def main():
args = parse_args()
header, counts = read_counts(args.counts)
counts = pd.DataFrame(counts, columns=header)
counts = sort_counts(counts)
num_genes = int(args.num_genes)-1
out_dir = args.out_dir
# plot pca
print('Generating PCA plot ...')
plot.plot_pca(out_dir, counts)
# plot heatmap
print('Generating Gene Expression Heatmap ...')
plot.plot_heatmap(out_dir, counts, num_genes)
# Plot gene expression tragectory
print('Generating Gene Expression Trajectory ...')
plot.plot_trajectory(out_dir, counts, num_genes)
# Save formatted and sorted count file
counts.to_csv('data/counts_clust.txt', index=False, sep='\t')
# Call clust to cluster the genes
print('Clustering Genes (this might take awhile) ...')
subprocess.call(['mkdir', 'clust_out'])
if args.kmeans is not None:
subprocess.call(['clust', 'data/counts_clust.txt',
'-o', './clust_out', '-K', args.kmeans])
else:
subprocess.call(['clust', 'data/counts_clust.txt',
'-o', './clust_out'])
# Make sure everythin is all set for motif enrichment
clust_out = args.input_genes
ref_bed = args.bedfile
ref_fa = args.genome
ref_motif = args.motif
try:
open(clust_out)
except FileNotFoundError:
print('Clustering failed, '
+ 'Clusters_Objects.tsv not found in the output directory')
print('Motif Enrichment Analysis (this might take awhile) ...')
try:
enrichment.run_motif_enrichment(clust_out,
ref_bed,
ref_fa, ref_motif,
args.ame,
100, 100)
except NameError:
print('AME is not installed! Please install AME and try again')
plt.plot(Y_full[(i * nbins):((i + 1) * nbins), 0],
Y_full[(i * nbins):((i + 1) * nbins), 1], 'k')
plt.colorbar(pad=0.1, fraction=0.1)
plt.xlim(-0.3, 0.5)
plt.ylim(-0.5, 0.3)
else:
ax = fig.add_subplot(3, 2, i + 1, projection='3d')
ax.scatter(Y_full[(i * nbins):((i + 1) * nbins), 0],
Y_full[(i * nbins):((i + 1) * nbins), 1],
Y_full[(i * nbins):((i + 1) * nbins), 2],
c=color,
cmap=cmap)
plt.title("MDS %s" % s1)
plt.tight_layout()
fplt.plot_pca()
plt.figure(6)
plt.clf()
fplt.plot_image_array((dist, ),
names=['dist_%s' % feat],
invert_y=True,
nplots=3)
plt.subplot(3, 1, 2)
plt.plot(dat_mean, 'r')
plt.title('%s_%s mean' % (strain, feat))
plt.subplot(3, 1, 3)
plt.plot(dat_var, 'b')
plt.title('%s_%s var' % (strain, feat))
# entropies /cross entropies