Curt M. Breneman Professor Physical, Organic & Computational Cogswell 319A 518.276.2678 brenec@rpi.edu

Dr. Breneman received his Ph.D. in organic chemistry from the University of California at Santa Barbara in 1987 after obtaining a B.S. in chemistry at UCLA. Before joining the Rensselaer faculty in 1989, Dr. Breneman was a postdoctoral research associate at Yale University under the direction of Professor Kenneth B. Wiberg.

The Automated Design and Discovery of Novel Pharmaceuticals using Semi-Supervised Learning in Large Molecular Databases

Ab Initio Computational Chemistry

With the advent of powerful new theoretical methods and computational hardware, most chemical phenomena can be studied in detail using ab initio computational methods. The continuing refinement of these tools is a research area in itself, but the general availability of modern quantum mechanical program packages such as Gaussian94 and Spartan allow these tools to be applied with increasing frequency to numerous physical-organic problems of structure and reactivity. Other tools, such as the PROAIM electron density analysis package, allow the user to delve even more deeply into the electronic roots of chemical reactivity and stability.

Rapid Construction of Molecular Electron Density Distributions: RECON/TAE Transferable Atom Equivalent (TAE) Modeling

The TAE method grew out of a need for a way to rapidly generate ab initio-quality electron density representations of molecules without the associated computational overhead. The roots of the method can be found in the Theory of Atoms in Molecules originally formulated by Professor Richard Bader of McMaster University. The AIM theory, later implemented in the PROAIM program, allows users to dissect molecular electron densities into atomic fragments for study. Our TAE method allows a library of such atoms to be used to reconstruct molecules -- with all desired electronic properties intact. This feature has proven valuable in generating electron density-based property descriptors for use in regression analysis.

Machine Learning in High-Throughput Screening and Data Mining of Molecular Databases

In collaboration with Prof. Mark Embrechts from the department of Decision Sciences and Engineering Systems and Prof. Kristin Bennett from the Math department, a cross-disciplinary effort is has been initiated to develop a new method for automated molecular design. The new technique utilizes a combination of novel electron density-based molecular property descriptors and the latest developments in machine learning and artificial intelligence to find the molecular features most responsible for an observed molecular property. The resulting models may then be used in inverse-QSAR design experiments to propose new molecular structures for evaluation.

Electron Density-Based QSAR and QSPR Descriptor Computation

Following the discovery that many TAE electron density-derived properties of molecules can be used for creating property descriptors, many examples of such descriptors have been computed and used in Structure-Property Relationship studies. While some of the regression studies have been performed upon sets of drug candidate molecules, other studies have been undertaken as varied subjects as the HPLC retention times of modern explosives or the intramolecular packing characteristics of photographic dyes.

Automated Drug Discovery Methods and "Materials by Design"

The development of the TAE-based molecular property descriptors led to some fruitful collaborations with members of the Statistics and Chemometrics communities. These interactions have resulted in a new set of automated molecular design tools which are currently undergoing parameterization and testing. These tools contain some of the characteristics of "expert systems" as well as other modern statistical algorithms such as Partial Least Squares modules. The result is a system which can be used to predict properties of unknown molecules to within a specific set of error limits.

Molecular Recognition

Imprinting polymer matrices at the molecular level has become a "hot" area of research in the field of Molecular Recognition. Template molecules which can be removed after polymerization are the key to this work. The cavities left behind in the polymer media can be exploited as either stationary-phase binding sites in chromatographic media, or as catalytic sites for specific transformations. Most other workers in this area have used polymethylmethacrylate polymers that are highly cross-linked with divinyl benzene. In our laboratory, photopolymerization of aerosols composed of template+monomer+photoinitiator mixtures have successfully produced "smart beads" of 20-30 micrometers in diameter -- just the right size for chromatographic media. Further studies are being planned for determining the catalytic potential of such silicone beads.

C.M. Breneman, C.M. Sundling, N. Sukumar, L. Shen, W.P. Katt, and M.J. Embrechts “New Developments in PEST shape/property Hybrid Descriptors”, Journal of Computer-Aided Molecular Design, 17, 231-240, 2003.

C. E. Whitehead, C.M. Breneman, N. Sukumar and M.D. Ryan, “Transferable Atom Equivalent Multi-Centered Multipole Expansion Method”, J. Comp. Chem. (Special Issue on electron densities and electrostatic potentials) – S. R. Gadre, Ed.24(4), 512-529 MAR 2003.

Jinbo Bi, Kristin Bennett, Mark Embrechts, Curt Breneman, Minghu Song; Dimensionality Reduction via Sparse Support Vector Machines” Journal of Machine Learning Research, 3(Mar):1229-1243, 2003.

Tugcu, N., Ladiwala, A., Breneman, C.M. and Cramer, S.M., “Identification of chemically selective displacers using parallel batch screening experiments and quantitative structure efficacy relationship models.” Analytical Chemistry, 2003. 75(21): p. 5806-5816.

Tugcu, N., Song, M.H., Breneman, C.M., Sukumar, N., Bennett, K.P. and Cramer, S.M., “Prediction of the effect of mobile-phase salt type on protein retention and selectivity in anion exchange systems.” Analytical Chemistry, 2003. 75(14): p. 3563-3572.

Lavine, B.K., Davidson, C.E., Breneman, C. and Katt, W., “Electronic van der Waals surface property descriptors and genetic algorithms for developing structure-activity correlations in olfactory databases.” Journal of Chemical Information and Computer Sciences, 2003. 43(6): p. 1890-1905.

Ladiwala, A., Rege, K., C.M. Breneman and Cramer, S.M., “Investigation of mobile phase salt type effects on protein retention and selectivity in cation-exchange systems using quantitative structure retention relationship models.” Langmuir, 2003. 19(20): p. 8443-8454.

D. Zagorevskii, M. Song, C. Breneman, Y. Yuan, T. Fuchs, K. Gates and C. Greenlief, “A Mass Spectrometry Study of Tirapazamine and its Metabolites: Insights Into the Mechanism of Metabolic Transformations and the Characterization of Reaction Intermediates”, Journal of the American Society for Mass Spectrometry 14, 881-892, 2003.

M. Song, C.M. Breneman, J. Bi, N. Sukumar, K.P. Bennett, S. Cramer, and N. Tugcu, "Prediction of Protein Retention Times in Anion-exchange Chromatography Systems using Support Vector Machine Regression", JCICS (Journal of Chemical Information and Computer Science), 42(6), 1347-1357 NOV-DEC 2002. See: http://dx.doi.org/10.1021/ci025580t

C. B. Mazza, C. E. Whitehead, C.M. Breneman and Steven M. Cramer, "Predictive Quantitative Structure-Retention Relationship Models for Ion-Exchange Chromatography" Chromatographia, 56(3-4), 147-152, 2002.

N. Tugcu, C. Mazza, C. Breneman, Y. Sanghvi, J. Moore and S. M. Cramer, "High Throughput Screening and Quantitative Structure-Efficacy Relationship Models for Designing Displacers for Anti-sense Oligonucleotide Purification in Anion-Exchange Systems", Separation Science and Technology. 37(7) 1667-1681, 2002.

C. B. Mazza, K. Rege, C.M. Breneman, J. S. Dordick and S. M. Cramer. "High Throughput Screening and Quantitative-Structure Efficacy Relationship Models of Potential Displacer Molecules for Ion Exchange Systems". Biotechnology and Bioengineering 80(1), 60-72, 2002.

C.M. Breneman, Mark J. Embrechts, Muhsin Ozdemir, Larry Lockwood, Kristin Bennett, and Dirk DeVogelaere, "Feature Selection Methods Based on Genetic Algorithms for In Silico Drug Design," Chapter 15 (26 pages) in Evolutionary Computation in Bioinformatics, Corne, D. W., and Fogel, G.B., Eds., Morgan Kaufmann, San Francisco (2002) (A Peer-Reviewed Edited Compilation)

M. Embrechts, F. Arcinegas, M. Ozdemir, M. Momma, C.M. Breneman, L. Lockwood, K.P. Bennett and R.H. Kewley, "Stripmining for Molecules", Proc. IEEE IJCNN'02, pp. 305 - 310, 2002.

M. J. Embrechts, F. Arciniegas, M. Ozdemir, C.M. Breneman and K. P. Bennett, "Kernel PLS Feature Selection with Sensitivity Analysis for In-Silico Drug Design", ASME ANNIE Proceedings, C. Dagli, Ed. 2002. (6 pages)

Mark J. Embrechts, C. M. Breneman, Fabio Arciniegas, Muhsin Ozdemir, and Kristin P. Bennett, "Data Mining Using 2-D Neural Network Sensitivity Analysis for Molecules," in Intelligent Engineering Systems through Artificial Neural Networks: Smart Engineering System Design: Vol. 11, C. H. Dagli et al., Eds., pp. 345 - 350, ASME Press (2001). (A Peer-Reviewed Edited Compilation).

M. Embrechts, F. Arciniegas, M. Ozdemir, C. M. Breneman, K. Bennett, and L. Lockwood, "Bagging Neural Network Sensitivity Analysis for Feature Reduction for In Silico Drug Design", Proc. IEEE pp. 2478-2482, IJCNN'01, 2001.

M. Ozdemir, M. J. Embrechts, F. Arciniegas, C. M. Breneman, and K. Bennett, "Feature Selection for In-Silico Drug Design using Genetic Algorithms and Neural Networks," Proc. IEEE SMCia-01 Mountain workshop on Soft Computing in Industrial Applications, pp 53-57, Blacksburg, Virginia, June 25-27, M. Embrechts, H. VanLandingham, S. Ovaska, Eds. 2001.

M. Embrechts, F. Arciniegas, M. Ozdemir, C.M. Breneman, and K. Bennett, "Data Mining Using 2-D Neural Network Sensitivity Analysis for Molecules" ASME ANNIE Proceedings, C. Dagli, Ed. 2001. (6 pages).

Demiriz, A., Bennett, K. P., Breneman, C. M., Embrechts, M. J. "Support
Vector Machine Regression in Chemometrics". In Computing Science and
Statistics: Proceedings of Interface, "Frontiers in Data Mining and Bioinformatics" Volume 33, Arnold Goodman and Padhraic Smyth, Eds. 2001. (Referred - 9 pages - published on CD).

Mazza, C.B., Sukumar, N., Breneman, C. M. and Cramer, S.M., "Prediction of Protein Retention in Ion-Exchange Systems Using Molecular Descriptors Obtained from Crystal Structure", Analytical Chemistry, 73(22) 5457-5461 2001.