| Pacific Rim Symposium on Surfaces, Coatings and Interfaces (PacSurf 2016) | |
| Biomaterial Surfaces & Interfaces | Wednesday Sessions |
| Session BI-WeM |
| Session: | Biomolecule/Material Interactions |
| Presenter: | Paul Pigram, La Trobe University, Australia |
| Authors: | N.G. Welch, La Trobe University, Australia R.M.T. Madiona, La Trobe University, Australia T.B. Payten, La Trobe University, Australia R.T. Jones, La Trobe University, Australia N. Brack, La Trobe University, Australia B.W. Muir, CSIRO, Australia P.J. Pigram, La Trobe University, Australia |
| Correspondent: | Click to Email |
Artificial neural networks (ANNs) form a class of powerful multivariate analysis techniques, yet their routine use in the surface analysis community is limited. Principal component analysis (PCA) is more commonly employed to reduce the dimensionality of large time-of-flight secondary ion mass spectrometry (ToF-SIMS) data sets and highlight key characteristics. The strengths and weaknesses of PCA and ANNs as methods for investigation and interpretation of a complex multivariate sample set will be considered. Using ToF-SIMS, spectra were acquired from an antibody and its proteolysis fragments with three primary-ion sources to obtain a panel of 72 spectra and a characteristic peak list of 775 fragment ions. The use of ANNs as a means to interpret the ToF-SIMS spectral data is explored, highlighting the optimal neural network design and computational parameters, and considering the technique limitations. Employing Bi3+ as the primary-ion source, ANNs can accurately classify antibody fragments from the parent antibody based on ToF-SIMS spectra.