Search

Abstract Biased population samples pose a prevalent problem in the social sciences. Therefore, we present two novel methods that are based on positive-unlabeled learning to mitigate bias. Both methods leverage auxiliary information from a representative data set and train machine learning classifiers to determine the sample weights. The first method, named maximum representative subsampling (MRS), uses a classifier to iteratively remove instances, by assigning a sample weight of 0, from the biased data set until it aligns with the representative one. The second method is a variant of MRS – Soft-MRS – that iteratively adapts sample weights instead of removing samples completely. To assess the effectiveness of our approach, we induced artificial bias in a public census data set and examined the corrected estimates. We compare the performance of our methods against existing techniques, evaluating the ability of sample weights created with Soft-MRS or MRS to minimize differences and improve downstream classification tasks. Lastly, we demonstrate the applicability of the proposed methods in a real-world study of resilience research, exploring the influence of resilience on voting behavior. Through our work, we address the issue of bias in social science, amongst others, and provide a versatile methodology for bias reduction based on machine learning. Based on our experiments, we recommend to use MRS for downstream classification tasks and Soft-MRS for downstream tasks where the relative bias of the dependent variable is relevant.

The circulatory lipidome is a valuable source for disease markers, but reliable marker discovery requires continuous development of lipidomic methods for large-scale clinical profiling. Here, the authors present a 4-dimensional lipidomics solution for confident and reproducible blood lipidome profiling.

Abstract Background Recent years have seen a surge of novel neural network architectures for the integration of multi-omics data for prediction. Most of the architectures include either encoders alone or encoders and decoders, i.e., autoencoders of various sorts, to transform multi-omics data into latent representations. One important parameter is the depth of integration: the point at which the latent representations are computed or merged, which can be either early, intermediate, or late. The literature on integration methods is growing steadily, however, close to nothing is known about the relative performance of these methods under fair experimental conditions and under consideration of different use cases. Results We developed a comparison framework that trains and optimizes multi-omics integration methods under equal conditions. We incorporated early integration, PCA and four recently published deep learning methods: MOLI, Super.FELT, OmiEmbed, and MOMA. Further, we devised a novel method, Omics Stacking, that combines the advantages of intermediate and late integration. Experiments were conducted on a public drug response data set with multiple omics data (somatic point mutations, somatic copy number profiles and gene expression profiles) that was obtained from cell lines, patient-derived xenografts, and patient samples. Our experiments confirmed that early integration has the lowest predictive performance. Overall, architectures that integrate triplet loss achieved the best results. Statistical differences can, overall, rarely be observed, however, in terms of the average ranks of methods, Super.FELT is consistently performing best in a cross-validation setting and Omics Stacking best in an external test set setting. Conclusions We recommend researchers to follow fair comparison protocols, as suggested in the paper. When faced with a new data set, Super.FELT is a good option in the cross-validation setting as well as Omics Stacking in the external test set setting. Statistical significances are hardly observable, despite trends in the algorithms’ rankings. Future work on refined methods for transfer learning tailored for this domain may improve the situation for external test sets. The source code of all experiments is available under https://github.com/kramerlab/Multi-Omics_analysis

Abstract In the extensive search for new physics, the precise measurement of the Higgs boson continues to play an important role. To this end, machine learning techniques have been recently applied to processes like the Higgs production via vector-boson fusion. In this paper, we propose to use algorithms for learning to rank, i.e., to rank events into a sorting order, first signal, then background, instead of algorithms for the classification into two classes, for this task. The fact that training is then performed on pairwise comparisons of signal and background events can effectively increase the amount of training data due to the quadratic number of possible combinations. This makes it robust to unbalanced data set scenarios and can improve the overall performance compared to pointwise models like the state-of-the-art boosted decision tree approach. In this work we compare our pairwise neural network algorithm, which is a combination of a convolutional neural network and the DirectRanker, with convolutional neural networks, multilayer perceptrons or boosted decision trees, which are commonly used algorithms in multiple Higgs production channels. Furthermore, we use so-called transfer learning techniques to improve overall performance on different data types.

Abstract Many bird species have the ability to navigate home after being brought to a remote, even unfamiliar location. Environmental odours have been demonstrated to be critical to homeward navigation in over 40 years of experiments, yet the chemical identity of the odours has remained unknown. In this study, we investigate potential chemical navigational cues by measuring volatile organic compounds (VOCs): at the birds’ home-loft; in selected regional forest environments; and from an aircraft at 180 m. The measurements showed clear regional, horizontal and vertical spatial gradients that can form the basis of an olfactory map for marine emissions (dimethyl sulphide, DMS), biogenic compounds (terpenoids) and anthropogenic mixed air (aromatic compounds), and temporal changes consistent with a sea-breeze system. Air masses trajectories are used to examine GPS tracks from released birds, suggesting that local DMS concentrations alter their flight directions in predictable ways. This dataset reveals multiple regional-scale real-world chemical gradients that can form the basis of an olfactory map suitable for homing pigeons.

Deep neural networks are widely used in pattern-recognition tasks for which a human-comprehensible, quantitative description of the data-generating process, cannot be obtained. While doing so, neural networks often produce an abstract (entangled and non-interpretable) representation of the data-generating process. This may be one of the reasons why neural networks are not yet used extensively in physics-experiment signal processing: physicists generally require their analyses to yield quantitative information about the system they study. In this article we use a deep neural network to disentangle components of oscillating time series. To this aim, we design and train the neural network on synthetic oscillating time series to perform two tasks: a regression of the signal latent parameters and signal denoising by an Autoencoder-like architecture. We show that the regression and denoising performance is similar to those of least-square curve fittings with true latent-parameters initial guesses, in spite of the neural network needing no initial guesses at all. We then explore various applications in which we believe our architecture could prove useful for time-series processing, when prior knowledge is incomplete. As an example, we employ the neural network as a preprocessing tool to inform the least-square fits when initial guesses are unknown. Moreover, we show that the regression can be performed on some latent parameters, while ignoring the existence of others. Because the Autoencoder needs no prior information about the physical model, the remaining unknown latent parameters can still be captured, thus making use of partial prior knowledge, while leaving space for data exploration and discoveries.

Classification approaches that allow to extract logical rules such as decision trees are often considered to be more interpretable than neural networks. Also, logical rules are comparatively easy to verify with any possible input. This is an important part in systems that aim to ensure correct operation of a given model. However, for high-dimensional input data such as images, the individual symbols, i.e. pixels, are not easily interpretable. Therefore, rule-based approaches are not typically used for this kind of high-dimensional data. We introduce the concept of first-order convolutional rules, which are logical rules that can be extracted using a convolutional neural network (CNN), and whose complexity depends on the size of the convolutional filter and not on the dimensionality of the input. Our approach is based on rule extraction from binary neural networks with stochastic local search. We show how to extract rules that are not necessarily short, but characteristic of the input, and easy to visualize. Our experiments show that the proposed approach is able to model the functionality of the neural network while at the same time producing interpretable logical rules. Thus, we demonstrate the potential of rule-based approaches for images which allows to combine advantages of neural networks and rule learning.

The purpose of this study is to understand, compare, and contrast professional experiences, perceptions, and beliefs among personnel in academic libraries in the USA and in Germany, which may inform future library and librarian collaborations between the two countries. Notable findings include differences in: respondents’ professional backgrounds; services offered by, and perceived adequacy and support of, respondents’ libraries; and views of the library profession and its future.

Spontaneous electroencephalogram (EEG) and auditory evoked potentials (AEP) have been suggested to monitor the level of consciousness during anesthesia. As both signals reflect different neuronal pathways, a combination of parameters from both signals may provide broader information about the brain status during anesthesia. Appropriate parameter selection and combination to a single index is crucial to take advantage of this potential. The field of machine learning offers algorithms for both parameter selection and combination. In this study, several established machine learning approaches including a method for the selection of suitable signal parameters and classification algorithms are applied to construct an index which predicts responsiveness in anesthetized patients. The present analysis considers several classification algorithms, among those support vector machines, artificial neural networks and Bayesian learning algorithms. On the basis of data from the transition between consciousness and unconsciousness, a combination of EEG and AEP signal parameters developed with automated methods provides a maximum prediction probability of 0.935, which is higher than 0.916 (for EEG parameters) and 0.880 (for AEP parameters) using a cross-validation approach. This suggests that machine learning techniques can successfully be applied to develop an improved combined EEG and AEP parameter to separate consciousness from unconsciousness.

1.AbstractInterest is increasing in the development of non-animal methods for toxicological evaluations. These methods are however, particularly challenging for complex toxicological endpoints such as repeated dose toxicity. European Legislation, e.g. the European Union´s Cosmetic Directive and REACH, demands the use of alternative methods. Frameworks, such as the Read-across Assessment Framework or the Adverse Outcome Pathway Knowledge Base, support the development of these methods. The aim of the project presented in this publication was to develop substance categories for a read-across with complex endpoints of toxicity based on existing databases. The basic conceptual approach was to combine structural similarity with shared mechanisms of action. Substances with similar chemical structure and toxicological profile form candidate categories suitable for read-across. We combined two databases on repeated dose toxicity, RepDose database and ELINCS database to form a common database for the identification of categories. The resulting database contained physicochemical, structural and toxicological data, which were refined and curated for cluster analyses. We applied the Predictive Clustering Tree (PCT) approach for clustering chemicals based on structural and on toxicological information to detect groups of chemicals with similar toxic profiles and pathways/mechanisms of toxicity. As many of the experimental toxicity values were not available, this data was imputed by predicting them with a multi-label classification method, prior to clustering. The clustering results were evaluated by assessing chemical and toxicological similarities with the aim of identifying clusters with a concordance between structural information and toxicity profiles/mechanisms. From these chosen clusters, seven were selected for a quantitative read-across, based on a small ratio of NOAEL of the members with the highest and the lowest NOAEL in the cluster (

Design Considerations for DDI-Based Data Systems

We present a method to discover discriminative brain metabolism patterns in [18F] fluorodeoxyglucose positron emission tomography (PET) scans, facilitating the clinical diagnosis of Alzheimer's disease. In the work, the term "pattern" stands for a certain brain region that characterizes a target group of patients and can be used for a classification as well as interpretation purposes. Thus, it can be understood as a so-called "region of interest (ROI)". In the literature, an ROI is often found by a given brain atlas that defines a number of brain regions, which corresponds to an anatomical approach. The present work introduces a semi-data-driven approach that is based on learning the characteristics of the given data, given some prior anatomical knowledge. A Gaussian Mixture Model (GMM) and model selection are combined to return a clustering of voxels that may serve for the definition of ROIs. Experiments on both an in-house dataset and data of the Alzheimer's Disease Neuroimaging Initiative (ADNI) suggest that the proposed approach arrives at a better diagnosis than a merely anatomical approach or conventional statistical hypothesis testing.

Network inference deals with the reconstruction of biological networks from experimental data. A variety of different reverse engineering techniques are available; they differ in the underlying assumptions and mathematical models used. One common problem for all approaches stems from the complexity of the task, due to the combinatorial explosion of different network topologies for increasing network size. To handle this problem, constraints are frequently used, for example on the node degree, number of edges, or constraints on regulation functions between network components. We propose to exploit topological considerations in the inference of gene regulatory networks. Such systems are often controlled by a small number of hub genes, while most other genes have only limited influence on the network's dynamic. We model gene regulation using a Bayesian network with discrete, Boolean nodes. A hierarchical prior is employed to identify hub genes. The first layer of the prior is used to regularize weights on edges emanating from one specific node. A second prior on hyperparameters controls the magnitude of the former regularization for different nodes. The net effect is that central nodes tend to form in reconstructed networks. Network reconstruction is then performed by maximization of or sampling from the posterior distribution. We evaluate our approach on simulated and real experimental data, indicating that we can reconstruct main regulatory interactions from the data. We furthermore compare our approach to other state-of-the art methods, showing superior performance in identifying hubs. Using a large publicly available dataset of over 800 cell cycle regulated genes, we are able to identify several main hub genes. Our method may thus provide a valuable tool to identify interesting candidate genes for further study. Furthermore, the approach presented may stimulate further developments in regularization methods for network reconstruction from data.

Objective:Cornell University’s Research Data Management Service Group (RDMSG) surveyed NSF principal investigators (PIs) at Cornell in order to understand how well-prepared researchers are to meet the new NSF data management planning requirement, to build our own understanding of the potential impact on campus services, and to identify service gaps. Methods: We administered a 43-question online survey, which included questions about the respondents’ research and research data, their interest in assistance with the creation of data management plans, and questions for each of the five general areas cited in the NSF’s Grant Proposal Guide (2011) section on data management plans. Results and Discussion: Respondents produce a wide variety of types and formats of data, although most expect to share relatively small amounts of data. Respondents are generally uncertain as to whether the data they produce conforms to disciplinary standards. The majority create no metadata; of those that do, most do not create metadata according to a particular standard. Most researchers do not express a need for advice regarding intellectual property issues. Researchers report using a variety of strategies (on-campus and commercial) for backing up and for providing access to their data sets. Conclusions: The overarching finding from our survey is that there is much uncertainty about what the new requirement means and how to meet it, and researchers welcome offers of assistance. To the extent that Cornell researchers are representative of NSF PIs, our findings reveal something about researchers’ readiness to meet the new requirement, and their attitudes towards it.