Tim Wilhelm Nattkemper

Phylogenetic classification of short environmental DNA fragments

Metagenomics is providing striking insights into the ecology of microbial communities. The recently developed massively parallel 454 pyrosequencing technique gives the opportunity to rapidly obtain metagenomic sequences at a low cost and without cloning bias. However, the phylogenetic analysis of the short reads produced represents a significant computational challenge. The phylogenetic algorithm CARMA for predicting the source organisms of environmental 454 reads is described. The algorithm searches for conserved Pfam domain and protein families in the unassembled reads of a sample. These gene fragments (environmental gene tags, EGTs), are classified into a higher-order taxonomy based on the reconstruction of a phylogenetic tree of each matching Pfam family. The method exhibits high accuracy for a wide range of taxonomic groups, and EGTs as short as 27 amino acids can be phylogenetically classified up to the rank of genus. The algorithm was applied in a comparative study of three aquatic microbial samples obtained by 454 pyrosequencing. Profound differences in the taxonomic composition of these samples could be clearly revealed.

A neural classifier enabling high-throughput topological analysis of lymphocytes in tissue sections

A neural cell detection system (NCDS) for the automatic quantitation of fluorescent lymphocytes in tissue sections is presented in this paper. The system acquires visual knowledge from a set of training cell-image patches selected by a user. The trained system evaluates an image in 2 min calculating: the number, the positions, and the phenotypes of the fluorescent cells. For validation, the NCDS learning performance was tested by cross validation on digitized images of tissue sections obtained from inherently different types of tissue: diagnostic tissue sections across the human tonsil and across an inflammatory lymphocyte infiltrate of the human skeletal muscle. The NCDS detection results were compared with detection results from biomedical experts and were visually evaluated by our most experienced biomedical expert. Although the micrographs were noisy and the fluorescent cells varied in shape and size, the NCDS detected a minimum of 95% of the cells. In contrast, the cellular counts based on visual cell recognition of the experts were inconsistent and largely unreproducible for approximately 80% of the lymphocytes present in a visual field.

Construction of a Large Signature-Tagged Mini-Tn5 Transposon Library and Its Application to Mutagenesis of Sinorhizobium meliloti†

ABSTRACT Sinorhizobium meliloti genome sequence determination has provided the basis for different approaches of functional genomics for this symbiotic nitrogen-fixing alpha-proteobacterium. One of these approaches is gene disruption with subsequent analysis of mutant phenotypes. This method is efficient for single genes; however, it is laborious and time-consuming if it is used on a large scale. Here, we used a signature-tagged transposon mutagenesis method that allowed analysis of the survival and competitiveness of many mutants in a single experiment. A novel set of signature tags characterized by similar melting temperatures and G+C contents of the tag sequences was developed. The efficiencies of amplification of all tags were expected to be similar. Thus, no preselection of the tags was necessary to create a library of 412 signature-tagged transposons. To achieve high specificity of tag detection, each transposon was bar coded by two signature tags. In order to generate defined, nonredundant sets of signature-tagged S. meliloti mutants for subsequent experiments, 12,000 mutants were constructed, and insertion sites for more than 5,000 mutants were determined. One set consisting of 378 mutants was used in a validation experiment to identify mutants showing altered growth patterns.

An adaptive tissue characterization network for model-free visualization of dynamic contrast-enhanced magnetic resonance image data

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become an important source of information to aid cancer diagnosis. Nevertheless, due to the multi-temporal nature of the three-dimensional volume data obtained from DCE-MRI, evaluation of the image data is a challenging task and tools are required to support the human expert. We investigate an approach for automatic localization and characterization of suspicious lesions in DCE-MRI data. It applies an artificial neural network (ANN) architecture which combines unsupervised and supervised techniques for voxel-by-voxel classification of temporal kinetic signals. The algorithm is easy to implement, allows for fast training and application even for huge data sets and can be directly used to augment the display of DCE-MRI data. To demonstrate that the system provides a reasonable assessment of kinetic signals, the outcome is compared with the results obtained from the model-based three-time-points (3TP) technique which represents a clinical standard protocol for analysing breast cancer lesions. The evaluation based on the DCE-MRI data of 12 cases indicates that, although the ANN is trained with imprecisely labeled data, the approach leads to an outcome conforming with 3TP without presupposing an explicit model of the underlying physiological process.

Human vs. machine: evaluation of fluorescence micrographs

To enable high-throughput screening of molecular phenotypes, multi-parameter fluorescence microscopy is applied. Object of our study is lymphocytes which invade human tissue. One important basis for our collaborative project is the development of methods for automatic and accurate evaluation of fluorescence micrographs. As a part of this, we focus on the question of how to measure the accuracy of microscope image interpretation, by human experts or a computer system. Following standard practice we use methods motivated by receiver operator characteristics to discuss the accuracies of human experts and of neural network-based algorithms. For images of good quality the algorithms achieve the accuracy of the medium-skilled experts. In images with increased noise, the classifiers are outperformed by some of the experts. Furthermore, the neural network-based cell detection is much faster than the human experts.

Evaluation of radiological features for breast tumour classification in clinical screening with machine learning methods

OBJECTIVE In this work, methods utilizing supervised and unsupervised machine learning are applied to analyze radiologically derived morphological and calculated kinetic tumour features. The features are extracted from dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) time-course data. MATERIAL The DCE-MRI data of the female breast are obtained within the UK Multicenter Breast Screening Study. The group of patients imaged in this study is selected on the basis of an increased genetic risk for developing breast cancer. METHODS The k-means clustering and self-organizing maps (SOM) are applied to analyze the signal structure in terms of visualization. We employ k-nearest neighbor classifiers (k-nn), support vector machines (SVM) and decision trees (DT) to classify features using a computer aided diagnosis (CAD) approach. RESULTS Regarding the unsupervised techniques, clustering according to features indicating benign and malignant characteristics is observed to a limited extend. The supervised approaches classified the data with 74% accuracy (DT) and providing an area under the receiver-operator-characteristics (ROC) curve (AUC) of 0.88 (SVM). CONCLUSION It was found that contour and wash-out type (WOT) features determined by the radiologists lead to the best SVM classification results. Although a fast signal uptake in early time-point measurements is an important feature for malignant/benign classification of tumours, our results indicate that the wash-out characteristics might be considered as important.

A Neural Network Architecture for Automatic Segmentation of Fluorescence Micrographs

Abstract A system for the automatic segmentation of fluorescence micrographs is presented. In the first step, positions of fluorescent cells are detected by a fast learning neural network, which acquires the visual knowledge from a set of training cell-image patches selected by the user. Guided by the detected cell positions the system extracts in the second step the contours of the cells. For contour extraction, a recurrent neural network model is used to approximate the cell shapes. Even though the micrographs are noisy and the fluorescent cells vary in shape and size, the system detects at minimum 95% of the cells.

Identification of Genes Relevant to Symbiosis and Competitiveness in Sinorhizobium meliloti Using Signature-Tagged Mutants

Sinorhizobium meliloti enters an endosymbiosis with alfalfa plants through the formation of nitrogen-fixing nodules. In order to identify S. meliloti genes required for symbiosis and competitiveness, a method of signature-tagged mutagenesis was used. Two sets, each consisting of 378 signature-tagged mutants with a known transposon insertion site, were used in an experiment in planta. As a result, 67 mutants showing attenuated symbiotic phenotypes were identified, including most of the exo, fix, and nif mutants in the sets. For 38 mutants in genes previously not described to be involved in competitiveness or symbiosis in S. meliloti, attenuated competitiveness phenotypes were tested individually. A large part of these phenotypes was confirmed. Moreover, additional symbiotic defects were observed for mutants in several novel genes such as infection deficiency phenotypes (ilvI and ilvD2 mutants) or delayed nodulation (pyrE, metA, thiC, thiO, and thiD mutants).

GISMO—gene identification using a support vector machine for ORF classification

We present the novel prokaryotic gene finder GISMO, which combines searches for protein family domains with composition-based classification based on a support vector machine. GISMO is highly accurate; exhibiting high sensitivity and specificity in gene identification. We found that it performs well for complete prokaryotic chromosomes, irrespective of their GC content, and also for plasmids as short as 10 kb, short genes and for genes with atypical sequence composition. Using GISMO, we found several thousand new predictions for the published genomes that are supported by extrinsic evidence, which strongly suggest that these are very likely biologically active genes. The source code for GISMO is freely available under the GPL license.

MeltDB 2.0–advances of the metabolomics software system

Motivation: The research area metabolomics achieved tremendous popularity and development in the last couple of years. Owing to its unique interdisciplinarity, it requires to combine knowledge from various scientific disciplines. Advances in the high-throughput technology and the consequently growing quality and quantity of data put new demands on applied analytical and computational methods. Exploration of finally generated and analyzed datasets furthermore relies on powerful tools for data mining and visualization. Results: To cover and keep up with these requirements, we have created MeltDB 2.0, a next-generation web application addressing storage, sharing, standardization, integration and analysis of metabolomics experiments. New features improve both efficiency and effectivity of the entire processing pipeline of chromatographic raw data from pre-processing to the derivation of new biological knowledge. First, the generation of high-quality metabolic datasets has been vastly simplified. Second, the new statistics tool box allows to investigate these datasets according to a wide spectrum of scientific and explorative questions. Availability: The system is publicly available at https://meltdb.cebitec.uni-bielefeld.de. A login is required but freely available. Contact: nkessler@cebitec.uni-bielefeld.de