Rapid quantitative analysis of binary mixtures of Escherichia coli strains using pyrolysis mass spectrometry with multivariate calibration and artificial neural networks

Pyrolysis mass spectrometry (PyMS) and multivariate calibration were used to show the high degree of relatedness between Escherichia coli HB101 and E. coli UB5201. Next, binary mixtures of these two phenotypically closely related E. coli strains were prepared and subjected to PyMS. Fully interconnected feedforward artificial neural networks (ANNs) were used to analyse the pyrolysis mass spectra to obtain quantitative information representative of the level of E. coli UB5201 in E. coli HB101. The ANNs exploited were trained using the standard back propagation algorithm, and the nodes used sigmoidal squashing functions. Accurate quantitative information was obtained for mixtures with >3% E. coli UB5201 in E. coli HB101. To remove noise from the pyrolysis mass spectra and so lower the limit of detection, the spectra were reduced using principal components analysis (PCA) and the first 13 principal components used to train ANNs. These PCA-ANNs allowed accurate estimates at levels as low as 1% E. coli UB5201 in E. coli HB101 to be predicted. In terms of bacterial numbers, it was shown that the limit of detection for PyMS in conjunction with ANNs was 3 × 10⁴ E. coli UB5201 cells in 1·6 × 10⁷ E. coli HB101 cells. It may be concluded that PyMS with ANNs provides a powerful and rapid method for the quantification of mixtures of closely related bacterial strains.     

Identification and Discrimination of Oral Asaccharolytic Eubacterium spp. by Pyrolysis Mass Spectrometry and Artificial Neural Networks

Curie-point pyrolysis mass spectra were obtained from 29 oral asaccharolytic Eubacterium strains and 6 abscess isolates previously identified as Peptostreptococcus heliotrinreducens. Pyrolysis mass spectrometry (PyMS) with cluster analysis was able to clarify the taxonomic position of this group of organisms. Artificial neural networks (ANNs) were then trained by supervised learning (with the back-propagation algorithm) to recognize the strains from their pyrolysis mass spectra; all Eubacterium strains were correctly identified, and the abscess isolates were identified as un-named Eubacterium taxon C₂ and were distinct from the type strain of P. heliotrinreducens. These results demonstrate that the combination of PyMS and ANNs provides a rapid and accurate identification technique.     

Rapid analysis of the expression of heterologous proteins in Escherichia coli using pyrolysis mass spectrometry and Fourier transform infrared spectroscopy with chemometrics: application to alpha 2-interferon production.

Cell pastes and supernatant Escherichia coli samples, taken from an industrial bioprocess overproducing recombinant alpha 2 IFN were analysed using pyrolysis mass spectrometry (PyMS) and diffuse reflectance-absorbance Fourier transform infrared spectroscopy (FT-IR). PyMS and FT-IR are physico-chemical methods which measure predominantly the bond strengths of molecules and the vibrations of bonds within functional groups, respectively. They therefore give quantitative information about the total biochemical composition of the bioprocess sample. The interpretation of these hyperspectral data, in terms of the quantity of alpha 2 IFN in the cell pastes and supernatant samples was possible only after the application of the 'supervised learning' methods of artificial neural networks (ANNs) and partial least squares (PLS) regression. Both PyMS and FT-IR are novel, rapid and economical methods for the screening and the quantitative analysis of complex biological bioprocess over producing recombinant proteins. Models established using either spectral data set had a similarly satisfactory predictive ability. This shows that whole-reaction mixture spectral methods, which measure all molecules simultaneously, do contain enough information to allow their quantification when the entire spectra are used as the inputs to methods based on supervised learning. Moreover, this is the first study where FT-IR in the mid-IR range has been used to quantify the expression of a heterologous protein directly from fermentation broths and the first study to compare the abilities of PyMS and FT-IR for the quantitative analyses of an industrial bioprocess.     

Rapid authentication of animal cell lines using pyrolysis mass spectrometry and auto-associative artificial neural networks

Summary Pyrolysis mass spectrometry (PyMS) was used to produce biochemical fingerprints from replicate frozen cell cultures of mouse macrophage hybridoma 2C11-12, human leukaemia K562, baby hamster kidney BHK 21/C13, and mouse tumour BW-O, and a fresh culture of Chinese hamster ovary CHO cells. The dimensionality of these data was reduced by the unsupervised feature extraction pattern recognition technique of auto-associative neural networks. The clusters observed were compared with the groups obtained from the more conventional statistical approaches of hierarchical cluster analysis. It was observed that frozen and fresh cell line cultures gave very different pyrolysis mass spectra. When only the frozen animal cells were analysed by PyMS, auto-associative artificial neural networks (ANNs) were employed to discriminate between them successfully. Furthermore, very similar classifications were observed when the same spectral data were analysed using hierarchical cluster analysis. We demonstrate that this approach can detect the contamination of cell lines with low numbers of bacteria and fungi; this approach could plausibly be extended for the rapid detection of mycoplasma infection in animal cell lines. The major advantages that PyMS offers over more conventional methods used to type cell lines and to screen for microbial infection, such as DNA fingerprinting, are its speed, sensitivity and the ability to analyse hundreds of samples per day. We conclude that the combination of PyMS and ANNs can provide a rapid and accurate discriminatory technique for the authentication of animal cell line cultures.     

Prediction of Streptococcus salivarius subsp. thermophilus and Lactobacillus delbrueckii subsp. bulgaricus populations in yoghurt by Curie point pyrolysis-mass spectrometry.

We evaluated the potential of pyrolysis-mass spectrometry (PyMS) for quantifying the binary mixed population of Streptococcus salivarius subsp. thermophilus and Lactobacillus delbrueckii subsp. bulgaricus in yoghurt. For this purpose, a new analytical approach was developed. The yoghurt was transparised and its total bacterial population was recovered by centrifugation and estimated by turbidimetric measurement. The quantity of each population (L. bulgaricus, S. thermophilus) was then estimated in the pellet by PyMS, and the data were analysed by artificial neural networks (ANNs). In parallel, streptococci and lactobacilli were numerated on SYL agar and these data were used as reference values to predict the bacterial counts of each population by PyMS. A close correlation was established between the streptococci and the lactobacilli counts on SYL agar and PyMS measurements (r(2)=0.98 for S. thermophilus and r(2)=0.96 for L. bulgaricus). Combined turbidimetric measurement and PyMS/ANNs seemed to be a powerful method for obtaining rapid counts of binary mixtures of bacteria in yoghurt.     

Rapid identification using pyrolysis mass spectrometry and artificial neural networks of Propionibacterium acnes isolated from dogs

Curie-point pyrolysis mass spectra were obtained from reference Propionibacterium strains and canine isolates. Artificial neural networks (ANNs) were trained by supervised learning (with the back-propagation algorithm) to recognize these strains from their pyrolysis mass spectra; all the strains isolated from dogs were identified as human wild type P. acnes. This is an important nosological discovery, and demonstrates that the combination of pyrolysis mass spectrometry and ANNs provides an objective, rapid and accurate identification technique. Bacteria isolated from different biopsy specimens from the same dog were found to be separate strains of P. acnes , demonstrating a within-animal variation in microflora. The classification of the canine isolates by Kohonen artificial neural networks (KANNs) was compared with the classical multivariate techniques of canonical variates analysis and hierarchical cluster analysis, and found to give similar results. This is the first demonstration, within microbiology, of KANNs as an unsupervised clustering technique which has the potential to group pyrolysis mass spectra both automatically and relatively objectively.     

Rapid phenotypic characterization of Salmonella enterica strains by pyrolysis metastable atom bombardment mass spectrometry with multivariate statistical and artificial neural network pattern recognition

Pyrolysis mass spectrometry was investigated for rapid characterization of bacteria. Spectra of Salmonella were compared to their serovars, pulsed-field gel electrophoresis (PFGE) patterns, antibiotic resistance profiles, and MIC values. Pyrolysis mass spectra generated via metastable atom bombardment were analyzed by multivariate principal component-discriminant analysis and artificial neural networks (ANNs). Spectral patterns developed by discriminant analysis and tested with Leave-One-Out (LOO) cross-validation distinguished Salmonella strains by serovar (97% correct) and by PFGE groups (49%). An ANN model of the same PFGE groups was cross-validated, using the LOO rule, with 92% agreement. Using an ANN, thirty previously unseen spectra were correctly classified by serotype (97%) and at the PFGE level (67%). Attempts by ANN to model spectra grouped by resistance profile-but ignoring PFGE or serotype-failed (10% correct), but ANNs differentiating ten samples of the same serotype/PFGE class were more successful. To assess the information content of PyMS data serendipitously associated with or directly related to resistance character, the ten isolates were grouped into four, three, or two categories. The four categories corresponded to four resistance profiles. The four class and three class ANNs showed much improved but insufficient modeling power. The two-class ANN and a corresponding multivariate model maximized inferential power for a coarse antibiotic-resistance-related distinction. They each cross-validated by LOO at 90%. This is the first direct correlation of pyrolysis metastable atom bombardment mass spectrometry with immunological (e.g. serology) or molecular biology (e.g. PFGE) based techniques.     

Discrimination of higher plant calluses based on embryogenic capacity and taxonomic classification by pyrolysis mass spectrometry

Pyrolysis mass spectrometry (PyMS) is a rapid, simple, high-resolution analytical method based on thermal degradation of complex material in a vacuum, and has been widely applied to the discrimination of closely related microbial strains. Minimally prepared samples of embryogenic and non-embryogenic calluses derived from various higher plants (sweet potato, morning glory, Korean ginseng, Siberian ginseng, and balloon flower) were subjected to PyMS for spectral fingerprinting. A dendrogram based on the unweighted pair group method, with arithmetic mean of pyrolysis mass spectra, divided the calluses into Siberian ginseng embryogenic callus and the others, which were subsequently divided into embryogenic and non-embryogenic callus groups, regardless of plant species from which the calluses were derived. In the non-embryogenic callus group, the dendrogram was in agreement with the known taxonomy of the plants. These results indicate that PyMS analysis could be applied for discriminating plant calluses based on embryogenic capacity and taxonomic classification.     

Resolution of batch variations in pyrolysis mass spectrometry of bacteria by the use of artificial neural network analysis

A simple, but stringent, three group model of bacterial interstrain identity (two cultures of the same strain ofEscherichia coli) and difference (a culture of a serologically distinct strain) was used in multiple serial weekly subcultures for five weeks to demonstrate the effect of both growth-related (phenotypic) and machine-related variation on pyrolysis mass spectra. An aliquot of serum from a single sample was included in each pyrolysis batch to distinguish machine drift from culture drift. Conventional principal component (PC) canonical variate (CV) analysis was successful within each pyrolysis batch but the variations between batches precluded the use of data from more than one batch in successful PCCV analysis. In contrast, artificial neural networks (ANNs) trained with data from one batch could be successfully used to identify groups in data from non-contemporaneous pyrolysis batches. Although the ANN method will require validation in more complex settings than this simple model, it is a promising approach to the problem of batch constraint in pyrolysis mass spectrometry.     

Characterization of Carnobacterium species by pyrolysis mass spectrometry

L.N. MANCHESTER, A. TOOLE AND R. GOODACRE. 1995. Forty-eight strains of Carnobacterium were examined by pyrolysis mass spectrometry (PyMS). The effects of culture age and reproducibility over a 4 week period were also examined. The results were analysed by multivariate statistical techniques and compared with those from a previous numerical taxonomic study based on morphological, physiological and biochemical characteristics and with studies which used DNA-DNA and 16S rRNA sequence homologies. Taxonomic correlations were observed between the PyMS data and the previous studies. Culture age was observed to have little effect on the mass spectra obtained and the reproducibility study indicated that there was very little variation over the 4 week period. It was concluded that PyMS provides a reliable method for studying carnobacterial classification and provides a rapid way for clarifying and refining subgeneric relationships within the genus Carnobacterium. Further work may also show that it offers a potentially very rapid and accurate method for the identification of Carnobacterium.     

Monitoring of complex industrial bioprocesses for metabolite concentrations using modern spectroscopies and machine learning: application to gibberellic acid production

Two rapid vibrational spectroscopic approaches (diffuse reflectance-absorbance Fourier transform infrared [FT-IR] and dispersive Raman spectroscopy), and one mass spectrometric method based on in vacuo Curie-point pyrolysis (PyMS), were investigated in this study. A diverse range of unprocessed, industrial fed-batch fermentation broths containing the fungus Gibberella fujikuroi producing the natural product gibberellic acid, were analyzed directly without a priori chromatographic separation. Partial least squares regression (PLSR) and artificial neural networks (ANNs) were applied to all of the information-rich spectra obtained by each of the methods to obtain quantitative information on the gibberellic acid titer. These estimates were of good precision, and the typical root-mean-square error for predictions of concentrations in an independent test set was <10% over a very wide titer range from 0 to 4925 ppm. However, although PLSR and ANNs are very powerful techniques they are often described as "black box" methods because the information they use to construct the calibration model is largely inaccessible. Therefore, a variety of novel evolutionary computation-based methods, including genetic algorithms and genetic programming, were used to produce models that allowed the determination of those input variables that contributed most to the models formed, and to observe that these models were predominantly based on the concentration of gibberellic acid itself. This is the first time that these three modern analytical spectroscopies, in combination with advanced chemometric data analysis, have been compared for their ability to analyze a real commercial bioprocess. The results demonstrate unequivocally that all methods provide very rapid and accurate estimates of the progress of industrial fermentations, and indicate that, of the three methods studied, Raman spectroscopy is the ideal bioprocess monitoring method because it can be adapted for on-line analysis.     

Mycobacterium avium-intracellulare from patients with and without AIDS compared by pyrolysis mass spectrometry

Isolates of Mycobacterium avium-intracellulare complex (MAI) from AIDS and non-AIDS patients were compared by pyrolysis mass spectrometry (PyMS). Those from AIDS patients were more closely related to each other than those from non-AIDS patients which were significantly more disparate.     

The value of pyrolysis mass spectrometry to investigate nosocomial outbreaks caused by Serratia marcescens

Simultaneous outbreaks of S. marcescens infection going on in the Neonatal Intensive Care Unit and the Surgical Department of the same hospital were investigated by pyrolysis mass spectrometry (PyMS). The PyMS analysis of the strains clearly demonstrated that the two outbreaks were caused by different strains. The 14 S. marcescens isolates from the first outbreak were closely related, with the exception of one environmental isolate, which did not harbour the ESBL plasmid, which was present in all other isolates. However, the phage type of all 14 isolates was the same. Among the 9 S. marcescens isolates from the second outbreak, PyMS clearly distinguished 3 that exhibited gentamicin resistance from the remaining 6 gentamicin-susceptible isolates. Phage typing was unhelpful in this case, as none of the isolates were typable. The PyMS typing of nosocomial outbreak strains can reach the level of discrimination approaching that achieved by molecular genetic analysis.     

Whole-organism fingerprinting of the genus Carnobacterium using Fourier transform infrared spectroscopy (FT-IR)

Sixty seven strains of Carnobacterium, atypical Lactobacillus, Enterococcus durans, Lactobacillus maltaromicus and Vagacoccus salmoninarum were examined by Fourier transform infrared (FT-IR) spectroscopy. The effects of culture age and reproducibility over a six month period were also investigated. The results were analysed by multivariate statistics and compared with those from a previous numerical phenetic study, a pyrolysis mass spectrometry (PyMS) study and with investigations which used DNA-DNA and 16S rRNA sequencing homologies. Taxonomic correlations were observed between the FT-IR data and these studies. Culture age was observed to have little effect on the spectra obtained. The reproducibility study indicated that there was correlation between spectra produced on two occasions over the six month period. It was concluded that FTIR is a reliable method for investigating carnobacterial classification, and may have further potential as a rapid method for use in Carnobacterium identification.     

Rapid characterisation of deep-sea actinomycetes for biotechnology screening programmes

A continual need in natural product discovery is dereplication, that is the ability to exclude previously tested microorganisms from screening programmes. Whole-cell fingerprinting techniques offer an ideal solution to this problem because of their rapidity and reproducibility, dependence on small samples, and automation. One such technique, Curie-point pyrolysis mass spectrometry (PyMS), has been deployed for the characterisation of a unique collection of actinomycetes recovered from Pacific Ocean sediments approximately 2000 to 6500 m below sea level. This paper addresses the question: to what extent are pyrogroups, defined on the basis of PyMS fingerprinting, related to classifications derived from more conventional microbial systematics? A collection of 44 randomly chosen deep-sea rhodococci were coded and subjected to a double-blind PyMS and numerical taxonomic (NT) analysis; the latter sorted the strains into clusters (taxospecies) using large sets of equally weighted phenotypic data. At the end of the experiment the codes were disclosed and the NT classification shown to generate 6 homogeneous clusters corresponding to different deep-sea sites. The matching of these clusters with the resulting pyrogroups was very high with an overall congruence of nearly 98%. Thus, PyMS characterisation is directly ascribable to the phenotypic variation being sought for biotechnology screens. Moreover, the exquisite discriminatory power of PyMS readily revealed infraspecific diversity in these industrially important bacteria.     

Prediction of Cell Wall Properties and Response to Deconstruction Using Alkaline Pretreatment in Diverse Maize Genotypes Using Py-MBMS and NIR

In this work, we explore the ability of several characterization approaches for phenotyping to extract information about plant cell wall properties in diverse maize genotypes with the goal of identifying approaches that could be used to predict the plant’s response to deconstruction in a biomass-to-biofuel process. Specifically, a maize diversity panel was subjected to two high-throughput biomass characterization approaches, pyrolysis molecular beam mass spectrometry (py-MBMS) and near-infrared (NIR) spectroscopy, and chemometric models to predict a number of plant cell wall properties as well as enzymatic hydrolysis yields of glucose following either no pretreatment or with mild alkaline pretreatment. These were compared to multiple linear regression (MLR) models developed from quantified properties. We were able to demonstrate that direct correlations to specific mass spectrometry ions from pyrolysis as well as characteristic regions of the second derivative of the NIR spectrum regions were comparable in their predictive capability to partial least squares (PLS) models for p-coumarate content, while the direct correlation to the spectral data was superior to the PLS for Klason lignin content and guaiacyl monomer release by thioacidolysis as assessed by cross-validation. The PLS models for prediction of hydrolysis yields using either py-MBMS or NIR spectra were superior to MLR models based on quantified properties for unpretreated biomass. However, the PLS models using the two high-throughput characterization approaches could not predict hydrolysis following alkaline pretreatment while MLR models based on quantified properties could. This is likely a consequence of quantified properties including some assessments of pretreated biomass, while the py-MBMS and NIR only utilized untreated biomass.     

Assessment of respiratory system mechanics by artificial neural networks: an exploratory study.

We evaluated 1) the performance of an artificial neural network (ANN)-based technology in assessing the respiratory system resistance (Rrs) and compliance (Crs) in a porcine model of acute lung injury and 2) the possibility of using, for ANN training, signals coming from an electrical analog (EA) of the lung. Two differently experienced ANNs were compared. One ANN (ANN(BIO)) was trained on tracings recorded at different time points after the administration of oleic acid in 10 anesthetized and paralyzed pigs during constant-flow mechanical ventilation. A second ANN (ANN(MOD)) was trained on EA simulations. Both ANNs were evaluated prospectively on data coming from four different pigs. Linear regression between ANN output and manually computed mechanics showed a regression coefficient (R) of 0.98 for both ANNs in assessing Crs. On Rrs, ANN(BIO) showed a performance expressed by R = 0.40 and ANN(MOD) by R = 0.61. These results suggest that ANNs can learn to assess the respiratory system mechanics during mechanical ventilation but that the assessment of resistance and compliance by ANNs may require different approaches.     

Pyrolysis mass spectrometry as a method for inter-strain discrimination of Candida albicans

A claim that Candida albicans strains NCPF 3153 and B311 were identical was investigated. Authentic strains were shown to be distinct (P less than 0.1%) by pyrolysis mass spectrometry (PyMS). Of twelve strains, provided as clones of NCPF 3153, seven were authenticated, one yielded an equivocal result and four were distinct from both NCPF 3153 and B311. Of eight B311 clones, six were authenticated and two yielded equivocal results. Although five non-C. albicans yeast strains were identified as distinct from B311 and NCPF 3153, Torulopsis glabrata NCPF 3240 was identified as B311, and one clinical isolate of C. albicans as NCPF 3153. This could be explained by the specificity of the mathematical analysis for discrimination between the authentic strains.     

Characterizing and Predicting Submovements during Human Three-Dimensional Arm Reaches

We have demonstrated that 3D target-oriented human arm reaches can be represented as linear combinations of discrete submovements, where the submovements are a set of minimum-jerk basis functions for the reaches. We have also demonstrated the ability of deterministic feed-forward Artificial Neural Networks (ANNs) to predict the parameters of the submovements. ANNs were trained using kinematic data obtained experimentally from five human participants making target-directed movements that were decomposed offline into minimum-jerk submovements using an optimization algorithm. Under cross-validation, the ANNs were able to accurately predict the parameters (initiation-time, amplitude, and duration) of the individual submovements. We also demonstrated that the ANNs can together form a closed-loop model of human reaching capable of predicting 3D trajectories with VAF >95.9% and RMSE ≤4.32 cm relative to the actual recorded trajectories. This closed-loop model is a step towards a practical arm trajectory generator based on submovements, and should be useful for the development of future arm prosthetic devices that are controlled by brain computer interfaces or other user interfaces.