Bacterial species identification from MALDI-TOF mass spectra through data analysis and machine learning

Bruyne, Katrien De; Slabbinck, Bram; Waegeman, Willem; Vauterin, Paul; Baets, Bernard De; Vandamme, Peter

doi:10.1016/j.syapm.2010.11.003

Cited by 182 publications

(127 citation statements)

References 36 publications

Supporting

Mentioning

125

Contrasting

Order By: Relevance

“…In the described method it is assumed that the spectra at the 96DWP scale contains information that allows the prediction of the productivity of the cell line at the 10 L bioreactor scale and makes no assumptions as to whether the MALDI-ToF fingerprint changes or is the same between the two scales for a given cell line. This approach has similarities to the use of intact cell MALDI-ToF profiling of bacterial strains that is used clinically, in biodefence and in the academic environment to classify and identify bacterial strains (De Bruyne et al, 2011;Lundquist et al, 2005;Panda et al, 2013;Veloo et al, 2011;Warscheid and Fenselau, 2004). The proposed approach is straightforward and rapid and based around the development of a historical database of MALDI-ToF spectra associated with subsequent productivity data at the 10 L scale to predict the performance of cell lines from the 96 DWP scale.…”

Section: Discussionmentioning

confidence: 99%

“…see (De Bruyne et al, 2011;Franco et al, 2010;Lundquist et al, 2005;Munteanu and Hopf, 2013;Panda et al, 2013;Veloo et al, 2011;Warscheid and Fenselau, 2004) and has led to a fundamental shift in the characterisation of bacteria in the clinical microbiology setting (Clark et al, 2013). Commercial software has been developed that allows the comparison of test spectra with a library of known spectra to identify bacterial strains with high precision (Bright et al, 2002;Sogawa et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rapid high-throughput characterisation, classification and selection of recombinant mammalian cell line phenotypes using intact cell MALDI-ToF mass spectrometry fingerprinting and PLS-DA modelling

Povey

O'Malley

Root

et al. 2014

Journal of Biotechnology

View full text Add to dashboard Cite

Despite many advances in the generation of high producing recombinant mammalian cell lines over the last few decades, cell line selection and development is often slowed by the inability to predict a cell line's phenotypic characteristics (e.g. growth or recombinant protein productivity) at larger scale (large volume bioreactors) using data from early cell line construction at small culture scale. Here we describe the development of an intact cell MALDI-ToF mass spectrometry fingerprinting method for mammalian cells early in the cell line construction process whereby the resulting mass spectrometry data is used to predict the phenotype of mammalian cell lines at larger culture scale using a Partial Least Squares Discriminant Analysis (PLS-DA) model. Using MALDI-ToF mass spectrometry, a library of mass spectrometry fingerprints was generated for individual cell lines at the 96 deep well plate stage of cell line development. The growth and productivity of these cell lines were evaluated in a 10 L bioreactor model of Lonza's large-scale (up to 20,000 L) fed-batch cell culture processes.Using the mass spectrometry information at the 96 deep well plate stage and phenotype information at the 10 L bioreactor scale a PLS-DA model was developed to predict the productivity of unknown cell lines at the 10 L scale based upon their MALDI-ToF fingerprint at the 96 deep well plate scale. This approach provides the basis for the very early prediction of cell lines' performance in cGMP manufacturing-scale bioreactors and the foundation for methods and models for predicting other mammalian cell phenotypes from rapid, intact-cell mass spectrometry based measurements.Keywords: Cell line development, Chinese hamster ovary cells, whole cell MALDI-ToF mass spectrometry, PLS-DA modelling, cell line prediction 3 IntroductionThe majority of recombinant protein biopharmaceuticals are produced from cultured mammalian cells (Walsh, 2010), with the most commonly used industrial mammalian cell host being the Chinese hamster ovary (CHO) cell (Kim et al., 2012). Despite the development of high throughput methods that allow the screening of many recombinant cell lines to isolate those with desirable phenotypes (e.g. high growth and productivity), the ability of such methods to select or predict the performance of a given cell line at manufacturing scale remains limited with the best cell lines at a manufacturing scale often distributed across the phenotypic performance of cell lines at smaller-scale (Porter et al., 2010a;Porter et al., 2010b). As a result, early use of a simple productivity based approach does not necessarily allow the identification of high producers in the population of cell lines, and some potentially high producers are discarded early in the process (Porter et al., 2010b). In order to address this issue, a number of proteomic, transcriptomic and metabolic based studies have now been undertaken and the subsequent data used to develop models to predict the phenotype of a given cell line (e.g. Clarke et al., 2011;Clarke...

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Rapid high-throughput characterisation, classification and selection of recombinant mammalian cell line phenotypes using intact cell MALDI-ToF mass spectrometry fingerprinting and PLS-DA modelling

Povey

O'Malley

Root

et al. 2014

Journal of Biotechnology

View full text Add to dashboard Cite

show abstract

“…Lina Savickaitė, Jelena Kopeykinienė Klaipeda University Hospital, Lithuania sample preparation, matrix solutions and organic solvents, affect the quality and reproducibility of bacterial MALDI-TOF mass spectrometry fingerprints (11)(12)(13)(14)(15)(16). With a special set of MALDI Sepsityper is possible to identify bacteria directly from the positive blood culture (17)(18)(19)(20)(21)(22)(23)(24)(25).…”

Section: An Evaluation Of Direct Identification Of Pathogens From Blomentioning

confidence: 99%

An Evaluation Of Direct Identification Of Pathogens From Blood Cultures By Maldi-Tof Mass Spectrometry

Savickaitė

Kopeykinienė

2016

Sveikatos Mokslai

View full text Add to dashboard Cite

Rapid identification of the infecting organism may aid in choosing appropriate antimicrobial therapy. We used MALDI-TOF mass spectrometry to identify bacteria directly from the positive blood culture samples (n=21). 85,71 percent of these results was identified using of MALDI-TOF mass spectrometry. Identification time of bacteria directly from the blood culture takes more than 1 hour for 27,8 percent results.

show abstract

“…Afterwards, various algorithms for cluster analysis can be applied, as well as Principal Component Analysis (Böhme et al, 2011b). In a different study, the BioNumerics 6.0 software (Applied-Maths, Sint-Martens-Latem, Belgium) was used for data analysis and machine learning for bacterial identification by MALDI-TOF MS (De Bruyne et al, 2011).…”

Section: Data Analysis and Phyloproteomicsmentioning

confidence: 99%

Species Identification of Food Spoilage and Pathogenic Bacteria by MALDI-TOF Mass Fingerprinting

Böhme¹,

Fernández-No²,

Barros‐Velázquez³

et al. 2012

Food Quality

View full text Add to dashboard Cite

Bacterial species identification from MALDI-TOF mass spectra through data analysis and machine learning

Cited by 182 publications

References 36 publications

Rapid high-throughput characterisation, classification and selection of recombinant mammalian cell line phenotypes using intact cell MALDI-ToF mass spectrometry fingerprinting and PLS-DA modelling

Rapid high-throughput characterisation, classification and selection of recombinant mammalian cell line phenotypes using intact cell MALDI-ToF mass spectrometry fingerprinting and PLS-DA modelling

An Evaluation Of Direct Identification Of Pathogens From Blood Cultures By Maldi-Tof Mass Spectrometry

Species Identification of Food Spoilage and Pathogenic Bacteria by MALDI-TOF Mass Fingerprinting

Contact Info

Product

Resources

About