Una Nueva Metodología para la identificación de Patrones de Biomarcación aplicados al Estudio, Prevención y Tratamiento Temprano de Enfermedades Crónicas


  • Roberto Carlos Herrera-Lara Escuela Politécnica Nacional
  • Luis Alberto Herrera-Lara Facultad de Ingeniería Eléctrica y Electrónica Escuela Politécnica Nacional


Resumen: Hoy en día, la aplicación de métodos matemáticos y computacionales han permitido revolucionar las investigaciones relacionadas con la medicina, quimiometria, proteómica y genomica. Algoritmos matemáticos de minería de datos y aprendizaje de maquina están abriendo las pruebas a nuevas esperanzas en la lucha contra las enfermedades crónicas como el cáncer, la diabetes, el alzheimer, cirrosis, enfermedades cardiovasculares y enfermedades suprarrenales. El presente trabajo presenta una nuevo método de selección y validación de patrones de biomarcadores aplicados al tratamiento temprano de enfermedades crónicas. La metodología propuesta en este trabajo aborda el análisis de datos procedentes directamente de los instrumentos de medición, hasta la definición de los patrones de biomarcación. Ésta basa su funcionamiento en la combinación de t–test y Mann–Whitney U test en un filtro estadístico, el cual define zonas de interés en los espectros de mediciones, luego estas zonas de interés son agrupadas y reducidas a las características cercanas a la media de cada una de estas, eliminando así la información redundante. La contribución de este trabajo radica en la estructura de este filtro estadístico, el cual posee una enorme capacidad de extracción de información a través de cálculos sencillos, en comparación a complejos algoritmos presentados en trabajos similares. Finalmente las características seleccionadas por este filtro son validadas usando clasificadores de Adaboost, TotalBoost y LPBoost probados con validación cruzada y pruebas con muestras externas. Los resultados obtenidos reflejan un rendimiento superior al 95%, además gran robustez en contra del sobreentrenamiento( Overfitting) e infraentrenamiento(Underfitting).

Abstract: Today, the application of mathematical and computational methods have revolutionized research related to medicine, chemometrics, proteomics and genomics. Mathematical algorithms for data mining and machine learning are opening the doors to new hopes in the fight against chronic diseases like cancer, diabetes, Alzheimer’s disease, cirrhosis, cardiovascular disease and adrenal diseases. This paper presents a new method for selection and validation of biomarker patterns applied to early treatment of chronic diseases. The proposed methodology deals with the analysis of data obtained directly from measuring instruments to defining patterns. It is based on the combination of t - test and Mann - Whitney U test in a statistical filter. These tests define areas of interest in the spectra of measurements, and then these areas of interest are grouped and reduced the closest feature to the average of each group of these features, thereby eliminating redundant information. The contribution of this work lies in the structure of the statistical filter, which has an enormous capacity for extracting information through simple calculations compared to complex algorithms presented in similar articles. Finally, the features selected by this methodology are validated using Adaboost, TotalBoost and LPTBoost classifiers tested using cross-validation and testing with external samples. The obtained results reflect an efficiency greater than 95%, furthermore robustness against overfitting and underfitting.


Los datos de descargas todavía no están disponibles.


BAOLIN Wu,ABBOTT Tom , FISHMAN David , McMURRAY Walter, MOR Gil,STONE Kathryn, WARD David, WILLIAMS Kenneth y ZHAO Hongyu, Comparison of statistical methods for classification of ovarian cancer using mass spectrometry data, Bioinformatics Journal, Print ISSN 1367-4803.Online ISSN 1460-2059.

WRIGHT Michael, HAN David, AEBERSOLDRuedi, Mass spectrometry-based expression profiling of clinical prostate cancer, Molecular & Cellular Proteomics Journal, Print ISSN 1535-9476, Online ISSN 1535-9484.

PAULO A. Joao, KADIYALA Vivek, BANKS A. Peter, CONWELL L. Darwinl, STTEN Hanno, Mass Spectrometry-based Quantitative Proteomic Profiling of Human Pancreatic and Hepatic Stellate Cell Lines, Genomics, Proteomics & Bioinformatics Journal, ISSN: 1672-0229.

CHO William C. S.,YIP Timothy T. C.,YIP Christine ,YIP Victor ,THULASIRAMAN Vanitha, NGAN Roger K. C., YIP Tai-Tung, LAU Wai-Hon,AU Joseph S. K., LAW Stephen C. K., CHENG Wai-Wai , MA Victor W. S., y LIM Cadmon K. P., Identification of Serum Amyloid A Protein As a Potentially Useful Biomarker to Monitor Relapse of Nasopharyngeal Cancer by Serum Proteomic Profiling, Clinical Cancer Research (CCR) Journal, Print ISSN: 1078-0432; Online ISSN: 1557-3265.

ZHANG Z, BAST RC Jr, YU Y, LI J, SOKOLL LJ, RAI AJ, ROSENZWEIG JM, CAMERON B, WANG YY, MENG XY, BERCHUCK A, VAN Haaften-Day C, HACKER NF, HW Bruijn DE, VAN der Zee AG, IJ Jacobs , ET Fung,DW Chan , Three biomarkers identified from serum proteomic analysis for the detection of early stage ovarian cancer, Cancer Research (CanRes) Journal, Print ISSN: 0008-5472; Online ISSN: 1538-7445.

Dr. PETRICOIN Emanuel F. PhD., ARDEKANI Ali M. PhD., HITT Ben A. PhD., LEVIANE Peter J. , FUSARO Vincent A., STEINBERG Seth M. PhD., MILLS Gordon B. MD., SIMONE Charles MD., FISHMAN David A. MD., KOHN Elise C. MD., LIOTTA Lance A. MD., Use of proteomic patterns in serum to identify ovarian cancer, The Lancet Journal ( Vol. 359, Issue 9306, Pages 572-577 ) , ISSN: 0140-6736.

WADSWORTH J. Trad , MD.;SOMERS Kenneth D. PhD.; BRENDAN C. Stack, Jr, MD.;CAZARES Lisa, BS.; GUNJAN Malik, PhD.; BAO Ling Adam, PhD.; WRIGHT George L. Jr, PhD.; O. John Semmes, PhD., Identification of Patients With Head and Neck Cancer Using Serum Protein Profiles, JAMA Otolaryngology–Head & Neck Surgery Journal, Print: ISSN 2168-6181, Online: ISSN 2168-619X.

O. J. Semmes, L. H. Cazares, M. D. Ward, L. Qi, M. Moody, E. Maloney, J. Morris, M. W. Trosset, M. Hisada, S. Gygi y S. Jacobson, Discrete serum protein signatures discriminate between human retrovirus-associated hematologic and neurologic disease, Leukemia Journal, ISSN: 0887-6924, EISSN: 1476-5551.

FERRARI Lorenza , SERAGLIA Roberta , ROSSI Carlo Riccardo , BERTAZZO Antonella ,LISE Mario , ALLEGRI Graziella y TRALDI Pietro ,Protein profiles in sera of patients with malignant cutaneous melanoma Rapid Communications in Mass Spectrometry Journal, ISSN: 1097-0231.

WOODING Kerry M. y AUCHUS Richard J., Mass spectrometry theory and application to adrenal diseases, Molecular and Cellular Endocrinology Journal, ISSN: 0303-7207.

McDONALD Jeffrey G., MATTHEW Susan ,AUCHUS Richard J., Steroid profiling by gas chromatography-mass spectrometry and high performance liquid chromatography-mass spectrometry for adrenal diseases, Hormones and Cancer Journal, ISSN: 1868-8497 (print version) ISSN: 1868-8500 (electronic version).

LAPOLLA Annunziata, MOLIN Laura , and TRALDI Pietroi, Protein Glycation in Diabetes as Determined by Mass Spectrometry, International Journal of Endocrinology, ISSN: 1687-8337.

LAPOLLA Annunziata,FEDELE1 D. y TRALDI Pietroi, Diabetes and mass spectrometry, Diabetes/Metabolism Research and Reviews Journal, ISSN: 1520-7560.

LI Xiang , LUO Xiangxia , LU Xin, DUAN Junguo y XU Guowang , Metabolomics study of diabetic retinopathy using gas chromatography–mass spectrometry: a comparison of stages and subtypes diagnosed by Western and Chinese medicine, Molecular BioSystems Journal, ISSN: 1742-206X (print).

FERNANDEZ Llama P., Aportaciones de la prote´omica al estudio de las enfermedades cardiovasculares, Revista Hipertensi´on y Riesgo Vascular, ISSN: 1889-1837.

CAO Yuan, HE Kun , CHENG Ming , SI Hai-Yani,ZHANG He-Lin, SONG Wei , LI Ai-Ling, HU Cheng-Jin , y WANG Na, Two Classifiers Based on Serum Peptide Pattern for Prediction of HBV-Induced Liver Cirrhosis Using MALDI-TOF MS, BioMed Research International Journal, ISSN: 2314-6133.

A. K. Batta, R. Arora, G. Salen, G. S. Tint, D. Eskreis y S. Katz, Characterization of serum and urinary bile acids in patients with primary biliary cirrhosis by gas-liquid chromatography-mass spectrometry: effect of ursodeoxycholic acid treatment, Journal of Lipid Research, ISSN 0022-2275.

MUSUNURI Sravanii , WETTERHALL Magnusl ,INGELSSON Martin , LANN-FELT Lars , ARTEMENKO Konstantin ,BERGQUIST Jonas , K´ultima Kim , and SHEVCHENKO Ganna, Quantification of the Brain Proteome in Alzheimer’s Disease Using Multiplexed Mass Spectrometry, Journal of Proteome Research, ISSN: 1535-3893.

MATTHIESEN Rune and MUTENDA Kudzai E., Introduction to Proteomics, pp. 1-37, Mass spectrometry data analysis in proteomics / edited by Rune Matthiesen, ISBN-13: 978-1-58829-563-7.

FUSHIKI Tadayoshii, FUJISAWA Hironori y EGUCHI Shinto, Identification of biomarkers from mass spectrometry data using a ”common” peak approach, BMC Bioinformatics Journal, ISSN 1471-2105.

PHAM P., A Novel Algorithm for Multi-class Cancer Diagnosis on MALDI-TOF Mass Spectra, Bioinformatics and Biomedicin IEEE Journal, pages 398-401, ISBN 978-1-4577- 1799-4, 12-15 Nov. 2011.

JELONEK Karol , ROS Malgorzata ,PIETROWSKA Monika, WIDLAK Piotr, Cancer biomarkers and mass spectrometry-based analyses of phospholipids in body fluids, Clinical Lipidology Journal, ISSN 1746-0875, pages 137-150, 2013/2.

PIETROSWSKA M., JELONEK K., MICHALAK M., ROS M.,RODZIEWICZ P.,CHMIELEWSKA K ,POLAMSKI K ,POLANSKA J,KLOSOK A Gdowicz,GIGLOK M,SUWINSKI R,TARNAWSKI R , DZIADZIUSZKO R, RZYMAN W ,WIDLAK P, Identification of serum proteome components associated with progression of non-small cell lung cancer, Acta biochimica Polonica Journal, 2014/5.

G. A. GOWDA Nagana , ZHANG Shucha,GU Haiwei , ASIAGO Vincent , SHANAIAH Narasimhamurthy, y RAFTERY Daniel, Metabolomics-Based Methods for Early Disease Diagnostics - A Review, Expert Review of Molecular Diagnostics Journal, Sep 2008; 8(5): 617–633, ISSN 1473-7159.

TARAWNEH Sandra K. Al,BORDER Michael B.,DIBBLE Christopher F., y BEN-CHARIT Sompop,Defining Salivary Biomarkers Using Mass Spectrometry-Based Proteomics - A systematic review, OMICS A Journal of Integrative Biology, ISSN: 1536-2310.

Dr. LEE Yu Hsiang, Phd. y Dr.WONG David T., DMD., DMSC. Saliva - An emerging biofluid for early detection of diseases, Am J Dent 2009;22:241-8.

KHADIR Abdelkrim and TISS Ali, Proteomics Approaches towards Early Detection and Diagnosis of Cancer, Carcinogenesis & Mutagenesis Journal, ISSN: 2157-2518.

GIL Alterovitz, RAMONI Marco F., Systems Bioinformatics: An Engineering Case-based Approach, cap. 4, Editorial: Artech House; Edici´on: Har/Cdr (1 de marzo de 2007), ISBN-10: 1857431820.

EIDHAMMER Ingvar, FLIKKA Kristian, MARTENS Lennart, MIKALSEN Svein-Ole, Computational Methods for Mass Spectrometry Proteomics , Wiley & Sons Publications, January 2008, ISBN: 978-0-470-51297-5.

EIDHAMMER Ingvar, BARSNES Harald, EGIL EIDE Geir, MARTENS Lennart, Computational and Statistical Methods for Protein Quantification by Mass Spectrometry, Wiley & Sons Publications, February 2013, ISBN: 978-1-119-96400-1.

TESSITORE Alessandra, GAGGIANO Agata, CICCIARELLI Germanai, VERZELLA Daniela, CAPECE Daria, FISCHIETTI Mariafausta, ZAZZERONI Francesca, y ALESSE Edoardo, Serum Biomarkers Identification by Mass Spectrometry in High-Mortality Tumors, International Journal of Proteomics, Volume 2013 (2013), Article ID 125858, 15 pages, ISSN 1874-3919.

SAEYS Yvan, INZA Inaki y LARRANAGA Pedro, A review of feature selection techniques in bioinformatics, Bioinformatics Journal, ISSN 1460-2059, 2007.

HE Ping, Classification Methods and Appplications to Mass Spectrometry Data, PhD. Thesis, Hong Kong Baptist University, 2005.

XU Q. ,MOHAMED S.S. ,SALAMA M.M.A.,KAMEL M. y RIZKALLA K., Mass Spectrometry-Based Proteomic Pattern Analysis for Prostate Cancer Detection Using Neural Networks with Statistical Significance Test-Based Feature Selection , Science and Technology for Humanity (TIC-STH), 2009 IEEE Toronto International Conference.

GUYON, I., GUNN, S., NIKRAVESH, M., ZADEH, L.A., Feature Extraction – Foundations and Applications, pp. 90, Studies in Fuzziness and Soft Computing, Vol. 207, Springer Publications, ISBN 978-3-540-35488-8.

SINGH Ajit P. , HALLORAN John , BILMES Jeff A. , KIRCHOFF Katrin , NOBLE William S. , Spectrum Identification using a Dynamic Bayesian Network Model of Tandem Mass Spectra, Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012), ISSN 2159-5399.

BJM Webb-Robertson , Support vector machines for improved peptide identification from tandem mass spectrometry database search, Mass Spectrometry of Proteins and peptides: Methods in Molecular Biology Journal, Vol 146. Humana Press, New York, NY, ISSN 1064-3745.

WU Baolin, ABBOTT Tom, FISHMAN David, MCMURRAY Walter, MOR Gil, STONE Kathryn, WARD David, WILLIAMS Kenneth and ZHAO Hongyu,, Comparison of statistical methods for classification of ovarian cancer using mass spectrometry data, March 6, 2003, Bioinformatics Journal, ISSN 1367-4803.

QU Yinsheng, ADAM Bao-Ling, YUTAKA Yasui, WARD Michael D., CAZARES Lisa H., SCHELLHAMMER Paul F., FENG Ziding, SEMMES O. John, and WRIGHT JR. George L., Boosted Decision Tree Analysis of Surface-enhanced Laser Desorption/Ionization Mass Spectral Serum Profiles Discriminates Prostate Cancer from Noncancer Patients, October 2002 vol. 48 no. 10 1835-1843, Clinical Chemistry Journal, ISSN 0009-9147.

NARSKY Ilya , PORTER Frank C., Statistical Analysis Techniques in Particle Physics: Fits, Density Estimation and Supervised Learning, Wiley-VCH; 1 edition (October 24, 2013), ISBN: 9783527677290 - 3527677291.

HETHELYI E., TETENYI P.,DABI E, DANOS B., The role of mass spectrometry in medicinal plant research, Biological Mass Spectrometry Journal, Online ISSN: 1096-9888.

IDOYAGA Moliona Natilde y LUXARDO Natalia, Medicinas no convencionales en cancer, Medicina (B. Aires) [online]. 2005, vol.65, n.5, pp. 390-394. ISSN 1669-9106.

MANZANO SANTANA Patricia , ORELLANA LEON Tulio , MARTINEZ MIGDALIA Miranda C., ABREU PAYROL C. Juan , RUIZ Omar , PERALTA GARCIA C. Esther L., Algunos par´ametros farmacogn´osticos de Vernonanthura patens (Kunth) H. Rob. (Asteraceae) end´emica de Ecuador, Rev Cubana Plant Med vol.18 no.1 Ciudad de la Habana ene.-mar. 2013, ISSN 1028-4796.




Cómo citar

Herrera-Lara, R. C., & Herrera-Lara, L. A. (2015). Una Nueva Metodología para la identificación de Patrones de Biomarcación aplicados al Estudio, Prevención y Tratamiento Temprano de Enfermedades Crónicas. Revista Politécnica, 35(2), 71. Recuperado a partir de https://revistapolitecnica.epn.edu.ec/ojs2/index.php/revista_politecnica2/article/view/375