Distinguishing Chemically Similar Polyamide Materials with ToF-SIMS Using Self-Organizing Maps and a Universal Data Matrix

Abstract

Time-of-flight secondary ion mass spectrometry (ToF-SIMS) is advancing rapidly, providing instruments with growing capabilities and resolution. The data sets generated by these instruments are likewise increasing dramatically in size and complexity. Paradoxically, methods for efficient analysis of these large, rich data sets have not improved at the same rate. Clearly, more effective computational methods for analysis of ToF-SIMS data are becoming essential. Several research groups are customizing standard multivariate analytical tools to decrease computational demands, provide user-friendly interfaces, and simplify identification of trends and features in large ToF-SIMS data sets. We previously applied mass segmented peak lists to data from PMMA, PTFE, PET, and LDPE. Self-organizing maps (SOMs), a type of artificial neural network (ANN), classified the polymers based on their molecular composition and primary ion probe type more effectively than simple PCA. The effectiveness of this approach led us to question whether it would be useful in distinguishing polymers that were very similar. How sensitive is the technique to changes in polymer chemical structure and composition? To address this question, we generated ToF-SIMS ion peak signatures for seven nylon polymers with similar chemistries and used our up-binning and SOM approach to classify and cluster the polymers. The widely used linear PCA method failed to separate the samples. Supervised and unsupervised training of SOMs using positive or negative ion mass spectra resulted in effective classification and separation of the seven nylon polymers. Our SOM classification method has proven to be tolerant of minor sample irregularities, sample-to-sample variations, and inherent data limitations including spectral resolution and noise. We have demonstrated the potential of machine learning methods to analyze ToF-SIMS data more effectively than traditional methods. Such methods are critically important for future complex data analysis and provide a pipeline for rapid classification and identification of features and similarities in large data sets.

QSAR without borders

“…ToF-SIMS in particular has proven to generate data that is very useful for QSPR material modeling. 285 Recent work has shown how self-organizing maps (SOMS) can provide superior clustering of complex mass peak data, 289 probing into the intrinsic information content (Shannon entropy) of these surface analysis methods. 290 As the field of biomaterials modeling is relatively nascent, there are many issues that need resolving before the full benefit of AI/ML-based QSAR methods can be realized.…”

Controlling orientation, conformation, and biorecognition of proteins on silane monolayers, conjugate polymers, and thermo-responsive polymer brushes: investigations using TOF-SIMS and principal component analysis

“…PCA could also be applied to an analysis of TOF-SIMS 2D images [33,[58][59][60] and even 3D TOF-SIMS sputtering data [50]. Other multivariate methods already applied for TOF-SIMS data analysis are non-negative matrix factorization (NMF) [61,62], the k-means cluster method [63], discriminant analysis [64,65], and artificial neuronal networks [55,66] involving self-organizing maps [67][68][69][70][71].…”

Understanding mass spectrometry images: complexity to clarity with machine learning

“…ToF-SIMS data. [12,13,[62][63][64][65][66][67] Initially, investigations were limited to 1D spectra, focusing on the performance of the SOM-with reference to techniques such as PCA and MCR-for the unsupervised discrimination of highly similar spectra. Results indicated that the SOM, because of its inherent non-linearity, performed better than its linear counterparts for this task, exhibiting greater tolerance for noise and apparently requiring minimal data preprocessing.…”