GENE_CLUSTER - Cluster Genetic Expression Data

GENE_CLUSTER takes data from genetic expression experiments, and tries to group the genes into clusters. Each cluster has a representative point, and the clustering minimizes the sum of the squares of the "distances" of each data point to its cluster representative. Here, the "distance" may be either the Euclidean distance or a similarity measure based on angles.

The data to be examined is assumed to be stored in a file.

The file is assumed to contain a number of records, with each record stored on its own line.

Each record, in turn, contains a fixed number of data values that describe a particular gene expression experiment.

Each record will be regarded as a point in N dimensional space.

The program will try to cluster the data, that is, to organize the data by defining a number of cluster centers, which are also points in N dimensional space, and assigning each record to the cluster associated with a particular center.

The method of assigning data aims to minimize the cluster energy, which is taken to be the sum of the squares of the distances of each data point from its cluster center.

In some contexts, it makes sense to use the usual Euclidean sort of distance. In others, it may make more sense to replace each data record by a normalized version, and to assign distance by computing angles between the unit vectors.

Files you may copy include:

• gene_cluster.f90, the source code.

Genetic expression data files include:

• i1650.dat, 180 lines of data.
• i29111.dat, 1031 lines of data.
• i1039.dat, 1152 lines of data.
• i2032.dat, 1481 lines of data.
• i29486.dat, 8526 lines of data.
• i2282.dat, 11016 lines of data.

For data set 1039, there are the following files:

• gene_cluster_1039.inp, an input file describing the run to be made;
• gene_cluster_1039.out, the output file containing the results;
• normal_1039.txt, a table of the energy versus number of clusters, for normalized data;
• normal_1039.ps, a plot of the energy versus number of clusters, for normalized data;
• normal2_1039.txt, a table of the energy versus the inverse number of clusters, for normalized data;
• normal2_1039.ps, a plot of the energy versus the inverse number of clusters, for normalized data;
• unnormal_1039.txt, a table of the energy versus number of clusters, for unnormalized data;
• unnormal_1039.ps, a plot of the energy versus number of clusters, for unnormalized data;
• unnormal2_1039.txt, a table of the energy versus the inverse number of clusters, for unnormalized data;

The list of routines includes:

• GENE_CLUSTER groups gene expression data into clusters.
• ANALYSIS computes the energy for a range of number of clusters.
• CLUSTER_ITERATION seeks the minimal energy of a cluster of a given size.
• ENERGY_COMPUTATION computes the total energy of a given clustering.
• DATA_TO_GNUPLOT writes data to a file suitable for processing by GNUPLOT.
• FILE_COLUMN_COUNT counts the number of columns in the first line of a file.
• FILE_LINE_COUNT counts the number of lines in a file.
• GET_UNIT returns a free FORTRAN unit number.
• I_INPUT prints a prompt string and reads an integer from the user.
• I_RANDOM returns a random integer in a given range.
• I_RANGE_INPUT reads a pair of integers from the user, representing a range.
• NEAREST_POINT finds the center point nearest a data point.
• POINT_GENERATE generates data points for the problem.
• POINT_PRINT prints out the values of the data points.
• R_RANDOM returns a random real in a given range.
• RANDOM_INITIALIZE initializes the FORTRAN 90 random number seed.
• S_INPUT prints a prompt string and reads a string from the user.
• S_TO_I reads an integer value from a string.
• TIMESTAMP prints the current YMDHMS date as a time stamp.
• WORD_COUNT counts the number of "words" in a string.

Return to the FORTRAN software page.