An integrated approach utilizing artificial neural networks and SELDI mass spectrometry for the classification of human tumours and rapid identification of potential biomarkers

MOTIVATION MALDI mass spectrometry is able to elicit macromolecular expression data from cellular material and when used in conjunction with Ciphergen protein chip technology (also referred to as SELDI-Surface Enhanced Laser Desorption/Ionization), it permits a semi-high throughput approach to be taken with respect to sample processing and data acquisition. Due to the large array of data that is generated from a single analysis (8-10000 variables using a mass range of 2-15 kDa-this paper) it is essential to implement the use of algorithms that can detect expression patterns from such large volumes of data correlating to a given biological/pathological phenotype from multiple samples. If successful, the methodology could be extrapolated to larger data sets to enable the identification of validated biomarkers correlating strongly to disease progression. This would not only serve to enable tumours to be classified according to their molecular expression profile but could also focus attention upon a relatively small number of molecules that might warrant further biochemical/molecular characterization to assess their suitability as potential therapeutic targets. RESULTS Using a multi-layer perceptron Artificial Neural Network (ANN) (Neuroshell 2) with a back propagation algorithm we have developed a prototype approach that uses a model system (comprising five low and seven high-grade human astrocytomas) to identify mass spectral peaks whose relative intensity values correlate strongly to tumour grade. Analyzing data derived from MALDI mass spectrometry in conjunction with Ciphergen protein chip technology we have used relative importance values, determined from the weights of trained ANNs (Balls et al., Water, Air Soil Pollut., 85, 1467-1472, 1996), to identify masses that accurately predict tumour grade. Implementing a three-stage procedure, we have screened a population of approximately 100000-120000 variables and identified two ions (m/z values of 13454 and 13457) whose relative intensity pattern was significantly reduced in high-grade astrocytoma. The data from this initial study suggests that application of ANN-based approaches can identify molecular ion patterns which strongly associate with disease grade and that its application to larger cohorts of patient material could potentially facilitate the rapid identification of validated biomarkers having significant clinical (i.e. diagnostic/prognostic) potential for the field of cancer biology. AVAILIBILITY: Neuroshell 2 is commercially available from ward systems.

[1]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[2]  P. Kelly,et al.  Grading of astrocytomas: A simple and reproducible method , 1988, Cancer.

[3]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[4]  Yianni Attikiouzel,et al.  Artificial Neural Networks and Breast Cancer Prognosis , 1994, Aust. Comput. J..

[5]  L. S. Adelman.  Grading astrocytomas. , 1994, Neurosurgery clinics of North America.

[6]  R. Freeman,et al.  Pyrolysis mass spectrometry. , 1995, Methods in molecular biology.

[7]  D. Palmer-Brown,et al.  Towards unravelling the complex interactions between microclimate, ozone dose, and ozone injury in clover , 1995 .

[8]  D. Kell,et al.  Pyrolysis mass spectrometry and its applications in biotechnology. , 1996, Current opinion in biotechnology.

[9]  Dominic Palmer-Brown,et al.  Modeling complex environmental data , 1997, IEEE Trans. Neural Networks.

[10]  J. Wei,et al.  Understanding artificial neural networks and exploring their potential applications for the practicing urologist. , 1998, Urology.

[11]  G. Ball,et al.  Identifying factors which modify the effects of ambient ozone on white clover (Trifolium repens) in Europe , 1998 .

[12]  J. Yates.  Mass spectrometry and the age of the proteome. , 1998, Journal of mass spectrometry : JMS.

[13]  G Reibnegger,et al.  Artificial Neural Networks in Laboratory Medicine and Medical Outcome Prediction , 1999, Clinical chemistry and laboratory medicine.

[14]  G. Wright,et al.  Proteinchip® surface enhanced laser desorption/ionization (SELDI) mass spectrometry: a novel protein biochip technology for detection of prostate cancer biomarkers in complex protein mixtures , 1999, Prostate Cancer and Prostatic Diseases.

[15]  Z. Zhang,et al.  Artificial neural networks in urology: Update 2000 , 1999, Prostate Cancer and Prostatic Diseases.

[16]  Da-Jung Ha.  The ProteinChip System from Ciphergen: a new technique for rapid, micro-scale protein biology. , 2000 .

[17]  E. Petricoin,et al.  Rapid protein display profiling of cancer progression directly from human tissue using a protein biochip , 2000 .

[18]  G. Ball,et al.  Identification of non-linear influences on the seasonal ozone dose-response of sensitive and resistant clover clones using artificial neural networks , 2000 .

[19]  Fung Et,et al.  Proteomic strategies for biomarker identification: progress and challenges. , 2000 .

[20]  G. Wright,et al.  Development of a novel proteomic approach for the detection of transitional cell carcinoma of the bladder in urine. , 2001, The American journal of pathology.

[21]  R. Tibshirani,et al.  Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implications , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[22]  H. Cai,et al.  BACE1 is the major β-secretase for generation of Aβ peptides by neurons , 2001, Nature Neuroscience.

[23]  M. Ringnér,et al.  Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks , 2001, Nature Medicine.

[24]  E. Fung,et al.  Protein biochips for differential profiling. , 2001, Current opinion in biotechnology.