Dataset Information

Novel Use of Proteomic Profiles in a Convex-Hull Ensemble Classifier to Predict Gynecological Cancer Patients' Susceptibility to Gastrointestinal Mucositis as Side Effect of Radiation Therapy.

ABSTRACT: BACKGROUND:Whole-pelvis radiation therapy is common practice in the post-surgical treatment of cervical and endometrial cancer. Gastrointestinal mucositis is an adverse side effect of radiation therapy, and is a primary concern in patient management. We investigate whether proteomic information obtained from blood samples drawn from patients scheduled to receive radiation therapy for gynecological cancers could be used to predict which patients are most susceptible to radiation-induced gastrointestinal mucositis, in order to improve the individualization of radiation therapy. METHODS:We use 132 proteins measured on 17 gynecological cancer patients in a convex-hull-based, selective-voting ensemble classifier to classify each patient into one of two classes: patients who would not (class 1) or would (class 2) develop gastrointestinal mucositis. We employ 20 repetitions of 10-fold cross-validation to measure classification accuracy. RESULTS:We achieved a 95% confidence interval on average prediction accuracy of (0.711, 0.771) using pre-radiation proteomic profiles to predict which patients would experience gastrointestinal mucositis. Pathway analysis of the 12 most prominent proteins indicated that they could be assembled into a single interaction network with direct associations. The function associated with the highest number of these 12 proteins was cell-to-cell signaling and interaction. CONCLUSIONS:Pre-radiation proteomic profiles have the potential to classify cervical/endometrial cancer patients with high accuracy as to their susceptibility to gastrointestinal mucositis following radiation therapy. Further study of the network of 12 identified proteins is warranted with a larger patient sample to confirm that these proteins are predictive of gastrointestinal mucositis in this patient population.

SUBMITTER: Kodell RL

PROVIDER: S-EPMC4587761 | biostudies-literature | 2015 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Novel Use of Proteomic Profiles in a Convex-Hull Ensemble Classifier to Predict Gynecological Cancer Patients' Susceptibility to Gastrointestinal Mucositis as Side Effect of Radiation Therapy.

Kodell Ralph L RL Haun Randy S RS Siegel Eric R ER Zhang Chuanlei C Trammel Angela B AB Hauer-Jensen Martin M Burnett Alexander F AF

Journal of proteomics & bioinformatics 20150625 7

<h4>Background</h4>Whole-pelvis radiation therapy is common practice in the post-surgical treatment of cervical and endometrial cancer. Gastrointestinal mucositis is an adverse side effect of radiation therapy, and is a primary concern in patient management. We investigate whether proteomic information obtained from blood samples drawn from patients scheduled to receive radiation therapy for gynecological cancers could be used to predict which patients are most susceptible to radiation-induced g ...[more]

PMID: 26430350

Similar Datasets

Project description:The external appearance of the dodo (Raphus cucullatus, Linnaeus, 1758) has been a source of considerable intrigue, as contemporaneous accounts or depictions are rare. The body mass of the dodo has been particularly contentious, with the flightless pigeon alternatively reconstructed as slim or fat depending upon the skeletal metric used as the basis for mass prediction. Resolving this dichotomy and obtaining a reliable estimate for mass is essential before future analyses regarding dodo life history, physiology or biomechanics can be conducted. Previous mass estimates of the dodo have relied upon predictive equations based upon hind limb dimensions of extant pigeons. Yet the hind limb proportions of dodo have been found to differ considerably from those of their modern relatives, particularly with regards to midshaft diameter. Therefore, application of predictive equations to unusually robust fossil skeletal elements may bias mass estimates. We present a whole-body computed tomography (CT) -based mass estimation technique for application to the dodo. We generate 3D volumetric renders of the articulated skeletons of 20 species of extant pigeons, and wrap minimum-fit 'convex hulls' around their bony extremities. Convex hull volume is subsequently regressed against mass to generate predictive models based upon whole skeletons. Our best-performing predictive model is characterized by high correlation coefficients and low mean squared error (a = - 2.31, b = 0.90, r (2) = 0.97, MSE = 0.0046). When applied to articulated composite skeletons of the dodo (National Museums Scotland, NMS.Z.1993.13; Natural History Museum, NHMUK A.9040 and S/1988.50.1), we estimate eviscerated body masses of 8-10.8 kg. When accounting for missing soft tissues, this may equate to live masses of 10.6-14.3 kg. Mass predictions presented here overlap at the lower end of those previously published, and support recent suggestions of a relatively slim dodo. CT-based reconstructions provide a means of objectively estimating mass and body segment properties of extinct species using whole articulated skeletons.

Dataset Information

Novel Use of Proteomic Profiles in a Convex-Hull Ensemble Classifier to Predict Gynecological Cancer Patients' Susceptibility to Gastrointestinal Mucositis as Side Effect of Radiation Therapy.

Publications

Novel Use of Proteomic Profiles in a Convex-Hull Ensemble Classifier to Predict Gynecological Cancer Patients' Susceptibility to Gastrointestinal Mucositis as Side Effect of Radiation Therapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets