def cluster(*args):
#"cyano.txt"
with open(args[0]) as handle:
record = Cluster.read(handle)
genetree = record.treecluster(method='s')
#genetree.scale()
exptree = record.treecluster(dist='u', transpose=1)
record.save(args[1], genetree, exptree)
def cluster_and_assign_all_cuts(file, dist):
with open(file) as handle:
record = Cluster.read(handle)
row_tree = record.treecluster(transpose=False, method='a', dist=dist)
row_tree.scale()
record.save(name.split('.')[0], geneclusters=row_tree)
# cut tree into n clusters, for 1 <= n <= n_elements
n_elements = len(record.geneid)
mat = np.zeros((n_elements, n_elements))
for i in range(n_elements):
mat[:, i] = row_tree.cut(i + 1) # cut into 1 <= i+1 <= n_elements
return pd.DataFrame(data=mat,
dtype=int,
index=record.geneid,
columns=range(1, n_elements + 1))
def cluster_dataset(filename,
name=None,
rows=True,
cols=True,
method='a',
dist='c',
row_order=None,
col_order=None):
with open(filename) as handle:
record = Cluster.read(handle)
if row_order:
record.gorder = [row_order.index(row) for row in record.geneid]
if col_order:
record.eorder = [col_order.index(col) for col in record.expid]
# initialize trees as 'None' in case only one axis is being clustered
row_tree = None
col_tree = None
# cluster rows (mutants)
if rows:
row_tree = record.treecluster(transpose=False,
method=method,
dist=dist)
row_tree.scale() # scale to [0,1] for ease of viewing in Java TreeView
# cluster columns (library genes)
if cols:
col_tree = record.treecluster(transpose=True, method=method, dist=dist)
col_tree.scale()
if not name:
name = filename.split('.')[0]
record.save(name, row_tree, col_tree)
return record, row_tree, col_tree
from Bio import Cluster
with open("/home/koreanraichu/cyano.txt") as handle:
record = Cluster.read(handle)
# 불러왔다
matrix = record.distancematrix()
# Distance matrix 계산
cdata, cmask = record.clustercentroids()
# Cluster 무게중심(Centroid) 계산
distance = record.clusterdistance()
# 클러스터간 거리 계산
tree = record.treecluster()
# hierarchical clustering
# 이거 matplot으로 못뽑나...
clusterid, error, nfound = record.kcluster()
# k-mean clustering
# method='a': k-mean
# method='m': k-median
clusterid, celldata = record.somcluster()
# SOM 계산하기
jobname = "cyano_clustering"
record.save(jobname, record.treecluster(), record.treecluster(transpose=1))
# 내 컴퓨터에 저(별)장
# 기본 형식: record.save(jobname, geneclusters, expclusters)
# geneclusters=record.treecluster()
# expclusters=record.treecluster(transpose=1)
def clust(source):
with open(source,'r') as handle: data=Cluster.read(handle)
tree=data.treecluster()
tree.scale()
data.save(path.splitext(source)[0],tree)
Z = linkage(Y, 'average')
print Z
dendrogram(Z)
fclust = fcluster(Z, 2, criterion='distance')
clust_dict = defaultdict( list )
for i, row in enumerate(water_list):
#print fclust[i], str(fclust[i])
clust_dict[ str(fclust[i]) ].append( row )
#print clust_dict
for c in clust_dict:
print 'select water and (' + ' or '.join( [ '(~' + w[12] + ' and ' + str(w[5]) + ')' for w in clust_dict[c] ] ) + '); isosurface id "foo' + c + '" color lightblue center {selected} SPHERE @{ [ {selected}.x.stddev, {selected}.y.stddev, {selected}.z.stddev, 0.5 ].max *2 } translucent' + ';'
sys.exit(0)
from Bio import Cluster
lines = "Start\tX\tY\tZ\n" + "\n".join( [ "\t".join( [ row[12] + "|" + str(row[5]), str(row[6]), str(row[7]), str(row[8]) ] ) for row in water_list ] ) + "\n"
import StringIO
handle = StringIO.StringIO(lines)
record = Cluster.read(handle)
tree = record.treecluster( method="c", dist="e" )
record.save( '../data/test_tree', tree )
print tree
