Search

Publisher Copyright: IEEE Copyright: Copyright 2021 Elsevier B.V., All rights reserved. Detecting predictive biomarkers from multi-omics data is important for precision medicine, to improve diagnostics of complex diseases and for better treatments. This needs substantial experimental efforts that are made difficult by the heterogeneity of cell lines and huge cost. An effective solution is to build a computational model over the diverse omics data, including genomic, molecular, and environmental information. However, choosing informative and reliable data sources from among the different types of data is a challenging problem. We propose DIVERSE, a framework of Bayesian importance-weighted tri- and bi-matrix factorization(DIVERSE3 or DIVERSE2) to predict drug responses from data of cell lines, drugs, and gene interactions. DIVERSE integrates the data sources systematically, in a step-wise manner, examining the importance of each added data set in turn. More specifically, we sequentially integrate five different data sets, which have not all been combined in earlier bioinformatic methods for predicting drug responses. Empirical experiments show that DIVERSE clearly outperformed five other methods including three state-of-the-art approaches, under cross-validation, particularly in out-of-matrix prediction, which is closer to the setting of real use cases and more challenging than simpler in-matrix prediction. Additionally, case studies for discovering new drugs further confirmed the performance advantage of DIVERSE.

openaire: EC/H2020/826266/EU//CO-ADAPT Everyday digital tasks can highly benefit from systems that recommend the right information to use at the right time. However, existing solutions typically support only specific applications and tasks. In this demo, we showcase EntityBot, a system that captures context across application boundaries and recommends information entities related to the current task. The user's digital activity is continuously monitored by capturing all content on the computer screen using optical character recognition. This includes all applications and services being used and specific to individuals' computer usages such as instant messaging, emailing, web browsing, and word processing. A linear model is then applied to detect the user's task context to retrieve entities such as applications, documents, contact information, and several keywords determining the task. The system has been evaluated with real-world tasks, demonstrating that the recommendation had an impact on the tasks and led to high user satisfaction.

Publisher Copyright: © 2019 The Author(s). Copyright: Copyright 2021 Elsevier B.V., All rights reserved. Motivation: Adverse drug reaction (ADR) or drug side effect studies play a crucial role in drug discovery. Recently, with the rapid increase of both clinical and non-clinical data, machine learning methods have emerged as prominent tools to support analyzing and predicting ADRs. Nonetheless, there are still remaining challenges in ADR studies. Results: In this paper, we summarized ADR data sources and review ADR studies in three tasks: Drug-ADR benchmark data creation, drug-ADR prediction and ADR mechanism analysis. We focused on machine learning methods used in each task and then compare performances of the methods on the drug-ADR prediction task. Finally, we discussed open problems for further ADR studies. Availability: Data and code are available at https://github.com/anhnda/ADRPModels.

Automated classification of building damage in remote sensing images enables the rapid and spatially extensive assessment of the impact of natural hazards, thus speeding up emergency response efforts. Convolutional neural networks (CNNs) can reach good performance on such a task in experimental settings. How CNNs perform when applied under operational emergency conditions, with unseen data and time constraints, is not well studied. This study focuses on the applicability of a CNN-based model in such scenarios. We performed experiments on 13 disasters that differ in natural hazard type, geographical location, and image parameters. The types of natural hazards were hurricanes, tornadoes, floods, tsunamis, and volcanic eruptions, which struck across North America, Central America, and Asia. We used 175,289 buildings from the xBD dataset, which contains human-annotated multiclass damage labels on high-resolution satellite imagery with red, green, and blue (RGB) bands. First, our experiments showed that the performance in terms of area under the curve does not correlate with the type of natural hazard, geographical region, and satellite parameters such as the off-nadir angle. Second, while performance differed highly between occurrences of disasters, our model still reached a high level of performance without using any labeled data of the test disaster during training. This provides the first evidence that such a model can be effectively applied under operational conditions, where labeled damage data of the disaster cannot be available timely and thus model (re-)training is not an option.

Enterococcus faecium is one of the most frequent nosocomial pathogens of hospital-acquired infections. E. faecium has gained resistance against most commonly available antibiotics, most notably, against ampicillin, gentamicin, and vancomycin, which renders infections difficult to treat. Many antibiotic resistance traits, in particular, vancomycin resistance, can be encoded in autonomous and extrachromosomal elements called plasmids. These sequences can be disseminated to other isolates by horizontal gene transfer and confer novel mechanisms to source specificity. In our study, we elucidated the total plasmid content, referred to as the plasmidome, of 1,644 E. faecium isolates by using short- and long-read whole-genome technologies with the combination of a machine-learning classifier. This was fundamental to investigate the full collection of plasmid sequences present in our collection (pan-plasmidome) and to observe the potential transfer of plasmid sequences between E. faecium hosts. We observed that E. faecium isolates from hospitalized patients carried a larger number of plasmid sequences compared to that from other sources, and they elucidated different configurations of plasmidome populations in the hospital environment. We assessed the contribution of different genomic components and observed that plasmid sequences have the highest contribution to source specificity. Our study suggests that E. faecium plasmids are regulated by complex ecological constraints rather than physical interaction between hosts., Enterococcus faecium is a gut commensal of humans and animals but is also listed on the WHO global priority list of multidrug-resistant pathogens. Many of its antibiotic resistance traits reside on plasmids and have the potential to be disseminated by horizontal gene transfer. Here, we present the first comprehensive population-wide analysis of the pan-plasmidome of a clinically important bacterium, by whole-genome sequence analysis of 1,644 isolates from hospital, commensal, and animal sources of E. faecium. Long-read sequencing on a selection of isolates resulted in the completion of 305 plasmids that exhibited high levels of sequence modularity. We further investigated the entirety of all plasmids of each isolate (plasmidome) using a combination of short-read sequencing and machine-learning classifiers. Clustering of the plasmid sequences unraveled different E. faecium populations with a clear association with hospitalized patient isolates, suggesting different optimal configurations of plasmids in the hospital environment. The characterization of these populations allowed us to identify common mechanisms of plasmid stabilization such as toxin-antitoxin systems and genes exclusively present in particular plasmidome populations exemplified by copper resistance, phosphotransferase systems, or bacteriocin genes potentially involved in niche adaptation. Based on the distribution of k-mer distances between isolates, we concluded that plasmidomes rather than chromosomes are most informative for source specificity of E. faecium.

Predicting a scene graph that captures visual entities and their interactions in an image has been considered a crucial step towards full scene comprehension. Recent scene graph generation (SGG) models have shown their capability of capturing the most frequent relations among visual entities. However, the state-of-the-art results are still far from satisfactory, e.g. models can obtain 31% in overall recall R@100, whereas the likewise important mean class-wise recall mR@100 is only around 8% on Visual Genome (VG). The discrepancy between R and mR results urges to shift the focus from pursuing a high R to a high mR with a still competitive R. We suspect that the observed discrepancy stems from both the annotation bias and sparse annotations in VG, in which many visual entity pairs are either not annotated at all or only with a single relation when multiple ones could be valid. To address this particular issue, we propose a novel SGG training scheme that capitalizes on self-learned knowledge. It involves two relation classifiers, one offering a less biased setting for the other to base on. The proposed scheme can be applied to most of the existing SGG models and is straightforward to implement. We observe significant relative improvements in mR (between +6.6% and +20.4%) and competitive or better R (between -2.4% and 0.3%) across all standard SGG tasks., Comment: accepted to BMVC2020

In this paper we address the problem of establishing correspondences between different instances of the same object. The problem is posed as finding the geometric transformation that aligns a given image pair. We use a convolutional neural network (CNN) to directly regress the parameters of the transformation model. The alignment problem is defined in the setting where an unordered set of semantic key-points per image are available, but, without the correspondence information. To this end we propose a novel loss function based on cyclic consistency that solves this 2D point set registration problem by inferring the optimal geometric transformation model parameters. We train and test our approach on a standard benchmark dataset Proposal-Flow (PF-PASCAL)\cite{proposal_flow}. The proposed approach achieves state-of-the-art results demonstrating the effectiveness of the method. In addition, we show our approach further benefits from additional training samples in PF-PASCAL generated by using category level information., Comment: Accepted to WACV 2019

openaire: EC/H2020/780069/EU//MeMAD Convolutional neural networks (CNNs) have recently achieved outstanding results for various vision tasks, including indoor scene understanding. The de facto practice employed by state-of-the-art indoor scene recognition approaches is to use RGB pixel values as input to CNN models that are trained on large amounts of labeled data (ImageNet or Places). Here, we investigate CNN architectures by augmenting RGB images with estimated depth and texture information, as multiple streams, for monocular indoor scene recognition. First, we exploit the recent advancements in the field of depth estimation from monocular images and use the estimated depth information to train a CNN model for learning deep depth features. Second, we train a CNN model to exploit the successful Local Binary Patterns (LBP) by using mapped coded images with explicit LBP encoding to capture texture information available in indoor scenes. We further investigate different fusion strategies to combine the learned deep depth and texture streams with the traditional RGB stream. Comprehensive experiments are performed on three indoor scene classification benchmarks: MIT-67, OCIS and SUN-397. The proposed multi-stream network significantly outperforms the standard RGB network by achieving an absolute gain of 9.3%, 4.7%, 7.3% on the MIT-67, OCIS and SUN-397 datasets respectively.

Approximate Bayesian computation (ABC) and other likelihood-free inference methods have gained popularity in the last decade, as they allow rigorous statistical inference for complex models without analytically tractable likelihood functions. A key component for accurate inference with ABC is the choice of summary statistics, which summarize the information in the data, but at the same time should be low-dimensional for efficiency. Several dimension reduction techniques have been introduced to automatically construct informative and low-dimensional summaries from a possibly large pool of candidate summaries. Projection-based methods, which are based on learning simple functional relationships from the summaries to parameters, are widely used and usually perform well, but might fail when the assumptions behind the transformation are not satisfied. We introduce a localization strategy for any projection-based dimension reduction method, in which the transformation is estimated in the neighborhood of the observed data instead of the whole space. Localization strategies have been suggested before, but the performance of the transformed summaries outside the local neighborhood has not been guaranteed. In our localization approach the transformation is validated and optimized over validation datasets, ensuring reliable performance. We demonstrate the improvement in the estimation accuracy for localized versions of linear regression and partial least squares, for three different models of varying complexity.

The notorious incident of sudden infant death syndrome (SIDS) can easily happen to a newborn due to many environmental factors. To prevent such tragic incidents from happening, we propose a multi-task deep learning framework that detects different facial traits and two life-threatening indicators, i.e. which facial parts are occluded or covered, by analyzing the infant head image. Furthermore, we extend and adapt the recently developed models that capture data-dependent uncertainty from noisy observations for our application. The experimental results show significant improvements on YunInfants dataset across most of the tasks over the models that simply adopt the regular cross-entropy losses without addressing the effect of the underlying uncertainties.

Word embedding, which encodes words into vectors, is an important starting point in natural language processing and commonly used in many text-based machine learning tasks. However, in most current word embedding approaches, the similarity in embedding space is not optimized in the learning. In this paper we propose a novel neighbor embedding method which directly learns an embedding simplex where the similarities between the mapped words are optimal in terms of minimal discrepancy to the input neighborhoods. Our method is built upon two-step random walks between words via topics and thus able to better reveal the topics among the words. Experiment results indicate that our method, compared with another existing word embedding approach, is more favorable for various queries.

Waking mental well-being is assumed to be tightly linked to sleep and the affective content of dreams. However, empirical research is scant and has mostly focused on ill-being by studying the dreams of people with psychopathology. We explored the relationship between waking well-being and dream affect by measuring not only symptoms of ill-being but also different types and components of well-being. Importantly, this is the first time peace of mind was investigated as a distinct aspect of well-being in a Western sample and in relation to dream content. Healthy participants completed a well-being questionnaire, followed by a three-week daily dream diary and ratings of dream affect. Multilevel analyses showed that peace of mind was related to positive dream affect, whereas symptoms of anxiety were related to negative dream affect. Moreover, waking measures were better related to affect expressed in dream reports rather than participants’ self-ratings of dream affect. We propose that whereas anxiety may reflect affect dysregulation in waking and dreaming, peace of mind reflects enhanced affect regulation in both states of consciousness. Therefore, dream reports may possibly serve as markers of mental health. Finally, our study shows that peace of mind complements existing conceptualizations and measures of well-being.

This paper describes the MeMAD project entry to the WMT Multimodal Machine Translation Shared Task. We propose adapting the Transformer neural machine translation (NMT) architecture to a multi-modal setting. In this paper, we also describe the preliminary experiments with text-only translation systems leading us up to this choice. We have the top scoring system for both English-to-German and English-to-French, according to the automatic metrics for flickr18. Our experiments show that the effect of the visual features in our system is small. Our largest gains come from the quality of the underlying text-only NMT system. We find that appropriate use of additional data is effective., To appear in WMT18

openaire: EC/H2020/780069/EU//MeMAD This year, the PicSOM group participated only in the Video to Text (VTT), Description Generation subtask. For our submitted runs we used either the MSR-VTT dataset only, or MS COCO and MSR-VTT jointly for training. We used LSTM recurrent neural networks to generate descriptions based on multi-modal features extracted from the videos. We submitted four runs: • PICSOM_1: uses ResNet features for initialising the LSTM generator, and object and scene-type detection features as persistent input to the generator which is trained on MS COCO + MSR-VTT, • PICSOM_2: uses ResNet and object detection features for initialisation, and is trained on MS COCO + MSR-VTT, this is the only run based on our new PyTorch codebase, • PICSOM_3: uses ResNet and video category features for initialisation, and trajectory and audio-visual embedding features for persistent features, trained on MSR-VTT only, • PICSOM_4: is the same as PICSOM_3 except that the audio-visual embedding feature has been replaced with audio class detection outputs. The most significant difference between our runs came from expanding the original MSR-VTT training dataset by including MS COCO, which contains images annotated with captions. Having a larger and more diverse training set seems to bring larger improvements to the performance measures than using more advanced features. This finding has been confirmed also by our post-submission experiments that we are still continuing.

openaire: EC/H2020/665501/EU//PEGASUS-2 The exploration of high-dimensional real-valued data is one of the fundamental exploratory data analysis (EDA) tasks. Existing methods use predefined criteria for the representation of data. There is a lack of methods eliciting the user's knowledge from the data and showing patterns the user does not know yet. We provide a theoretical model where the user can input the patterns she has learned as knowledge. The background knowledge is used to find a MaxEnt distribution of the data, and the user is shown maximally informative projections in which the MaxEnt distribution and the data differ the most. We provide an interactive open source EDA system, study its performance, and present use cases on real data.

We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks

Counting the linear extensions of a given partial order not only has several applications in artificial intelligence but also represents a hard problem that challenges modern paradigms for approximate counting. Recently, Talvitie et al. (AAAI 2018) showed that an exponential time scheme beats the fastest known polynomial time schemes in practice, even if allowing hours of running time. Here, we present a novel scheme, relaxation Tootsie Pop, which in our experiments exhibits polynomial characteristics and significantly outperforms previous schemes. We also instantiate state-of-the-art model counters for CNF formulas; two natural encodings yield schemes that, however, are inferior to the more specialized schemes.

openaire: EC/H2020/780069/EU//MeMAD In this paper, we present the Predicting Media Memorability task, which is proposed as part of the MediaEval 2018 Benchmarking Initiative for Multimedia Evaluation. Participants are expected to design systems that automatically predict memorability scores for videos, which reflect the probability of a video being remembered. In contrast to previous work in image memorability prediction, where memorability was measured a few minutes after memorization, the proposed dataset comes with "short-term" and "long-term" memorability annotations. All task characteristics are described, namely: the task’s challenges and breakthrough, the released data set and ground truth, the required runs and the evaluation metrics.

Best student paper of the conference Annotating genes/proteins is a vital issue in biology. Particularly we focus on human proteins and medical annotation, which both are important. The most proper data for our annotation is human phenotype ontology (HPO), which are sparse but reliable (well-curated). Existing approaches for this problem are feature-based or network-based. The feature-based approach can incorporate a variety of information, by which this approach is more appropriate for noisy data than reliable data, while the network-based approach is not necessarily useful for sparse data. Low-rank approximation is very powerful for both sparse and reliable data. We thus propose to use matrix factorization to approximate the input annotation matrix (proteins × HPO terms) by factorized low-rank matrices. We further incorporate network information, i.e. protein-protein network (PPN) and network from HPO (NHPO), into the framework of matrix factorization as graph regularization over the two low-rank matrices. That is, the input annotation matrix is factorized into two low-rank factor matrices so that they can be smooth over PPN and NHPO. We call our software of implementing the above method “AiProAnnotator”, which in this paper has been empirically examined using the latest HPO data extensively under various experimental settings, including performance comparison under cross-validation, computation time and case studies, etc. Experimental results showed the high predictive performance and time efficiency of AiProAnnotator clearly.

This paper provides a description of the MediaEval 2018 “Emotional Impact of Movies task". It continues to build on last year’s edition, integrating the feedback of previous participants. The goal is to create systems that automatically predict the emotional impact that video content will have on viewers, in terms of valence, arousal and fear. Here we provide a description of the use case, task challenges, dataset and ground truth, task run requirements and evaluation metrics.

We analyse a linear regression problem with nonconvex regularization called smoothly clipped absolute deviation (SCAD) under an overcomplete Gaussian basis for Gaussian random data. We propose an approximate message passing (AMP) algorithm considering nonconvex regularization, namely SCAD-AMP, and analytically show that the stability condition corresponds to the de Almeida-Thouless condition in spin glass literature. Through asymptotic analysis, we show the correspondence between the density evolution of SCAD-AMP and the replica symmetric (RS) solution. Numerical experiments confirm that for a sufficiently large system size, SCADAMP achieves the optimal performance predicted by the replica method. Through replica analysis, a phase transition between replica symmetric and replica symmetry breaking (RSB) region is found in the parameter space of SCAD. The appearance of the RS region for a nonconvex penalty is a significant advantage that indicates the region of smooth landscape of the optimization problem. Furthermore, we analytically show that the statistical representation performance of the SCAD penalty is better than that of ℓ1-based methods, and the minimum representation error under RS assumption is obtained at the edge of the RS/RSB phase. The correspondence between the convergence of the existing coordinate descent algorithm and RS/RSB transition is also indicated.

We propose a novel method for classifying resume data of job applicants into 27 different job categories using convolutional neural networks. Since resume data is costly and hard to obtain due to its sensitive nature, we use domain adaptation. In particular, we train a classifier on a large number of freely available job description snippets and then use it to classify resume data. We empirically verify a reasonable classification performance of our approach despite having only a small amount of labeled resume data available., Comment: To be published in AIST proceedings: Springer's Lecture Notes in Computer Science (LNCS) series