Kooperativer Bibliotheksverbund

Berlin Brandenburg

and
and

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
Filter
  • Zell, Andreas  (16)
Type of Medium
Language
Year
  • 1
    Language: English
    In: Proceedings Of The 5th Asia-Pacific Bioinformatics Conference, 2007, pp.267-276
    Description: Abstract Inferring the structure of gene regulatory networks from gene expression data has attracted a growing interest during the last years. Several machine learning related methods, such as Bayesian networks, have been proposed to deal with this challenging problem. However, in many cases, network reconstructions purely based on gene expression data not lead to satisfactory results when comparing the obtained topology against a validation network. Therefore, in this paper we propose an "inverse" approach: Starting from a priori specified network topologies, we identify those parts of the network which are relevant for the gene expression data at hand. For this purpose, we employ linear ridge regression to predict the expression level of a given gene from its relevant regulators with high reliability. Calculated statistical significances of the resulting network topologies reveal that slight modifications of the pruned regulatory network enable an additional substantial improvement.
    Keywords: Contributed Papers
    ISBN: 9781860947995
    Source: World Scientific Books (World Scientific Publishing Co.)
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 2
    In: PLoS ONE, 2014, Vol.9(5)
    Description: The current gold-standard method for cancer safety assessment of drugs is a rodent two-year bioassay, which is associated with significant costs and requires testing a high number of animals over lifetime. Due to the absence of a comprehensive set of short-term assays predicting carcinogenicity, new approaches are currently being evaluated. One promising approach is toxicogenomics, which by virtue of genome-wide molecular profiling after compound treatment can lead to an increased mechanistic understanding, and potentially allow for the prediction of a carcinogenic potential via mathematical modeling. The latter typically involves the extraction of informative genes from omics datasets, which can be used to construct generalizable models allowing for the early classification of compounds with unknown carcinogenic potential. Here we formally describe and compare two novel methodologies for the reproducible extraction of characteristic mRNA signatures, which were employed to capture specific gene expression changes observed for nongenotoxic carcinogens. While the first method integrates multiple gene rankings, generated by diverse algorithms applied to data from different subsamplings of the training compounds, the second approach employs a statistical ratio for the identification of informative genes. Both methods were evaluated on a dataset obtained from the toxicogenomics database TG-GATEs to predict the outcome of a two-year bioassay based on profiles from 14-day treatments. Additionally, we applied our methods to datasets from previous studies and showed that the derived prediction models are on average more accurate than those built from the original signatures. The selected genes were mostly related to p53 signaling and to specific changes in anabolic processes or energy metabolism, which are typically observed in tumor cells. Among the genes most frequently incorporated into prediction models were Phlda3 , Cdkn1a , Akr7a3 , Ccng1 and Abcb4 .
    Keywords: Research Article ; Biology And Life Sciences ; Physical Sciences ; Computer And Information Sciences ; Medicine And Health Sciences
    E-ISSN: 1932-6203
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 3
    Language: English
    In: Analytica Chimica Acta, 2008, Vol.618(1), pp.29-34
    Description: It is known that patients suffering from cancer diseases excrete increased amounts of modified nucleosides with their urine. Especially methylated nucleosides have been proposed to be potential tumor markers for early diagnosis of cancer. For determination of nucleosides in randomly collected urine samples, the nucleosides were extracted using affinity chromatography and then analyzed via reversed phase high-performance liquid chromatography (HPLC) with UV-detection. Eleven nucleosides were quantified in urine samples from 51 breast cancer patients and 65 healthy women. The measured concentrations were used to train a Support Vector Machine (SVM) and a k-nearest-neighbor classifier (k-NN) to discriminate between healthy control subjects and patients suffering from breast cancer. Evaluations of the learned models by computing the leave-one-out error and the prediction error on an independent test set of 29 subjects (15 healthy, 14 breast cancer patients) showed that by using the eleven nucleosides, the occurrence of breast cancer could be forecasted with 86% specificity and 94% sensitivity when using an SVM and 86% for both specificity and sensitivity with the k-NN model.
    Keywords: Metabolomics ; High Performance Liquid Chromatography With Ultraviolett Detection (Hplc-Uv) ; Nucleosides ; Breast Cancer ; Support Vector Machine (Svm) ; K-Nearest-Neighbor Classifier (K-NN) ; Chemistry
    ISSN: 0003-2670
    E-ISSN: 1873-4324
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 4
    Language: English
    In: Journal of chemical information and computer sciences, 2004, Vol.44(3), pp.931-9
    Description: We show that the topological polar surface area (TPSA) descriptor and the radial distribution function (RDF) applied to electronic and steric atom properties, like the conjugated electrotopological state (CETS), are the most relevant features/descriptors for predicting the human intestinal absorption (HIA) out of a large set of 2934 features/descriptors. A HIA data set with 196 molecules with measured HIA values and 2934 features/descriptors were calculated using JOELib and MOE. We used an adaptive boosting algorithm to solve the binary classification problem (AdaBoost.M1) and Genetic Algorithms based on Shannon Entropy Cliques (GA-SEC) variants as hybrid feature selection algorithms. The selection of relevant features was applied with respect to the generalization ability of the classification model, avoiding a high variance for unseen molecules (overfitting).
    Keywords: Intestinal Absorption ; Models, Theoretical
    ISSN: 0095-2338
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 5
    Language: English
    In: QSAR & Combinatorial Science, July 2004, Vol.23(5), pp.311-318
    Description: In this paper we present a novel method for selecting descriptor subsets by means of Support Vector Machines in classification and regression – the Incremental Regularized Risk Minimization (IRRM) algorithm. In contrast to many other wrapper methods it is fully deterministic and computationally efficient. We compare our method to existing algorithms and present results on a Human Intestinal Absorption (HIA) classification data set and the Huuskonen regression data set for aqueous solubility.
    Keywords: Descriptor Selection ; Support Vector Machines ; Human Intestinal Absorption ; Aqueous Solubility
    ISSN: 1611-020X
    E-ISSN: 1611-0218
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 6
    Language: English
    In: Journal of chemical information and computer sciences, 2004, Vol.44(3), pp.921-30
    Description: The paper describes different aspects of classification models based on molecular data sets with the focus on feature selection methods. Especially model quality and avoiding a high variance on unseen data (overfitting) will be discussed with respect to the feature selection problem. We present several standard approaches and modifications of our Genetic Algorithm based on the Shannon Entropy Cliques (GA-SEC) algorithm and the extension for classification problems using boosting.
    Keywords: Chemistry ; Library & Information Science;
    ISSN: 0095-2338
    E-ISSN: 15205142
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 7
    Language: English
    In: Neural networks : the official journal of the International Neural Network Society, January 2008, Vol.21(1), pp.92-101
    Description: The forced swimming test of rats or mice is a frequently used behavioral test to evaluate compounds for antidepressant activity in vivo. The aim of this study was to replace the human observer, needed to score and analyze the behavior of animals, by a fully automated method. For this purpose, in a first step from a video recording of each rat, an activity profile was calculated, from which subsequently a set of meaningful properties was extracted. This set was finally used to train a Support Vector Machine (SVM). Furthermore, specialized kernel functions, namely the so-called time resolved p-spectrum and modified optimal assignment kernels, were developed to calculate the similarity of activity profiles. Our method allows for a very reliable discrimination of animals treated with antidepressants of different classes (tricyclics imipramine and desipramine as well as selective serotonin reuptake inhibitor, SSRI, fluoxetine) versus a vehicle-treated group. Moreover, our technique is able to classify between tricyclic antidepressants and SSRIs. The results of this work enabled the development of an automated and highly accurate behavior classification system.
    Keywords: Neural Networks (Computer) ; Swimming ; Behavior, Animal -- Physiology ; Electronic Data Processing -- Methods
    ISSN: 0893-6080
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 8
    Language: English
    In: Neural Networks, 2008, Vol.21(1), pp.92-101
    Description: The forced swimming test of rats or mice is a frequently used behavioral test to evaluate compounds for antidepressant activity in vivo. The aim of this study was to replace the human observer, needed to score and analyze the behavior of animals, by a fully automated method. For this purpose, in a first step from a video recording of each rat, an activity profile was calculated, from which subsequently a set of meaningful properties was extracted. This set was finally used to train a Support Vector Machine (SVM). Furthermore, specialized kernel functions, namely the so-called time resolved -spectrum and modified optimal assignment kernels, were developed to calculate the similarity of activity profiles. Our method allows for a very reliable discrimination of animals treated with antidepressants of different classes (tricyclics imipramine and desipramine as well as selective serotonin reuptake inhibitor, SSRI, fluoxetine) versus a vehicle-treated group. Moreover, our technique is able to classify between tricyclic antidepressants and SSRIs. The results of this work enabled the development of an automated and highly accurate behavior classification system.
    Keywords: Support Vector Machine ; Kernel ; Automated Behavior Classification ; Forced Swimming Test ; Antidepressant Activity ; Computer Science
    ISSN: 0893-6080
    E-ISSN: 1879-2782
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 9
    Language: English
    In: Biomarkers, 01 January 2008, Vol.13(4), pp.435-449
    Description: Modified nucleosides are formed post-transcriptionally in RNA. In cancer disease, the cell turnover and thus RNA metabolism is increased, yielding higher concentrations of excreted modified nucleosides. In the presented study, urinary ribonucleosides were used to differentiate between breast...
    Keywords: Medical Metabonomics ; Medical Metabolomics ; Modified Nucleosides ; Ion Trap Mass Spectrometry ; Support Vector Machine ; Cancer Diagnosis ; Medicine ; Biology
    ISSN: 1354-750X
    E-ISSN: 1366-5804
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 10
    Language: English
    In: QSAR & Combinatorial Science, March 2006, Vol.25(3), pp.205-220
    Description: We present a classification method, which is based on a coordinate‐free chemical space. Thus, it does not depend on descriptor values commonly used by coordinate‐based chemical space methods. In our method the molecular similarity of chemical structures is evaluated by a generalized maximum common graph isomorphism, which supports the usage of numerical physicochemical atom property labels in addition to discrete‐atom‐type labels. The Maximum Common Substructure (MCS) algorithm applies the Highest Scoring Common Substructure (HSCS) ranking of Sheridan and co‐workers, which penalizes discontinuous fragments. For all compared classification algorithms used in this work we analyze their usefulness based on two objectives. First, we are interested in highly accurate and general hypotheses and second, the interpretation ability is highly important to increase our structural knowledge for the ADME data sets and the activity data set investigated in this work.
    Keywords: Classification ; Coordinate‐Based Coding ; Coordinate‐Free Coding ; Data Mining ; Feature Selection ; Graph Mining ; Highest Scoring Common Substructure Hscs ; Maximum Common Substructure Mcs ; Molecular Similarity ; Pharmacophore
    ISSN: 1611-020X
    E-ISSN: 1611-0218
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
Close ⊗
This website uses cookies and the analysis tool Matomo. Further information can be found on the KOBV privacy pages