Mercurial > repos > greg > multilocus_genotype

comparison multilocus_genotype.R @ 15:62ad61eac1ff draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Thu, 20 Dec 2018 11:29:13 -0500
parents 96ee9122823e
children c4ec8727b50c
comparison
equal deleted inserted replaced
14:96ee9122823e 15:62ad61eac1ff
270 par(mar = c(8, 4, 4, 2)); 270 par(mar = c(8, 4, 4, 2));
271 x <- barplot(miss96, las=2, col=cols, ylim=c(0, 3), cex.axis=0.8, space=0.8, ylab="Missingness (%)", xaxt="n"); 271 x <- barplot(miss96, las=2, col=cols, ylim=c(0, 3), cex.axis=0.8, space=0.8, ylab="Missingness (%)", xaxt="n");
272 text(cex=0.6, x=x-0.25, y=-.05, name96, xpd=TRUE, srt=60, adj=1); 272 text(cex=0.6, x=x-0.25, y=-.05, name96, xpd=TRUE, srt=60, adj=1);
273 dev.off() 273 dev.off()
274 274
275 # Generate 96 pie charts. Make a table to subset the numerical 275 # Generate a pie chart for each sample with a genotype.
276 # and user_specimen_id values out of report_user for the 96 pies 276 # Store the numerical and user_specimen_id values from
277 # (user_specimen_id names will be used to label each pie). 277 # report_user for the charts (user_specimen_id names
278 # will be used to label each chart).
278 dt1 <- data.table(report_user); 279 dt1 <- data.table(report_user);
279 dt1 <- report_user[c(-2, -3, -4)]; 280 dt1 <- report_user[c(-2, -3, -4)];
280 dt1 <- na.omit(dt1); 281 dt1 <- na.omit(dt1);
281 # Translate to 96 columns and 5 rows. 282 # Translate to N (i.e., number of samples with a
283 # genotype) columns and 5 rows.
282 tdt1 <- t(dt1); 284 tdt1 <- t(dt1);
283 # Make another data table and transpose it the same as dt1 to 285 # Make another data table and transpose it the same as dt1 to
284 # just get numerics; these will feed into the creation of 96 286 # get numerics. These will feed into the creation of N vectors.
285 # vectors, "x" in the for loop below.
286 dt2 <- data.table(report_user); 287 dt2 <- data.table(report_user);
287 dt2 <- report_user[c(-1, -2, -3, -4)]; 288 dt2 <- report_user[c(-1, -2, -3, -4)];
288 # Translate to 96 columns and 5 rows. 289 # Translate to N columns and 5 rows.
289 tdt2 <- t(dt2); 290 tdt2 <- t(dt2);
290 # Create 96 vectors
291 x <- tdt2[1:96];
292 tdt1_matrix <- as.matrix(tdt1[-1,]); 291 tdt1_matrix <- as.matrix(tdt1[-1,]);
292 # The number of columns is the number of samples with genotypes.
293 nc <- ncol(tdt1_matrix);
293 mode(tdt1_matrix) <- "numeric"; 294 mode(tdt1_matrix) <- "numeric";
294 spy <- rowMeans(tdt1_matrix); 295 spy <- rowMeans(tdt1_matrix);
295 dev.new(width=10, height=7); 296 dev.new(width=10, height=7);
296 file_path = get_file_path("percent_breakdown.pdf"); 297 file_path = get_file_path("percent_breakdown.pdf");
297 pdf(file=file_path, width=10, height=7); 298 pdf(file=file_path, width=10, height=7);
300 col <- c("GREY", "#006DDB", "#24FF24", "#920000"); 301 col <- c("GREY", "#006DDB", "#24FF24", "#920000");
301 main <- "Average breakdown of SNP assignments across all samples"; 302 main <- "Average breakdown of SNP assignments across all samples";
302 pie(spy, labels=labels, radius=0.60, col=col, main=main, cex.main=.75); 303 pie(spy, labels=labels, radius=0.60, col=col, main=main, cex.main=.75);
303 par(mfrow=c(3, 2)); 304 par(mfrow=c(3, 2));
304 col <- c("GREY", "#006DDB", "#24FF24", "#920000"); 305 col <- c("GREY", "#006DDB", "#24FF24", "#920000");
305 for (i in 1:96) { 306 for (i in 1:nc) {
306 tmp_labels <- paste(labels, " (", round(tdt1_matrix[,i], 1), "%)", sep=""); 307 tmp_labels <- paste(labels, " (", round(tdt1_matrix[,i], 1), "%)", sep="");
307 main <- paste("Breakdown of SNP assignments for", tdt1[1, i]); 308 main <- paste("Breakdown of SNP assignments for", tdt1[1, i]);
308 pie(tdt1_matrix[,i], labels=tmp_labels, radius=0.90, col=col, main=main, cex.main=.85, cex=0.75); 309 pie(tdt1_matrix[,i], labels=tmp_labels, radius=0.90, col=col, main=main, cex.main=.85, cex=0.75);
309 } 310 }
310 dev.off() 311 dev.off()