UCSC's INVENTON Software Creates Molecules in 3D
by Elisabeth Wechsler
A software package under development at the University of California, Santa Cruz (UCSC) uses artificial intelligence techniques and a knowledge of chemistry to "invent" molecules in 3D space -- something that has been lacking to date, according to Professor Todd Wipke, of UCSC's Molecular Engineering Laboratory.
"Chemists have no good algorithms for manually enumerating the molecules
that can satisfy a set of constraints in 3D," he said, in his March 5th presentation at the NAS Computational Molecular Nanotechnology Workshop. Wipke believes that "computers, when properly programmed, [can] be more creative than chemists in the task of inventing new chemical structures."
Called INVENTON, the program automatically constructs chemical frameworks that position atoms in a desired 3D arrangement, giving researchers new ideas for building blocks. Wipke summarized the paradigm as: "Chemist describes objectives and constraints. Computer formulates strategy and tactics, then invents structures and ranks them. Chemist reviews resulting candidates." More specifically, INVENTON creates molecules by adding molecular fragments to span the space from one point to another. The points are given in the problem description provided by the chemist or are generated as subgoals. The molecular fragments come from a basis set established by the investigator. INVENTON also can build structures from individual atoms. Finally, the program ranks the candidate structures by scoring functions selected by the chemist, Wipke explained.
Productive Approach To Design
"A computer program can invent molecules that have never been conceived of
and do not exist in any database anywhere," he commented. In its six years of existence, INVENTON has designed structures in the domains of nanotechnology (self-assembling molecules in nanoscale systems) and pharmaceutical drugs (such as mimics of known drugs for cancer and enzyme inhibitors for AIDS).
"Designing a system like this is a complex task -- one that requires really
logical thinking. AI methods are already being used by INVENTON to prioritize tasks, and heuristic search is used to reduce the number of `relevant' constraints." In addition, bringing "engineering principles across boundaries to assist chemical design" has been useful, Wipke noted.
Automated molecular design will benefit from greater CPU speed, more knowledge and understanding, and larger organized collections of chemical information readable by computer, he said, adding that "having more complex problems will accelerate our abilities to problem solve."
Collaboration with NAS
Gina "Nanogirl" Miller
Collaborative work between Wipke's group at UCSC and Al Globus (NAS applications and tools group) has included modifications to the search strategy and solving simple initial problems. Current work is focused on developing fragment libraries designed for nanotechnology and then applying them to problems requiring very stiff molecules. A more difficult future problem is taking advantage of the high degree of symmetry common in nanotechnology problems and spanning space with molecular fragments that can be repeated an indefinite number of times.
Gina "Nanogirl" Miller