Software by Shawn Martin
GENERAL NOTE: Some of the
below files are *.tar.gz. For some reason these files are
sometimes altered when using Internet Explorer, e.g. unzipped. If
you have
trouble try renaming the file *.tar or *.tar.gz or try a different
browser.
iQSAR Solver: Inverse Molecular Design
This code accompanies the article
"Lattice Enumeration for Inverse Molecular Design using the Signature Descriptor"
in publications. It enumerates solutions to
a Diophantine system of equations used for molecular design. It uses the PARI library (2.5.1)
for arbitrary precision integer calculations. Please let me know if there any problems.
(source, contact)
NMTRI: Non-Manifold Surface Reconstruction
I have implemented a toolbox
for
triangulating non-manifold point clouds in high dimensional vector
spaces, as described in detail in "Non-Manifold Surface Reconstruction
from High Dimensional Point Cloud Data" in publications. The toolbox can
handle 2-manifolds, 2-manifolds with boundary, and 2-manifolds with
self-intersections (double curves, no cusps). The code is written
in Matlab. Also included is code used in the cyclo-octane project
"Topology of Cyclo-Octane Energy Landscape" in publications. Please let me know if you have any problems. (source, cyclo-octane
example, contact)
OpenOrd: Large-scale Graph Layout (formerly DrL)
We have developed a
force-directed graph layout toolbox focused on real-world large-scale
graphs. This toolbox
includes:
-
Standard force-directed
layout
of graphs using
algorithm based on the popular VxOrd routine (used in the VxInsight
program).
-
Parallel version of
force-directed layout
algorithm.
-
Recursive multilevel
version
for obtaining better
layouts of very large graphs.
-
Ability to add new
vertices to
a previously drawn
graph.
OpenOrd has been used on
graphs up
to 849k vertices. It is written in C++ and can be used with
Linux, Windows, and Mac, but has mostly been used in Linux.
Please email me with
comments/problems. Note: binaries have been provided in case of
compilation problems -- you should still download the source code for
documentation and examples. (source, windows binaries, mac
os x (intel) binaries, contact)
Matlab Autoencoder
I have revised the code found at G.
Hinton's webpage for using
an autoencoder for dimension reduction. The code has been
rewritten in a functional form but is otherwise the same as originally
implemented in G. Hinton and R. Salakhutdinov
(2006) "Reducing the Dimensionality of Data with Neural Networks," Science 5786:504-507. In order to use the code you will
also need to download the MNIST data from http://yann.lecun.com/exdb/mnist/
and C. Rasmussen's optimizer.
After downloading our rewritten code
follow the readme.txt file to install and use. You can also
download the files small_mnist_ex.mat
and full_mnist_ex.mat, which contain
the results mentioned in the readme (these files are separate in case
of slow download speed). Please email me
if you have any trouble with this
code. (download, full_mnist_ex.mat.zip, small_mnist_ex.mat.zip, contact)
Signature Products
We have developed a method for predicting
protein-protein
interactions (see "Predicting Protein-Protein Interactions using
Signature Products" in publications)
using amino acid sequences based on J.-L.
Faulon's signature descriptor
.
The software is written in
C/C++ and is based on T. Joachim's SVM-light package V5.0.
The software has been compiled using gcc/g++ under Linux and Cygwin. Please let
me know if you have any
problems compiling and/or using the software. (download, contact)
IMPORTANT NOTE: You must use SVM-light version 5, otherwise the patch
won't work. SVM-light version 5 is available from T. Joachim's
web page if you scroll down
to the bottom.
Training Support Vector Machines
We have also developed a method for training Support Vector
Machines using a Geometric approach (see "Training Support Vector
Machines using Gilbert's Algorithm" in
publications).
We have implemented this
approach using MATLAB. Please let me
know if you have any problems with this software. (
download,
contact)
Last Updated 24/5/2012.