.3",
Sample3="mgm4507294.3",
Sample4="mgm4507295.3",
Sample5="mgm4507296.3",
Sample6="mgm4507297.3",
Sample7="mgm4507298.3",
Sample8="mgm4507299.3",
Sample9="mgm4507300.3",
Sample10="mgm4507301.3",
Sample11="mgm4507302.3",
Sample12="mgm4507303.3",
Sample13="mgm4507304.3",
Sample14="mgm4507305.3",
Sample15="mgm4507443.3",
Sample16="mgm4507444.3",
Sample17="mgm4507445.3",
Sample18="mgm4507446.3",
Sample19="mgm4507447.3",
Sample20="mgm4507448.3",
Sample21="mgm4507306.3",
Sample22="mgm4507307.3",
Sample23="mgm4507449.3",
Sample24="mgm4507450.3",
Sample25="mgm4507308.3",
Sample26="mgm4507309.3",
Sample27="mgm4507310.3",
Sample28="mgm4507311.3",
Sample29="mgm4507312.3",
Sample30="mgm4507451.3"
)
cc<-collection(apple.data, Order=c(entry="counts",annot="organism",level="order",source="M5RNA"))
data.apple.table<-t(cc$Order)
mm<-metadata(cc)
as.matrix(mm)
write.csv(as.matrix(mm["air_temp_regm",bygroup=TRUE]), "apple_data_sample_info1.csv")
write.csv(data.apple.table, "apple_data_order.csv")


total.data<-c(body.data,soil.data,apple.data)
cc<-collection(total.data, Order=c(entry="counts",annot="organism",level="order",source="M5RNA"))
data.total.table<-t(cc$Order)
write.csv(data.total.table, "total_data_order.csv")