I then output the PGS results for both populations and continents so I could load them as below. There is an annoying issue where R Markdown uses UTF-8 style double quotes which I had to convert to ” below.
“`{r, results=’asis’}
cat(“Using SNP subset”, subset.note)
# Formatted data for cut and paste from knitted HTML
dump(“df_PGS”, “”)
“`
# Using SNP subset p < 5e-08
df_PGS <- structure(list(PGS_Z = c(0.5200636075001, -1.11902371997781, -1.02208247762685, -2.07651476702638, -0.302255484493313, -1.42211430460949, 1.40980466840254, 0.559582471229181, 1.09486218318298, 0.504133511124049, -0.466988474444203, 0.967393318105655, 1.69173244649728, 1.12514986737479, 1.67521351362267, 0.326979905514463, -0.310754319990793, 1.32151715857769, 0.0685786322416409, 1.14807956305697, 0.788887780341753, -0.372752615000197, 0.860232668360736, 1.3287069623234, 0.92922372898383, -0.581182512307871, -0.224925800495491, -0.764091225900405, 0.185373269728186, -0.7909882596934, 0.369592154021238, 0.248155541120252, -0.530569528552552, -1.28424949508351, -0.946197739930438, -1.72471514128299, -3.18629540939235, -1.19153830835272, 1.02634720313318, 0.338840917692266, -0.222976299902283, 0.568804159526946, 0.68520661899737, 0.40549941129595, -0.32654166812477, -0.594762957433412, 0.0515190783651431, -0.0106906814603098, 0.308741160042542, -0.246360815781283, -0.787651899184517, 0.755315367983932, -0.757312962299404), Population = c("Algeria (Mzab) – Mozabite", "Bougainville – NAN Melanesian", "Brazil – Karitiana", "Brazil – Surui", "C. African Republic – Biaka Pygmy", "Cambodia – Cambodian", "China – Dai", "China – Daur", "China – Han", "China – Hezhen", "China – Lahu", "China – Miaozu", "China – Mongola", "China – Naxi", "China – Oroqen", "China – She", "China – Tu", "China – Tujia", "China – Uygur", "China – Xibo", "China – Yizu", "Colombia – Piapoco and Curripaco", "D. R. of Congo – Mbuti Pygmy", "France – Basque", "France – French", "Israel (Carmel) – Druze", "Israel (Central) – Palestinian", "Israel (Negev) – Bedouin", "Italy – from Bergamo", "Italy – Sardinian", "Italy – Tuscan", "Japan – Japanese", "Kenya – Bantu", "Mexico – Maya", "Mexico – Pima", "Namibia – San", "New Guinea – Papuan", "Nigeria – Yoruba", "Orkney Islands – Orcadian", "Pakistan – Balochi", "Pakistan – Brahui", "Pakistan – Burusho", "Pakistan – Hazara", "Pakistan – Kalash", "Pakistan – Makrani", "Pakistan – Pathan", "Pakistan – Sindhi", "Population Set 1", "Russia – Russian", "Russia (Caucasus) – Adygei", "Senegal – Mandenka", "Siberia – Yakut", "South Africa – Bantu" )), .Names = c("PGS_Z", "Population"), row.names = c("Algeria (Mzab) – Mozabite", "Bougainville – NAN Melanesian", "Brazil – Karitiana", "Brazil – Surui", "C. African Republic – Biaka Pygmy", "Cambodia – Cambodian", "China – Dai", "China – Daur", "China – Han", "China – Hezhen", "China – Lahu", "China – Miaozu", "China – Mongola", "China – Naxi", "China – Oroqen", "China – She", "China – Tu", "China – Tujia", "China – Uygur", "China – Xibo", "China – Yizu", "Colombia – Piapoco and Curripaco", "D. R. of Congo – Mbuti Pygmy", "France – Basque", "France – French", "Israel (Carmel) – Druze", "Israel (Central) – Palestinian", "Israel (Negev) – Bedouin", "Italy – from Bergamo", "Italy – Sardinian", "Italy – Tuscan", "Japan – Japanese", "Kenya – Bantu", "Mexico – Maya", "Mexico – Pima", "Namibia – San", "New Guinea – Papuan", "Nigeria – Yoruba", "Orkney Islands – Orcadian", "Pakistan – Balochi", "Pakistan – Brahui", "Pakistan – Burusho", "Pakistan – Hazara", "Pakistan – Kalash", "Pakistan – Makrani", "Pakistan – Pathan", "Pakistan – Sindhi", "Population Set 1", "Russia – Russian", "Russia (Caucasus) – Adygei", "Senegal – Mandenka", "Siberia – Yakut", "South Africa – Bantu" ), class = "data.frame")
df_PGS <- structure(list(PGS_Z = c(-0.171877416500972, -0.76325883175675, 0.527052463582658, 1.13366534856215, 0.802379817204429, 0.0721060622819543, -2.00331924902356, 0.403251805650091), Population = c("AFRICA", "AMERICA", "CENTRAL-SOUTH ASIA", "EAST ASIA", "EUROPE", "MIDDLE EAST", "OCEANIA", "Population Set 1")), .Names = c("PGS_Z", "Population" ), row.names = c("AFRICA", "AMERICA", "CENTRAL-SOUTH ASIA", "EAST ASIA", "EUROPE", "MIDDLE EAST", "OCEANIA", "Population Set 1"), class = "data.frame")
# Using SNP subset p < 1e-30
df_PGS_pop_30 <- structure(list(PGS_Z = c(-0.22774097619992, -1.9715591510291, -0.671060706737492, 0.640248446937808, 0.498481462070653, -0.165132021585292, 1.20605525284874, 1.59005582149218, 1.5507521144634, 1.18022912859246, 0.38682595275503, 1.01660713020854, 0.622694079610597, 1.13644957931209, 0.808396343591038, 0.188319081351515, 1.12763415841273, 0.230240996196302, 0.816383059308068, 0.374866735853536, 0.656620936068732, 0.201996888194904, -0.421196361148007, -0.829255798533044, -0.637466166619254, -0.431621917284199, -0.86857201956625, -1.08538270811792, -1.77791883690442, -2.02167495788651, -0.437408949111198, 2.02081705336049, 0.22021588820191, -1.40166582744889, -0.650943749391742, -0.549937657847137, -2.65369336124334, 0.158268785377203, -0.43707246143649, 0.0229409510124096, -0.216314299709225, 0.928077501081921, 1.12058182169323, 1.20002072182299, -1.0069769085762, -0.249006441063474, -0.237998288498758, -0.0907098467875349, -1.0558649525544, -0.795996355644576, 0.335956524741878, 1.11970862227292, -0.467274315908915), Population = c("Algeria (Mzab) – Mozabite", "Bougainville – NAN Melanesian", "Brazil – Karitiana", "Brazil – Surui", "C. African Republic – Biaka Pygmy", "Cambodia – Cambodian", "China – Dai", "China – Daur", "China – Han", "China – Hezhen", "China – Lahu", "China – Miaozu", "China – Mongola", "China – Naxi", "China – Oroqen", "China – She", "China – Tu", "China – Tujia", "China – Uygur", "China – Xibo", "China – Yizu", "Colombia – Piapoco and Curripaco", "D. R. of Congo – Mbuti Pygmy", "France – Basque", "France – French", "Israel (Carmel) – Druze", "Israel (Central) – Palestinian", "Israel (Negev) – Bedouin", "Italy – from Bergamo", "Italy – Sardinian", "Italy – Tuscan", "Japan – Japanese", "Kenya – Bantu", "Mexico – Maya", "Mexico – Pima", "Namibia – San", "New Guinea – Papuan", "Nigeria – Yoruba", "Orkney Islands – Orcadian", "Pakistan – Balochi", "Pakistan – Brahui", "Pakistan – Burusho", "Pakistan – Hazara", "Pakistan – Kalash", "Pakistan – Makrani", "Pakistan – Pathan", "Pakistan – Sindhi", "Population Set 1", "Russia – Russian", "Russia (Caucasus) – Adygei", "Senegal – Mandenka", "Siberia – Yakut", "South Africa – Bantu" )), .Names = c("PGS_Z", "Population"), row.names = c("Algeria (Mzab) – Mozabite", "Bougainville – NAN Melanesian", "Brazil – Karitiana", "Brazil – Surui", "C. African Republic – Biaka Pygmy", "Cambodia – Cambodian", "China – Dai", "China – Daur", "China – Han", "China – Hezhen", "China – Lahu", "China – Miaozu", "China – Mongola", "China – Naxi", "China – Oroqen", "China – She", "China – Tu", "China – Tujia", "China – Uygur", "China – Xibo", "China – Yizu", "Colombia – Piapoco and Curripaco", "D. R. of Congo – Mbuti Pygmy", "France – Basque", "France – French", "Israel (Carmel) – Druze", "Israel (Central) – Palestinian", "Israel (Negev) – Bedouin", "Italy – from Bergamo", "Italy – Sardinian", "Italy – Tuscan", "Japan – Japanese", "Kenya – Bantu", "Mexico – Maya", "Mexico – Pima", "Namibia – San", "New Guinea – Papuan", "Nigeria – Yoruba", "Orkney Islands – Orcadian", "Pakistan – Balochi", "Pakistan – Brahui", "Pakistan – Burusho", "Pakistan – Hazara", "Pakistan – Kalash", "Pakistan – Makrani", "Pakistan – Pathan", "Pakistan – Sindhi", "Population Set 1", "Russia – Russian", "Russia (Caucasus) – Adygei", "Senegal – Mandenka", "Siberia – Yakut", "South Africa – Bantu" ), class = "data.frame")
df_PGS_cont_30 <- structure(list(PGS_Z = c(0.534009086642049, -0.207818862875531, 0.624192430205281, 1.47355288841214, -0.608538124342132, -0.258024397998142, -1.88798149112997, 0.330608471086306), Population = c("AFRICA", "AMERICA", "CENTRAL-SOUTH ASIA", "EAST ASIA", "EUROPE", "MIDDLE EAST", "OCEANIA", "Population Set 1")), .Names = c("PGS_Z", "Population" ), row.names = c("AFRICA", "AMERICA", "CENTRAL-SOUTH ASIA", "EAST ASIA", "EUROPE", "MIDDLE EAST", "OCEANIA", "Population Set 1"), class = "data.frame")
# Using SNP subset p < 1e-20
df_PGS_pop_20 <- structure(list(PGS_Z = c(0.786289242132707, -1.53926733341709, -0.282415142753057, -0.861436091656981, 0.715737084448114, -0.621032150920052, 1.01071195358365, 0.676893455546647, 1.36740374951033, 0.672415354678118, 1.40774807076906, 1.23085709241133, 1.54303815685287, 1.61726957190717, 1.36121243993766, 0.418990155927757, 1.10541795637635, 0.711390852697397, 0.408418829954349, 0.703152847230079, 0.704742905435769, -0.183833713655054, 1.34003273385856, 0.210120371586764, 0.222845196541972, -0.813324570376352, -0.412441362398562, -1.27382024839739, -0.859352341630058, -1.07915854413014, -0.0302683115662864, 1.76819650181227, 0.0458070914825576, -1.98327828188413, -1.2368391345566, -0.273867626298476, -2.35709998519742, -0.940251320839552, 0.0556024603329693, -0.439361189498476, -0.758666455784151, -0.197579706902746, 0.618366453613662, -0.234761348988804, -1.51306679241434, -1.05135377716523, -0.781881959483692, -0.140531600778617, -1.26428098899066, -0.885158365106794, -0.0578638316665617, 0.906023131624307, 0.463508516204846), Population = c("Algeria (Mzab) – Mozabite", "Bougainville – NAN Melanesian", "Brazil – Karitiana", "Brazil – Surui", "C. African Republic – Biaka Pygmy", "Cambodia – Cambodian", "China – Dai", "China – Daur", "China – Han", "China – Hezhen", "China – Lahu", "China – Miaozu", "China – Mongola", "China – Naxi", "China – Oroqen", "China – She", "China – Tu", "China – Tujia", "China – Uygur", "China – Xibo", "China – Yizu", "Colombia – Piapoco and Curripaco", "D. R. of Congo – Mbuti Pygmy", "France – Basque", "France – French", "Israel (Carmel) – Druze", "Israel (Central) – Palestinian", "Israel (Negev) – Bedouin", "Italy – from Bergamo", "Italy – Sardinian", "Italy – Tuscan", "Japan – Japanese", "Kenya – Bantu", "Mexico – Maya", "Mexico – Pima", "Namibia – San", "New Guinea – Papuan", "Nigeria – Yoruba", "Orkney Islands – Orcadian", "Pakistan – Balochi", "Pakistan – Brahui", "Pakistan – Burusho", "Pakistan – Hazara", "Pakistan – Kalash", "Pakistan – Makrani", "Pakistan – Pathan", "Pakistan – Sindhi", "Population Set 1", "Russia – Russian", "Russia (Caucasus) – Adygei", "Senegal – Mandenka", "Siberia – Yakut", "South Africa – Bantu" )), .Names = c("PGS_Z", "Population"), row.names = c("Algeria (Mzab) – Mozabite", "Bougainville – NAN Melanesian", "Brazil – Karitiana", "Brazil – Surui", "C. African Republic – Biaka Pygmy", "Cambodia – Cambodian", "China – Dai", "China – Daur", "China – Han", "China – Hezhen", "China – Lahu", "China – Miaozu", "China – Mongola", "China – Naxi", "China – Oroqen", "China – She", "China – Tu", "China – Tujia", "China – Uygur", "China – Xibo", "China – Yizu", "Colombia – Piapoco and Curripaco", "D. R. of Congo – Mbuti Pygmy", "France – Basque", "France – French", "Israel (Carmel) – Druze", "Israel (Central) – Palestinian", "Israel (Negev) – Bedouin", "Italy – from Bergamo", "Italy – Sardinian", "Italy – Tuscan", "Japan – Japanese", "Kenya – Bantu", "Mexico – Maya", "Mexico – Pima", "Namibia – San", "New Guinea – Papuan", "Nigeria – Yoruba", "Orkney Islands – Orcadian", "Pakistan – Balochi", "Pakistan – Brahui", "Pakistan – Burusho", "Pakistan – Hazara", "Pakistan – Kalash", "Pakistan – Makrani", "Pakistan – Pathan", "Pakistan – Sindhi", "Population Set 1", "Russia – Russian", "Russia (Caucasus) – Adygei", "Senegal – Mandenka", "Siberia – Yakut", "South Africa – Bantu" ), class = "data.frame")
df_PGS_cont_20 <- structure(list(PGS_Z = c(0.653893673462433, -0.730733849600686, -0.0670803805416632, 1.69027530476756, -0.0376922725492349, -0.102939430156396, -1.74614356692521, 0.3404205215432), Population = c("AFRICA", "AMERICA", "CENTRAL-SOUTH ASIA", "EAST ASIA", "EUROPE", "MIDDLE EAST", "OCEANIA", "Population Set 1")), .Names = c("PGS_Z", "Population" ), row.names = c("AFRICA", "AMERICA", "CENTRAL-SOUTH ASIA", "EAST ASIA", "EUROPE", "MIDDLE EAST", "OCEANIA", "Population Set 1"), class = "data.frame")
# Using SNP subset 1e-30 < p < 1e-20
df_PGS_pop_20_30 <- structure(list(PGS_Z = c(1.50332824545052, 0.00940525814543819, 0.379513465320102, -2.12421853700429, 0.506455789880328, -0.766008854773309, 0.101919149222941, -0.887214805243339, 0.236732431127176, -0.393669269400149, 1.72110498389014, 0.676320728858494, 1.64384563646339, 1.13206019709658, 1.13372778719622, 0.422870807910656, 0.345265036471351, 0.82728687942642, -0.360658796949194, 0.637818416914439, 0.296188301359843, -0.533147388375364, 2.60243314417584, 1.34018121526478, 1.12577531831984, -0.740171397170485, 0.418129553778085, -0.659269503141165, 0.832347387060755, 0.787548309241492, 0.48704585623588, 0.28715071020886, -0.197574598569653, -1.37846103661106, -1.13222828259139, 0.24490396224678, -0.431838742587047, -1.6583835258514, 0.620437780794498, -0.712625593701843, -0.917959936357313, -1.44133190041844, -0.405040128165086, -1.83139345145332, -1.12781816905905, -1.33409498880749, -0.927651317924142, -0.108190410703586, -0.680455708928403, -0.407089803572685, -0.500468056524642, 0.0442497400746086, 1.2929181117484), Population = c("Algeria (Mzab) – Mozabite", "Bougainville – NAN Melanesian", "Brazil – Karitiana", "Brazil – Surui", "C. African Republic – Biaka Pygmy", "Cambodia – Cambodian", "China – Dai", "China – Daur", "China – Han", "China – Hezhen", "China – Lahu", "China – Miaozu", "China – Mongola", "China – Naxi", "China – Oroqen", "China – She", "China – Tu", "China – Tujia", "China – Uygur", "China – Xibo", "China – Yizu", "Colombia – Piapoco and Curripaco", "D. R. of Congo – Mbuti Pygmy", "France – Basque", "France – French", "Israel (Carmel) – Druze", "Israel (Central) – Palestinian", "Israel (Negev) – Bedouin", "Italy – from Bergamo", "Italy – Sardinian", "Italy – Tuscan", "Japan – Japanese", "Kenya – Bantu", "Mexico – Maya", "Mexico – Pima", "Namibia – San", "New Guinea – Papuan", "Nigeria – Yoruba", "Orkney Islands – Orcadian", "Pakistan – Balochi", "Pakistan – Brahui", "Pakistan – Burusho", "Pakistan – Hazara", "Pakistan – Kalash", "Pakistan – Makrani", "Pakistan – Pathan", "Pakistan – Sindhi", "Population Set 1", "Russia – Russian", "Russia (Caucasus) – Adygei", "Senegal – Mandenka", "Siberia – Yakut", "South Africa – Bantu" )), .Names = c("PGS_Z", "Population"), row.names = c("Algeria (Mzab) – Mozabite", "Bougainville – NAN Melanesian", "Brazil – Karitiana", "Brazil – Surui", "C. African Republic – Biaka Pygmy", "Cambodia – Cambodian", "China – Dai", "China – Daur", "China – Han", "China – Hezhen", "China – Lahu", "China – Miaozu", "China – Mongola", "China – Naxi", "China – Oroqen", "China – She", "China – Tu", "China – Tujia", "China – Uygur", "China – Xibo", "China – Yizu", "Colombia – Piapoco and Curripaco", "D. R. of Congo – Mbuti Pygmy", "France – Basque", "France – French", "Israel (Carmel) – Druze", "Israel (Central) – Palestinian", "Israel (Negev) – Bedouin", "Italy – from Bergamo", "Italy – Sardinian", "Italy – Tuscan", "Japan – Japanese", "Kenya – Bantu", "Mexico – Maya", "Mexico – Pima", "Namibia – San", "New Guinea – Papuan", "Nigeria – Yoruba", "Orkney Islands – Orcadian", "Pakistan – Balochi", "Pakistan – Brahui", "Pakistan – Burusho", "Pakistan – Hazara", "Pakistan – Kalash", "Pakistan – Makrani", "Pakistan – Pathan", "Pakistan – Sindhi", "Population Set 1", "Russia – Russian", "Russia (Caucasus) – Adygei", "Senegal – Mandenka", "Siberia – Yakut", "South Africa – Bantu" ), class = "data.frame")
df_PGS_cont_20_30 <- structure(list(PGS_Z = c(0.438789045972685, -1.35288548955514, -1.55073254279487, 0.927621371934068, 1.25596106648565, 0.316698910098827, -0.147239425870863, 0.11178706372964), Population = c("AFRICA", "AMERICA", "CENTRAL-SOUTH ASIA", "EAST ASIA", "EUROPE", "MIDDLE EAST", "OCEANIA", "Population Set 1")), .Names = c("PGS_Z", "Population" ), row.names = c("AFRICA", "AMERICA", "CENTRAL-SOUTH ASIA", "EAST ASIA", "EUROPE", "MIDDLE EAST", "OCEANIA", "Population Set 1"), class = "data.frame")
library(corrplot)
cor(df_PGS_pop_30$PGS_Z, df_PGS_pop_20_30$PGS_Z)
corrplot(cor(data.frame(df_PGS_pop_20$PGS_Z, df_PGS_pop_30$PGS_Z, df_PGS_pop_20_30$PGS_Z)))
cor(df_PGS_cont_30$PGS_Z, df_PGS_cont_20_30$PGS_Z)
corrplot(cor(data.frame(df_PGS_cont_20$PGS_Z, df_PGS_cont_30$PGS_Z, df_PGS_cont_20_30$PGS_Z)))
