Explore the vast range of titles available.

Fluorine substituents have become a widespread and important drug component, their introduction facilitated by the development of safe and selective fluorinating agents. Organofluorine affects nearly all physical and adsorption, distribution, metabolism, and excretion properties of a lead compound. Its inductive effects are relatively well understood, enhancing bioavailability, for example, by reducing the basicity of neighboring amines. In contrast, exploration of the specific influence of carbon-fluorine single bonds on docking interactions, whether through direct contact with the protein or through stereoelectronic effects on molecular conformation of the drug, has only recently begun. Here, we review experimental progress in this vein and add complementary analysis based on comprehensive searches in the Cambridge Structural Database and the Protein Data Bank.

The predictive capabilities of Deep Neural Networks (DNNs) are well-established, yet the underlying mechanisms driving these predictions often remain opaque. The advent of Explainable Artificial Intelligence (XAI) has introduced novel methodologies to explore the reasoning behind complex model predictions of complex models. Among post-hoc attribution methods, Layer-wise Relevance Propagation (LRP) has demonstrated notable adaptability and performance for explaining individual predictions – provided the method is used to its full potential. For deeper dataset-wide and quantitative analyses, however, the manual inspection of individual attribution maps remains unnecessarily labor-intensive and time consuming. While several approaches for dataset-wide XAI-analyses have been proposed, unified and accessible implementations of such tools are still lacking. Furthermore, there is a notable absence of dedicated visualization and analysis software to support stakeholders in interpreting both local and global XAI results effectively. This gap underscores the need for comprehensive software tools that facilitate both granular and holistic understanding of model behavior, as well as easing the adaptability of XAI in applications and the sciences. To address these challenges, we present three software packages designed to facilitate the exploration of model reasoning using attribution approaches and beyond: (1) Zennit – a highly customizable and intuitive attribution framework implementing LRP and related methods in PyTorch, (2) CoRelAy – a framework to easily and quickly construct quantitative analysis pipelines for dataset-wide analyses of explanations, and (3) ViRelAy – an interactive web-application for exploring data, attributions, and analysis results. By providing a standardized implementation for XAI, we aim to promote reproducibility in our field and empower scientists and practitioners to uncover the intricacies of complex model behavior.

Machine learned potentials based on artificial neural networks are becoming a popular tool to define an effective energy model for complex systems, either incorporating electronic structure effects at the atomistic resolution, or effectively renormalizing part of the atomistic degrees of freedom at a coarse-grained resolution. One main criticism regarding neural network potentials is that their inferred energy is less interpretable than in traditional approaches, which use simpler and more transparent functional forms. Here we address this problem by extending tools recently proposed in the nascent field of explainable artificial intelligence to coarse-grained potentials based on graph neural networks. With these tools, neural network potentials can be practically decomposed into n-body interactions, providing a human understandable interpretation without compromising predictive power. We demonstrate the approach on three different coarse-grained systems including two fluids (methane and water) and the protein NTL9. The obtained interpretations suggest that well-trained neural network potentials learn physical interactions, which are consistent with fundamental principles. Machine-learned force fields are becoming increasingly popular but suffer from their “black-box” nature. Here the authors adapt explainable AI techniques to coarse-grained graph neural network potentials and show that they capture physically consistent interactions.

We propose a near-infrared spectroscopy (NIRS)-based brain-computer interface (BCI) that can be operated in eyes-closed (EC) state. To evaluate the feasibility of NIRS-based EC BCIs, we compared the performance of an eye-open (EO) BCI paradigm and an EC BCI paradigm with respect to hemodynamic response and classification accuracy. To this end, subjects performed either mental arithmetic or imagined vocalization of the English alphabet as a baseline task with very low cognitive loading. The performances of two linear classifiers were compared; resulting in an advantage of shrinkage linear discriminant analysis (LDA). The classification accuracy of EC paradigm (75.6 ± 7.3%) was observed to be lower than that of EO paradigm (77.0 ± 9.2%), which was statistically insignificant ( p  = 0.5698). Subjects reported they felt it more comfortable ( p  = 0.057) and easier ( p  < 0.05) to perform the EC BCI tasks. The different task difficulty may become a cause of the slightly lower classification accuracy of EC data. From the analysis results, we could confirm the feasibility of NIRS-based EC BCIs, which can be a BCI option that may ultimately be of use for patients who cannot keep their eyes open consistently.

Priming improves an organism's performance upon a future stress. To test whether cold priming supports protection in spring and how it is affected by cold acclimation, we compared seven Arabidopsis accessions with different cold acclimation potentials in the field and in the greenhouse for growth, photosynthetic performance and reproductive fitness in March and May after a 14 day long cold-pretreatment at 4 °C. In the plants transferred to the field in May, the effect of the cold pretreatment on the seed yield correlated with the cold acclimation potential of the accessions. In the March transferred plants, the reproductive fitness was most supported by the cold pretreatment in the accessions with the weakest cold acclimation potential. The fitness effect was linked to long-term effects of the cold pretreatment on photosystem II activity stabilization and leaf blade expansion. The study demonstrated that cold priming stronger impacts on plant fitness than cold acclimation in spring in accessions with intermediate and low cold acclimation potential.

We focus on detecting anomalies in images where the data distribution is supported by a lower-dimensional embedded manifold. Approaches based on autoencoders have aimed to control their capacity either by reducing the size of the bottleneck layer or by imposing sparsity constraints on their activations. However, none of these techniques explicitly penalize the reconstruction of anomalous regions, often resulting in poor detection. We tackle this problem by adapting a self-supervised learning regime that essentially implements a denoising autoencoder with structured non-i.i.d. noise. Informally, our objective is to regularize the model to produce locally consistent reconstructions while replacing irregularities by acting as a filter that removes anomalous patterns. Formally, we show that the resulting model resembles a nonlinear orthogonal projection of partially corrupted images onto the submanifold of uncorrupted examples. Furthermore, we identify the orthogonal projection as an optimal solution for a specific regularized autoencoder related to contractive and denoising variants. In addition, orthogonal projection provides a conservation effect by largely preserving the original content of its arguments. Together, these properties facilitate an accurate detection and localization of anomalous regions by means of the reconstruction error. We support our theoretical analysis by achieving state-of-the-art results (image/pixel-level AUROC of 99.8/99.2%) on the MVTec AD dataset—a challenging benchmark for anomaly detection in the manufacturing domain.

Despite chemotherapy-induced intestinal mucositis being a main risk factor for blood stream infections (BSIs), no studies have investigated mucositis severity to predict BSI at fever onset during acute leukemia treatment. This study prospectively evaluated intestinal mucositis severity in 85 children with acute leukemia, representing 242 febrile episodes (122 with concurrent neutropenia) by measuring plasma levels of citrulline (reflecting enterocyte loss), regenerating islet-derived-protein 3α (REG3α, an intestinal antimicrobial peptide) and CCL20 (a mucosal immune regulatory chemokine) along with the general neutrophil chemo-attractants CXCL1 and CXCL8 at fever onset. BSI was documented in 14% of all febrile episodes and in 20% of the neutropenic febrile episodes. In age-, sex-, diagnosis- and neutrophil count-adjusted analyses, decreasing citrulline levels and increasing REG3α and CCL20 levels were independently associated with increased odds of BSI (OR = 1.6, 1.5 and 1.7 per halving/doubling, all p  < 0.05). Additionally, higher CXCL1 and CXCL8 levels increased the odds of BSI (OR = 1.8 and 1.7 per doubling, all p  < 0.0001). All three chemokines showed improved diagnostic accuracy compared to C-reactive protein and procalcitonin. These findings underline the importance of disrupted intestinal integrity as a main risk factor for BSI and suggest that objective markers for monitoring mucositis severity may help predicting BSI at fever onset.

Deep learning has revolutionized data science in many fields by greatly improving prediction performances in comparison to conventional approaches. Recently, explainable artificial intelligence has emerged as an area of research that goes beyond pure prediction improvement by extracting knowledge from deep learning methodologies through the interpretation of their results. We investigate such explanations to explore the genetic architectures of phenotypes in genome-wide association studies. Instead of testing each position in the genome individually, the novel three-step algorithm, called DeepCOMBI, first trains a neural network for the classification of subjects into their respective phenotypes. Second, it explains the classifiers’ decisions by applying layer-wise relevance propagation as one example from the pool of explanation techniques. The resulting importance scores are eventually used to determine a subset of the most relevant locations for multiple hypothesis testing in the third step. The performance of DeepCOMBI in terms of power and precision is investigated on generated datasets and a 2007 study. Verification of the latter is achieved by validating all findings with independent studies published up until 2020. DeepCOMBI is shown to outperform ordinary raw P-value thresholding and other baseline methods. Two novel disease associations (rs10889923 for hypertension, rs4769283 for type 1 diabetes) were identified.

We study the problem of classifying images into a given, pre-determined taxonomy. This task can be elegantly translated into the structured learning framework. However, despite its power, structured learning has known limits in scalability due to its high memory requirements and slow training process. We propose an efficient approximation of the structured learning approach by an ensemble of local support vector machines (SVMs) that can be trained efficiently with standard techniques. A first theoretical discussion and experiments on toy-data allow to shed light onto why taxonomy-based classification can outperform taxonomy-free approaches and why an appropriately combined ensemble of local SVMs might be of high practical use. Further empirical results on subsets of Caltech256 and VOC2006 data indeed show that our local SVM formulation can effectively exploit the taxonomy structure and thus outperforms standard multi-class classification algorithms while it achieves on par results with taxonomy-based structured algorithms at a significantly decreased computing time.

In spite of green revolution and rapid economic growth, India’s vast population still suffers from hunger and poverty, especially in the rural areas. Moreover, drought adversely affects India’s economy by declining agricultural production and purchasing power. It also escalates rural unemployment which ultimately affects household food security. Our study investigated the food security of drought prone rural households in a broader context by linking the dimensions of food security with dimensions of climate change vulnerability. We used the primary data of 157 drought prone rural households of Odisha state in India for analysis. This study employed polychoric principal component analysis to construct an aggregate food security index. An ordered probit model was used to estimate the determinants of food security. The FSI showed that three-fourth of the respondents were facing food security issues with varying degrees. The estimates of ordered probit model indicated that joint family, education, migration and health insurance are key variables that determine food security, whereas drought adversely affected food security of rural households. Overarching strategies are required to effectively address food security issues in the wake of increased drought risk. This study provides an insight for policy makers in India and in similar south Asian countries who must consider food security in the light of drought.