Sub-exponential Time Parameterized Algorithms for Graph Layout Problems on Digraphs with Bounded Independence Number.

Fradkin and Seymour (J Comb Theory Ser B 110:19-46, 2015) defined the class of digraphs of bounded independence number as a generalization of the class of tournaments. They argued that the class of digraphs of bounded independence number is structured enough to be exploited algorithmically. In this paper, we further strengthen this belief by showing that several cut problems that admit sub-exponential time parameterized algorithms (a trait uncommon to parameterized algorithms) on tournaments, including Directed Feedback Arc Set, Directed Cutwidth and Optimal Linear Arrangement, also admit such algorithms on digraphs of bounded independence number.

Facilitating COVID recognition from X-rays with computer vision models and transfer learning.

Multimedia data plays an important role in medicine and healthcare since EHR (Electronic Health Records) entail complex images and videos for analyzing patient data. In this article, we hypothesize that transfer learning with computer vision can be adequately harnessed on such data, more specifically chest X-rays, to learn from a few images for assisting accurate, efficient recognition of COVID. While researchers have analyzed medical data (including COVID data) using computer vision models, the main contributions of our study entail the following.

Efficiently quantifying DNA methylation for bulk- and single-cell bisulfite data.

Motivation: DNA CpG methylation (CpGm) has proven to be a crucial epigenetic factor in the mammalian gene regulatory system. Assessment of DNA CpG methylation values via whole-genome bisulfite sequencing (WGBS) is, however, computationally extremely demanding.

Results: We present FAst MEthylation calling (FAME), the first approach to quantify CpGm values directly from bulk or single-cell WGBS reads without intermediate output files.

Novel multivariate methods to track frequency shifts of neural oscillations in EEG/MEG recordings.

Instantaneous and peak frequency changes in neural oscillations have been linked to many perceptual, motor, and cognitive processes. Yet, the majority of such studies have been performed in sensor space and only occasionally in source space. Furthermore, both terms have been used interchangeably in the literature, although they do not reflect the same aspect of neural oscillations.

Canonical Response Parameterization: Quantifying the structure of responses to single-pulse intracranial electrical brain stimulation.

Single-pulse electrical stimulation in the nervous system, often called cortico-cortical evoked potential (CCEP) measurement, is an important technique to understand how brain regions interact with one another. Voltages are measured from implanted electrodes in one brain area while stimulating another with brief current impulses separated by several seconds. Historically, researchers have tried to understand the significance of evoked voltage polyphasic deflections by visual inspection, but no general-purpose tool has emerged to understand their shapes or describe them mathematically.

Reconstructing Kernel-Based Machine Learning Force Fields with Superlinear Convergence.

Kernel machines have sustained continuous progress in the field of quantum chemistry. In particular, they have proven to be successful in the low-data regime of force field reconstruction. This is because many equivariances and invariances due to physical symmetries can be incorporated into the kernel function to compensate for much larger data sets.

Responsible model deployment via model-agnostic uncertainty learning.

Reliably predicting potential failure risks of machine learning (ML) systems when deployed with production data is a crucial aspect of trustworthy AI. This paper introduces the , a novel post-hoc for estimating failure risks and predictive uncertainties of black-box classification model. In addition to providing a , the decomposes the uncertainty estimates into aleatoric and epistemic uncertainty components, thus giving informative insights into the sources of uncertainty inducing the failures.

Accurate global machine learning force fields for molecules with hundreds of atoms.

Global machine learning force fields, with the capacity to capture collective interactions in molecular systems, now scale up to a few dozen atoms due to considerable growth of model complexity with system size. For larger molecules, locality assumptions are introduced, with the consequence that nonlocal interactions are not described. Here, we develop an exact iterative approach to train global symmetric gradient domain machine learning (sGDML) force fields (FFs) for several hundred atoms, without resorting to any potentially uncontrolled approximations.

Single-cell gene regulatory network prediction by explainable AI.

The molecular heterogeneity of cancer cells contributes to the often partial response to targeted therapies and relapse of disease due to the escape of resistant cell populations. While single-cell sequencing has started to improve our understanding of this heterogeneity, it offers a mostly descriptive view on cellular types and states. To obtain more functional insights, we propose scGeneRAI, an explainable deep learning approach that uses layer-wise relevance propagation (LRP) to infer gene regulatory networks from static single-cell RNA sequencing data for individual cells.

Breaking the -Barrier in the Construction of Compressed Suffix Arrays and Suffix Trees.

The suffix array, describing the lexicographical order of suffixes of a given text, and the suffix tree, a path-compressed trie of all suffixes, are the two most fundamental data structures for string processing, with plethora of applications in data compression, bioinformatics, and information retrieval. For a length- text, however, they use bits of space, which is often too costly. To address this, Grossi and Vitter [STOC 2000] and, independently, Ferragina and Manzini [FOCS 2000] introduced space-efficient versions of the suffix array, known as the (CSA) and the .

Advancing translational research in neuroscience through multi-task learning.

Translational research in neuroscience is increasingly focusing on the analysis of multi-modal data, in order to account for the biological complexity of suspected disease mechanisms. Recent advances in machine learning have the potential to substantially advance such translational research through the simultaneous analysis of different data modalities. This review focuses on one of such approaches, the so-called "multi-task learning" (MTL), and describes its potential utility for multi-modal data analyses in neuroscience.

DNA methylation-based classification of sinonasal tumors.

The diagnosis of sinonasal tumors is challenging due to a heterogeneous spectrum of various differential diagnoses as well as poorly defined, disputed entities such as sinonasal undifferentiated carcinomas (SNUCs). In this study, we apply a machine learning algorithm based on DNA methylation patterns to classify sinonasal tumors with clinical-grade reliability. We further show that sinonasal tumors with SNUC morphology are not as undifferentiated as their current terminology suggests but rather reassigned to four distinct molecular classes defined by epigenetic, mutational and proteomic profiles.

Functional analysis of structural variants in single cells using Strand-seq.

Somatic structural variants (SVs) are widespread in cancer, but their impact on disease evolution is understudied due to a lack of methods to directly characterize their functional consequences. We present a computational method, scNOVA, which uses Strand-seq to perform haplotype-aware integration of SV discovery and molecular phenotyping in single cells by using nucleosome occupancy to infer gene expression as a readout. Application to leukemias and cell lines identifies local effects of copy-balanced rearrangements on gene deregulation, and consequences of SVs on aberrant signaling pathways in subclones.

Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields.

Reconstructing force fields (FFs) from atomistic simulation data is a challenge since accurate data can be highly expensive. Here, machine learning (ML) models can help to be data economic as they can be successfully constrained using the underlying symmetry and conservation laws of physics. However, so far, every descriptor newly proposed for an ML model has required a cumbersome and mathematically tedious remodeling.

To pretrain or not? A systematic analysis of the benefits of pretraining in diabetic retinopathy.

There is an increasing number of medical use cases where classification algorithms based on deep neural networks reach performance levels that are competitive with human medical experts. To alleviate the challenges of small dataset sizes, these systems often rely on pretraining. In this work, we aim to assess the broader implications of these approaches in order to better understand what type of pretraining works reliably (with respect to performance, robustness, learned representation etc.

d-StructMAn: Containerized structural annotation on the scale from genetic variants to whole proteomes.

Background: Structural annotation of genetic variants in the context of intermolecular interactions and protein stability can shed light onto mechanisms of disease-related phenotypes. Three-dimensional structures of related proteins in complexes with other proteins, nucleic acids, or ligands enrich such functional interpretation, since intermolecular interactions are well conserved in evolution.

Results: We present d-StructMAn, a novel computational method that enables structural annotation of local genetic variants, such as single-nucleotide variants and in-frame indels, and implements it in a highly efficient and user-friendly tool provided as a Docker container.

2020 International brain-computer interface competition: A review.

The brain-computer interface (BCI) has been investigated as a form of communication tool between the brain and external devices. BCIs have been extended beyond communication and control over the years. The 2020 international BCI competition aimed to provide high-quality neuroscientific data for open access that could be used to evaluate the current degree of technical advances in BCI.

Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain.

Brain-age (BA) estimates based on deep learning are increasingly used as neuroimaging biomarker for brain health; however, the underlying neural features have remained unclear. We combined ensembles of convolutional neural networks with Layer-wise Relevance Propagation (LRP) to detect which brain features contribute to BA. Trained on magnetic resonance imaging (MRI) data of a population-based study (n = 2637, 18-82 years), our models estimated age accurately based on single and multiple modalities, regionally restricted and whole-brain images (mean absolute errors 3.

Parameterized Complexity of Directed Spanner Problems.

We initiate the parameterized complexity study of minimum -spanner problems on directed graphs. For a positive integer , a multiplicative -spanner of a (directed) graph is a spanning subgraph such that the distance between any two vertices in is at most times the distance between these vertices in , that is, keeps the distances in up to the distortion (or stretch) factor . An additive -spanner is defined as a spanning subgraph that keeps the distances up to the additive distortion parameter , that is, the distances in and differ by at most .

BIGDML-Towards accurate quantum machine learning force fields for materials.

Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Currently, MLFFs often introduce tradeoffs that restrict their practical applicability to small subsets of chemical space or require exhaustive datasets for training. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning (BIGDML) approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 geometries for materials including pristine and defect-containing 2D and 3D semiconductors and metals, as well as chemisorbed and physisorbed atomic and molecular adsorbates on surfaces.

Respiratory viruses dynamics and interactions: ten years of surveillance in central Europe.

Background: Lower respiratory tract infections are among the main causes of death. Although there are many respiratory viruses, diagnostic efforts are focused mainly on influenza. The Respiratory Viruses Network (RespVir) collects infection data, primarily from German university hospitals, for a high diversity of infections by respiratory pathogens.

Patient-level proteomic network prediction by explainable artificial intelligence.

Understanding the pathological properties of dysregulated protein networks in individual patients' tumors is the basis for precision therapy. Functional experiments are commonly used, but cover only parts of the oncogenic signaling networks, whereas methods that reconstruct networks from omics data usually only predict average network features across tumors. Here, we show that the explainable AI method layer-wise relevance propagation (LRP) can infer protein interaction networks for individual patients from proteomic profiling data.

Scrutinizing XAI using linear ground-truth data with suppressor variables.

Unlabelled: Machine learning (ML) is increasingly often used to inform high-stakes decisions. As complex ML models (e.g.

Prediction Tool on Fine Particle Pollutants and Air Quality for Environmental Engineering.

This article focuses on the research, design and implementation of a prediction tool for air quality to estimate pollutant concentrations, contributing to environmental engineering. It addresses prediction of fine particle air pollutants of diameter less than 2.5 µm (particulate matter 2.