Artificial Neural Networks Analysis of Surface-Enhanced Laser Desorption/Ionization Mass Spectra of Serum Protein Pattern Distinguishes Colorectal Cancer from Healthy Population

Chen, Yiding; Zheng, Shu; Yu, Jian; Hu, Xun

doi:10.1158/1078-0432.ccr-1162-03

Cited by 133 publications

(77 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chen et al (2004) also detected an elevation of a peak at 8930 m/z in samples from colon cancer patients that may be the same protein. A peak of similar mass was identified as apolipoprotein A-II in prostate cancer samples (Malik et al, 2005) and as a fragment of vitronectin in hepatocellular carcinoma samples (Paradis et al, 2005), underlining the need to validate identifications using independent assays.…”

Section: Discussionmentioning

confidence: 83%

“…This work identified some of these peaks as transferrin, a1-antitrypsin, complement C3a des-arg and apolipoprotein C1. A similar use of SELDI by Chen et al (2004), Guang et al (2004) and Yu et al (2004) suggested that SELDI profiling could be more sensitive than CEA analysis in diagnosing CRC. The data in this paper support this, but, additionally, identifies potential biomarkers, which require validation with large numbers of patients and if successful could point to the development of more widely applicable immunoassays.…”

Section: Discussionmentioning

confidence: 89%

See 1 more Smart Citation

Identification of serum biomarkers for colon cancer by proteomic analysis

et al. 2006

View full text Add to dashboard Cite

Colorectal cancer (CRC) is often diagnosed at a late stage with concomitant poor prognosis. Early detection greatly improves prognosis; however, the invasive, unpleasant and inconvenient nature of current diagnostic procedures limits their applicability. No serum-based test is currently of sufficient sensitivity or specificity for widespread use. In the best currently available blood test, carcinoembryonic antigen exhibits low sensitivity and specificity particularly in the setting of early disease. Hence, there is great need for new biomarkers for early detection of CRC. We have used surface-enhanced laser desorbtion/ionisation (SELDI) to investigate the serum proteome of 62 CRC patients and 31 noncancer subjects. We have identified proteins (complement C3a des-arg, a1-antitrypsin and transferrin) with diagnostic potential. Artificial neural networks trained using only the intensities of the SELDI peaks corresponding to identified proteins were able to classify the patients used in this study with 95% sensitivity and 91% specificity.

show abstract

Section: Discussionmentioning

confidence: 83%

Section: Discussionmentioning

confidence: 89%

Identification of serum biomarkers for colon cancer by proteomic analysis

et al. 2006

View full text Add to dashboard Cite

show abstract

“…Surface Enhanced Laser Desorption Ionisation-Time of Flight Mass Spectrometry (SELDI-TOF MS) 2,3 is being increasingly used to search for new and better tumour markers in (serum) protein profiles, for example, for ovarian, 4 breast, 5 prostate 6 and colorectal cancer. 7 Its appeal lies in the ease with which a multitude of samples can be analysed with a minimum of sample preparation in a single SELDI-TOF MS analysis. Indeed, SELDI-TOF MS has also been performed to identify biomarker proteins for early detection of RCC.…”

mentioning

confidence: 99%

Validation of SELDI-TOF MS serum protein profiles for renal cell carcinoma in new populations

Engwegen

Mehra

Haanen

et al. 2007

Laboratory Investigation

View full text Add to dashboard Cite

Currently, no suitable biomarker for the early detection or follow-up of renal cell carcinoma (RCC) is available. We aimed to validate previously reported potential serum biomarkers for RCC obtained with Surface Enhanced Laser Desorption Ionisation-Time of Flight Mass Spectrometry (SELDI-TOF MS) in our laboratory using distinct patient populations. Two sets of sera from RCC patients and healthy controls (HC) were gathered from different institutes and analysed according to published procedures. The first set (40 RCC, 32 HC) consisted of mainly presurgery samples from patients with disease stages I-IV. The second set (26 RCC, 27 HC) were mostly sera from patients with stage-IV disease, drawn after nephrectomy. Only the increased expression of the previously found serum amyloid-a (SAA) peak cluster could be validated in a similar RCC patient subset in both our populations in two independent analyses. It was seen both in earlyand late-stage disease and in pre-and postsurgery samples. These results were also confirmed by ELISA. Other previously identified biomarker candidates (mass-to-charge ratio's (m/z) 3900, 4107, 4153, 5352 and 5987) proved difficult to reproduce upon duplicate analysis. Modification of the analytical protocol for these markers resulted in their detection, but we did not achieve satisfactory classification of patients and controls with these alleged biomarkers in any of our two sample sets. Instead, two new peaks (m/z 4289 and 8151) were identified with better performance (sensitivity and specificity B65-90%) for separating patients from controls in the first sample set. Concluding, only the SAA peak cluster was validated as a robust RCC biomarker candidate, which is present in a specific subset of these patients, regardless of disease stage or nephrectomy status. In addition, two new peaks were seen which might prove useful as biomarkers, provided these are validated in new populations. Renal cell carcinoma (RCC) is difficult to diagnose at early stages due to a lack of clear clinical symptoms. When symptoms do occur, about 30% of patients already have metastatic disease. In addition, a similar part of patients with resection of localised disease will have a recurrence. 1 Therefore, a need remains for reliable markers for diagnosis and follow-up of RCC, preferably in easy-accessible body fluids. Surface Enhanced Laser Desorption Ionisation-Time of Flight Mass Spectrometry (SELDI-TOF MS) 2,3 is being increasingly used to search for new and better tumour markers in (serum) protein profiles, for example, for ovarian, 4 breast, 5 prostate 6 and colorectal cancer. 7 Its appeal lies in the ease with which a multitude of samples can be analysed with a minimum of sample preparation in a single SELDI-TOF MS analysis. Indeed, SELDI-TOF MS has also been performed to identify biomarker proteins for early detection of RCC. Two studies describe protein profiling of serum with SELDI-TOF MS. 8,9 Tolson et al 8 reported a peak cluster at a mass-to-charge ratio (m/z) of approximately 11 000 from serum amyloid a-...

show abstract

“…One such approach is proteomic profiling (Adam et al, 2002;Li et al, 2002;Kozak et al, 2003;Poon et al, 2003;Chen et al, 2004;Paradis et al, 2005;Schwegler et al, 2005;Yang et al, 2005;Ward et al, 2006a -c). We and other groups have suggested that patients with HCC may express a characteristic protein 'signature' even in the case of small tumours (Poon et al, 2003;Paradis et al, 2005;Schwegler et al, 2005;Ward et al, 2006a -c).…”

mentioning

confidence: 99%

“…These signatures are customarily detected using Surface-Enhanced Laser Desorption/ Ionisation (SELDI) technology, which permits the mass spectrum of a specific subset of serum proteins to be compared between cancer and non-cancer patients using various pattern recognition programmes. While there has been considerable controversy about the robustness of this approach, particularly with regard to its reproducibility and the techniques used to validate results (Diamandis, 2004;Petricoin et al, 2004;Ransohoff, 2004), a large body of evidence does suggest that such signatures are detectable (Adam et al, 2002;Li et al, 2002;Kozak et al, 2003;Poon et al, 2003;Chen et al, 2004;Paradis et al, 2005;Schwegler et al, 2005;Yang et al, 2005;Ward et al, 2006a -c), even if clinical utility remains to be convincingly shown.…”

mentioning

confidence: 99%

Preclinical and post-treatment changes in the HCC-associated serum proteome

et al. 2006

View full text Add to dashboard Cite

SELDI-based proteomic profiling of body fluids is currently in widespread use for cancer biomarker discovery. We have successfully used this technology for the diagnosis of hepatocellular carcinoma (HCC) in hepatitis C patients and now report its application to serial serum samples from 37 hepatitis C patients before development of HCC, with HCC and following radiofrequency ablation of the tumour. As with alpha-fetoprotein, an accepted biomarker for HCC, we hypothesised that HCC-associated proteomic features would 'return to normal' following successful treatment and the primary aim of our study was to test this hypothesis. Several SELDI peaks that changed significantly during HCC development were detected but they did not reverse following treatment. These data may be interpreted to suggest that the characteristic SELDI profile is not linearly related to tumour burden but may result from the progression of underlying liver disease or from the emergence of precancerous lesions. b2-Microglobulin, a protein previously reported to be markedly elevated in patients with HCV related HCC, was also the most significantly HCC associated proteomic feature (m/z 11720) in this study.

show abstract

Artificial Neural Networks Analysis of Surface-Enhanced Laser Desorption/Ionization Mass Spectra of Serum Protein Pattern Distinguishes Colorectal Cancer from Healthy Population

Cited by 133 publications

References 22 publications

Identification of serum biomarkers for colon cancer by proteomic analysis

Identification of serum biomarkers for colon cancer by proteomic analysis

Validation of SELDI-TOF MS serum protein profiles for renal cell carcinoma in new populations

Preclinical and post-treatment changes in the HCC-associated serum proteome

Contact Info

Product

Resources

About