def fit_plot_save(k, smoothExprs, day, probeID, geneSymbol, organ, strain, path):
"""
Fit k-means, plot and save results
Arguments
=========
k - no. of clusters
smoothExprs - gene expression rows = genes, columns = day
day - day
probeID - probeID
geneSymbol - geneSymbol
path - path
Returns
=========
None - results are plotted and saved
"""
model = KMeans(n_clusters=k)
model.fit(smoothExprs)
clustCentre = model.cluster_centers_
# Plot results
plot_silhouette(silhouette_samples(smoothExprs, model.labels_), model.labels_)
clust.multi_plot(smoothExprs, clustCentre, day, model.labels_)
# Hierarchical clustering
# Ward + Euclidean
header = ["Cluster%i" % label for label in np.unique(model.labels_)]
hclust = hc.linkage(clustCentre, method='ward', metric='euclidean')
plt.figure(); plt.title("Hclust() Ward + Euclidean")
hc.dendrogram(hclust, color_threshold=0.0, labels=header)
#seed=101
#embedding = tsne.tsne(smoothExprs, no_dims = 3, initial_dims = 20, perplexity = 30.0, seed=seed) # low dimensional embedding
#tsne.plot(embedding, model.labels_)
# Save model
io.save_pickle(os.path.join(path['Clust']['Model'], organ + strain + ".pickle"), model)
# Save Gene/Probe List
geneList = clust.get_gene_list(model.labels_, geneSymbol)
probeList = clust.get_gene_list(model.labels_, probeID)
io.write_list_to_csv(os.path.join(path['Clust']['GeneList'], organ + strain + ".csv"), header, geneList) # Gene list
io.write_list_to_csv(os.path.join(path['Clust']['ProbeList'], organ + strain + ".csv"), header, probeList) # Probe list
# Save Cluster "centres"
dataMatrix = np.hstack((np.array(header)[:, None], clustCentre))
header = list(itertools.chain.from_iterable([["Cluster"], list(day)]))
io.write_to_csv(os.path.join(path['Clust']['Centres'], organ + strain + ".csv"), header, dataMatrix) # Cluster "centres"
# Save Alternate plot
hFig = clust.multi_plot(smoothExprs, clustCentre, day, model.labels_)
io.save_pdf(os.path.join(path['Clust']['Plot'], organ + strain + "2.pdf"), hFig) # Plot
def merge(organ, strain, groupToMerge, groupLabel, originalLabel, path):
"""
Merge modules
Arguments
=========
groupToMerge - list of lists e.g [[1,2], [3]]
groupLabel - list of unique group labels e.g ["A", "B"]
Returns
=========
newLabel - A, B, C etc.
"""
# Load gene/probe list
oldGeneList = pandas.read_csv(os.path.join(path['Clust']['GeneList'], organ + strain + ".csv"), sep=",")
oldProbeList = pandas.read_csv(os.path.join(path['Clust']['ProbeList'], organ + strain + ".csv"), sep=",")
# Initialise vars
NGroup = len(groupToMerge)
newLabel = originalLabel.astype(type(groupLabel))
newGeneList = []
newProbeList = []
for iGroup in xrange(NGroup):
tempGeneList = []
tempProbeList = []
for label in groupToMerge[iGroup]:
newLabel[originalLabel == label] = groupLabel[iGroup]
bWant = ~pandas.isnull(oldGeneList['Cluster' + str(label)]) # some entries could be NaN
tempGeneList.append(np.array(oldGeneList['Cluster' + str(label)][bWant]))
tempProbeList.append(np.array(oldProbeList['Cluster' + str(label)][bWant]))
newGeneList.append(list(itertools.chain.from_iterable(tempGeneList)))
newProbeList.append(list(itertools.chain.from_iterable(tempProbeList)))
# Save Gene/Probe List
header = ["Cluster%s" % label for label in groupLabel]
io.write_list_to_csv(os.path.join(path['ClustMerge']['GeneList'], organ + strain + ".csv"), header, newGeneList)
io.write_list_to_csv(os.path.join(path['ClustMerge']['ProbeList'], organ + strain + ".csv"), header, newProbeList)
# Retrieve old clust centres
data = pandas.read_csv(os.path.join(path['Clust']['Centres'], organ + strain + ".csv"), sep=",")
#oldClustCentre = data.values[:, 1:] # pick only the centres
day = data.columns.values[1:].astype('float')
# Get smooth exprs
data = pandas.read_csv(os.path.join(path['GPFit']['SmoothExprs'], organ + strain + ".csv"), sep=",")
#bSelect = top_ranked(organ, strain, len(originalLabel), path) # 29/03/16 not applicable anymore as I'm choosing COMMON gene sets using clust.common_ranked()
allProbeID = np.array(data['ProbeID'])
wantedProbeID = np.array(list(itertools.chain.from_iterable(newProbeList)))
bSelect = np.array([allProbeID[i] in wantedProbeID for i in xrange(len(allProbeID))]) # simply creates a vector of T, F, T, whether gene is in geneSet or
smoothExprs = data.values[:, 2:].astype('float')[bSelect, :]
# get new label of old clust centres i.e 1, 2, 3, 4, 5 --> 'A', 'B', 'A', 'C', 'B'
# VERY ugly - should've used dictionaries....hey ho
newLabelOldClustCentre = np.empty((len(np.unique(originalLabel))), dtype='str')
for iGroup in xrange(NGroup):
for label in groupToMerge[iGroup]: # I know that label is numeric, else it would fail
newLabelOldClustCentre[label-1] = groupLabel[iGroup] # -1 as "I" start counting from 1
# Naively take the mean
clustCentre = np.empty((len(groupLabel), len(day)))
for i, label in enumerate(groupLabel):
clustCentre[i, :] = np.mean(smoothExprs[newLabel==label, :], axis=0)
# #Using GPR was creating numerical issues so now (naively) I'm taking the mean
# #Compute clust centres (should research into doing this "properly" i.e using MOHGP, but coz for now I'm only
# #interested in gene symbols it should be fine)
# clustCentre = np.empty((len(groupLabel), len(day)))
# for i, label in enumerate(np.unique(newLabel)):
# thisClustCentre = oldClustCentre[newLabelOldClustCentre == label, :]
# if sum(newLabelOldClustCentre == label) == 1:
# clustCentre[i, :] = thisClustCentre # no need to GPR
# else:
# xTrain = np.tile(day, sum(newLabelOldClustCentre == label)).flatten()[:, None]
# yTrain = thisClustCentre.flatten()[:, None]
# fit = gpr.fit(xTrain, yTrain)
# mu, var = fit.predict(day[:, None])
# clustCentre[i, :] = mu.T
# Save Cluster "centres"
dataMatrix = np.hstack((np.array(header)[:, None], clustCentre)) # using header from Save Gene/Probe List
header = list(itertools.chain.from_iterable([["Cluster"], list(day)]))
io.write_to_csv(os.path.join(path['ClustMerge']['Centres'], organ + strain + ".csv"), header, dataMatrix) # Cluster "centres"
# Save Alternate plot
hFig = multi_plot(smoothExprs, clustCentre, day, newLabel)
io.save_pdf(os.path.join(path['ClustMerge']['Plot'], organ + strain + "2.pdf"), hFig) # Plot
return newLabel
def MOHGP(probesToCluster, organ, strain, prefix, K, alpha, path, seed=0):
"""
Word cloud plot for all clusters in a dataset
Arguments
=========
probesToCluster - a set of unique probeIDs to cluster
organ - blood/spleen
strain - AS/CB
prefix - all/common/only
K - init no. of clusters
alpha - concentration parameter/strength parameter of the Dirichlet Process Prior
path - dictionary with all results paths
seed - to reproduce results due to multiple local optima
Returns
=========
None - a Mixture of Hierarchical Gaussian Process model is fitted and saved to disk
"""
# To reproduce results
np.random.seed(seed)
# Load gene expression data
data = pandas.read_csv(os.path.join(path['RawData']['Log2FC'], organ + strain + ".csv"), sep=",") # read data
probeID = np.array(data['ProbeID'])
yTrain = data.values[:, 2:].astype('float') # 45,281 genes x S samples
xTrain = np.floor(data.columns.values[2:].astype('float64'))[:, None] # floor to get int 0, 0, 2, 2, ..., 12
# Subset the data by keeping only probesToCluster
bWant = np.array([probeID[i] in probesToCluster for i in xrange(len(probeID))]) # simply creates a vector of T, F, T
yTrain = yTrain[bWant, :]
probeID = np.array(data['ProbeID'][bWant])
geneSymbol = np.array(data['GeneSymbol'][bWant])
# MOHGP fitting
# Define the covariance functions for the hierarchical GP structure
# The model of any cluster of genes has a hierarchical structure, with the unknown cluster-specific
# mean drawn from a GP, and then each gene in that cluster being drawn from a GP with said unknown mean function.
# Covariance function for the latent function that describes EACH cluster.
covFunCluster = GPy.kern.RBF(input_dim=1, variance=np.var(yTrain.ravel()), lengthscale=LENGTHSCALE)
# Covariance function that describes how EACH time-course (gene) deviates from the cluster
covFunGene = GPy.kern.RBF(input_dim=1, variance=np.var(yTrain.ravel())/10, lengthscale=LENGTHSCALE) + \
GPy.kern.White(1, variance=NOISE_VARIANCE)
# Set-up the clustering problem NB: For large alpha P resembles Po (i.e the base distribution)
fit = GPclust.MOHGP(X=xTrain, kernF=covFunCluster, kernY=covFunGene, Y=yTrain, K=K, prior_Z='DP', alpha=alpha)
# Constrain lengthscales (to avoid very short lengthscales as per Topa et al. (2012) on arXiv)
fit.rbf.lengthscale.constrain_bounded(LOWER_BOUND_LENGTHSCALE, UPPER_BOUND_LENGTHSCALE , warning=False)
fit.add.rbf.lengthscale.constrain_bounded(LOWER_BOUND_LENGTHSCALE, UPPER_BOUND_LENGTHSCALE , warning=False)
fit.hyperparam_opt_interval = 1000 # how often to optimize the hyperparameters
# Optimise hyperparameters
fit.optimize()
fit.systematic_splits(verbose=False)
# Name and reorder fit
fit.name = prefix + organ + strain
fit.reorder()
labels = np.argmax(fit.phi, axis=1) + 1 # cluster number
# Compute cluster prediction for xTest where xTest is taken from SmoothExprs
data = pandas.read_csv(os.path.join(path['GPFit']['SmoothExprs'], organ + strain + ".csv"), sep=",") # read data
smoothExprs = data.values[:, 2:].astype('float')[bWant, :]
xTest = data.columns.values[2:].astype('float64')[:, None]
mu, var = fit.predict_components(xTest)
clustCentre = np.empty((len(mu), xTest.shape[0]))
for iClust in xrange(len(mu)):
clustCentre[iClust, :] = mu[iClust]
# Save model and plot
io.save_pickle(os.path.join(path['Clust']['Model'], prefix + organ + strain + ".pickle"), fit)
io.save_pdf(os.path.join(path['Clust']['Plot'], prefix + organ + strain + ".pdf"), plot(fit))
# Save Gene/Probe List
geneList = get_gene_list(labels, geneSymbol)
probeList = get_gene_list(labels, probeID)
header = ["Cluster%i" % label for label in np.unique(labels)]
io.write_list_to_csv(os.path.join(path['Clust']['GeneList'], prefix + organ + strain + ".csv"), header, geneList) # Gene list
io.write_list_to_csv(os.path.join(path['Clust']['ProbeList'], prefix + organ + strain + ".csv"), header, probeList) # Probe list
# Save Cluster "centres"
dataMatrix = np.hstack((np.array(header)[:, None], clustCentre))
header = list(itertools.chain.from_iterable([["Cluster"], list(xTest.ravel())]))
io.write_to_csv(os.path.join(path['Clust']['Centres'], prefix + organ + strain + ".csv"), header, dataMatrix) # Cluster "centres"
# Save Alternate plot
hFig = multi_plot(smoothExprs, clustCentre, xTest, labels)
io.save_pdf(os.path.join(path['Clust']['Plot'], prefix + organ + strain + "2.pdf"), hFig) # Plot
# Word cloud
#vis.word_cloud_plot(organ, strain, prefix, path)
# Heatmap
vis.heatmap_plot_by_clusters(organ, strain, prefix, path)
def compare_arbitrary_clusters(organA, strainA, iiClusterA, colourA, organB, strainB, iiClusterB, colourB, prefix, path):
"""
Compare arbitrary cluster e.g CB_Bl_10 + CB_Bl_11 vs CB_Sp_07
Arguments
=========
organA/B - blood/spleen
strainA/B - AS/CB
iiClusterA/B - list of indices of clusters to compare e.g [10, 11]
colourA/B - colour of conditions red/blue "#e41a1c"/"#377eb8"
prefix - all/common/only
path - dictionary with all results paths
Returns
=========
None - figures saved to disk + .csv file of common genes saved to disk
"""
# Load probe list by cluster
probeListA = pandas.read_csv(os.path.join(path['Clust']['ProbeList'], prefix + organA + strainA + ".csv"), sep=",")
probeListB = pandas.read_csv(os.path.join(path['Clust']['ProbeList'], prefix + organB + strainB + ".csv"), sep=",")
# Pick only the clusters we're interested in
# A
probeIDA = []
for iClust in iiClusterA:
probeIDA.append(probeListA['Cluster' + str(iClust)].dropna()) # drop NA entries
probeIDA = list(itertools.chain.from_iterable(probeIDA))
# B
probeIDB = []
for iClust in iiClusterB:
probeIDB.append(probeListB['Cluster' + str(iClust)].dropna()) # drop NA entries
probeIDB = list(itertools.chain.from_iterable(probeIDB))
# Find common probes
commonProbes = set(probeIDA) & set(probeIDB)
# Read GPR smoothed gene expression
# A
data = pandas.read_csv(os.path.join(path['GPFit']['SmoothExprs'], organA + strainA + ".csv"), sep=",")
allProbeIDA = np.array(data['ProbeID'])
smoothExprsA = data.values[:, 2:].astype('float')
day = data.columns.values[2:].astype('float')
# B
data = pandas.read_csv(os.path.join(path['GPFit']['SmoothExprs'], organB + strainB + ".csv"), sep=",")
allProbeIDB = np.array(data['ProbeID'])
smoothExprsB = data.values[:, 2:].astype('float')
# Plot data
# Create figure
hFig, (hAx1, hAx2, hAx3) = plt.subplots(1, 3, sharex=False, sharey=False, figsize=(16, 8.27/1.8)) # a4 = 11.69 x 8.27 inches
# Condition A
for iProbe in xrange(len(probeIDA)):
iiWant = np.where(allProbeIDA == probeIDA[iProbe])[0][0] # should return only one index
if probeIDA[iProbe] in commonProbes:
hAx1.plot(day, smoothExprsA[iiWant, :], linewidth=2, color="#525252", alpha=ALPHA)
else:
hAx1.plot(day, smoothExprsA[iiWant, :], linewidth=0.5, color=colourA, alpha=ALPHA)
hAx1.axhline(y=0, color="black", linestyle='--', linewidth=2)
# Set x/y limits and title
hAx1.set_xlim(XLIM)
hAx1.set_ylim(YLIM)
#hAx1.set_title("%s%s - %s (#%d probes) r = %.2f" % (organA, strainA, clustNamesA[iClustA], len(thisProbeListA), rho))
hAx1.set_title(strainA + '_' + organA[:2] + str(iiClusterA))
hAx1.set_ylabel("$\log_2$(FC) wrt naive")
hAx1.set_xlabel("Days")
hAx1.grid(axis="y")
# Venn diagram
plt.sca(hAx2)
hVen = venn2([set(probeIDA), set(probeIDB)], set_colors=(colourA, colourB), set_labels=("", ""), alpha=0.9)
for label in hVen.subset_labels: # hVen.set_labels = "blood"/"spleen"; hVen.subset_labels = 3211/3211/1317
if hasattr(label, 'set_fontsize'):
label.set_fontsize(20)
if len(commonProbes)>0:
hVen.get_patch_by_id('11').set_color('#525252') # make the intersection grey
# Condition B
for iProbe in xrange(len(probeIDB)):
iiWant = np.where(allProbeIDB == probeIDB[iProbe])[0][0] # should return only one index
if probeIDB[iProbe] in commonProbes:
hAx3.plot(day, smoothExprsB[iiWant, :], linewidth=2, color="#525252", alpha=ALPHA)
else:
hAx3.plot(day, smoothExprsB[iiWant, :], linewidth=0.5, color=colourB, alpha=ALPHA)
hAx3.axhline(y=0, color="black", linestyle='--', linewidth=2)
# Set x/y limits and title
hAx3.set_xlim(XLIM)
hAx3.set_ylim(YLIM)
#hAx3.set_title("%s%s - %s (#%d probes)" % (organB, strainB, clustNamesB[iClustB], len(thisProbeListB)))
hAx3.set_title(strainB + '_' + organB[:2] + str(iiClusterB))
hAx3.set_ylabel("$\log_2$(FC) wrt naive")
hAx3.set_xlabel("Days")
hAx3.grid(axis="y")
# Save figure as .pdf
fileName = strainA + '_' + organA[:2] + str(iiClusterA) + '_vs_' + strainB + '_' + organB[:2] + str(iiClusterB)
io.save_pdf(os.path.join(path['Comparison'], fileName) + ".pdf", hFig)
# Write common probes to .csv
header = ["ProbeID", "GeneSymbol"]
commonGeneSymbol=[]
for probe in commonProbes: # get gene symbol
iiWant = np.where(allProbeIDB == probe)[0][0] # should return one value (probeIDs are unique)
commonGeneSymbol.append(data['GeneSymbol'].values[iiWant])
dataMatrix = np.hstack((np.array(list(commonProbes))[:, None], np.array(commonGeneSymbol)[:, None]))
io.write_to_csv(os.path.join(path['Comparison'], fileName) + "shared_genes.csv", header, dataMatrix)