NodeFlow: Towards End-to-End Flexible Probabilistic Regression on Tabular Data.

We introduce NodeFlow, a flexible framework for probabilistic regression on tabular data that combines Neural Oblivious Decision Ensembles (NODEs) and Conditional Continuous Normalizing Flows (CNFs). It offers improved modeling capabilities for arbitrary probabilistic distributions, addressing the limitations of traditional parametric approaches. In NodeFlow, the NODE captures complex relationships in tabular data through a tree-like structure, while the conditional CNF utilizes the NODE's output space as a conditioning factor. The training process of NodeFlow employs standard gradient-based learning, facilitating the end-to-end optimization of the NODEs and CNF-based density estimation. This approach ensures outstanding performance, ease of implementation, and scalability, making NodeFlow an appealing choice for practitioners and researchers. Comprehensive assessments on benchmark datasets underscore NodeFlow's efficacy, revealing its achievement of state-of-the-art outcomes in multivariate probabilistic regression setup and its strong performance in univariate regression tasks. Furthermore, ablation studies are conducted to justify the design choices of NodeFlow. In conclusion, NodeFlow's end-to-end training process and strong performance make it a compelling solution for practitioners and researchers. Additionally, it opens new avenues for research and application in the field of probabilistic regression on tabular data.

NMRNet: a deep learning approach to automated peak picking of protein NMR spectra.

Motivation: Automated selection of signals in protein NMR spectra, known as peak picking, has been studied for over 20 years, nevertheless existing peak picking methods are still largely deficient. Accurate and precise automated peak picking would accelerate the structure calculation, and analysis of dynamics and interactions of macromolecules. Recent advancement in handling big data, together with an outburst of machine learning techniques, offer an opportunity to tackle the peak picking problem substantially faster than manual picking and on par with human accuracy. In particular, deep learning has proven to systematically achieve human-level performance in various recognition tasks, and thus emerges as an ideal tool to address automated identification of NMR signals. Results: We have applied a convolutional neural network for visual analysis of multidimensional NMR spectra. A comprehensive test on 31 manually annotated spectra has demonstrated top-tier average precision (AP) of 0.9596, 0.9058 and 0.8271 for backbone, side-chain and NOESY spectra, respectively. Furthermore, a combination of extracted peak lists with automated assignment routine, FLYA, outperformed other methods, including the manual one, and led to correct resonance assignment at the levels of 90.40%, 89.90% and 90.20% for three benchmark proteins. Availability and implementation: The proposed model is a part of a Dumpling software (platform for protein NMR data analysis), and is available at https://dumpling.bio/. Supplementary information: Supplementary data are available at Bioinformatics online.

The in vivo effects of silver nanoparticles on terrestrial isopods, Porcellio scaber, depend on a dynamic interplay between shape, size and nanoparticle dissolution properties.

The present work aims to study the effects that acute exposure to low concentrations of silver nanoparticles (AgNPs) cause in digestive glands of terrestrial isopods (Porcellio scaber). The experiments were designed to integrate different analytical techniques, such as transmission electron microscopy, atomic absorption spectroscopy, proton induced X-ray emission, and Fourier transform IR imaging (FTIRI), in order to gain a comprehensive insight into the process from the AgNPs' synthesis to their interaction with biological tissues in vivo. To this aim, terrestrial isopods were fed with AgNPs having different shapes, sizes, and concentrations. For all the tested conditions, no toxicity at the whole organism level was observed after 14 days of exposure. However, FTIRI showed that AgNPs caused detectable local changes in proteins, lipids, nucleic acids and carbohydrates at the tissue level, to an extent dependent on the interplay of the AgNPs' properties: shape, size, concentration and dissolution of ions from them.

Screen-printed nanoparticles as anti-counterfeiting tags.

Metallic nanoparticles with different physical properties have been screen printed as authentication tags on different types of paper. Gold and silver nanoparticles show unique optical signatures, including sharp emission bandwidths and long lifetimes of the printed label, even under accelerated weathering conditions. Magnetic nanoparticles show distinct physical signals that depend on the size of the nanoparticle itself. They were also screen printed on different substrates and their magnetic signals read out using a magnetic pattern recognition sensor and a vibrating sample magnetometer. The novelty of our work lies in the demonstration that the combination of nanomaterials with optical and magnetic properties on the same printed support is possible, and the resulting combined signals can be used to obtain a user-configurable label, providing a high degree of security in anti-counterfeiting applications using simple commercially-available sensors.

High-speed water sterilization using silver-containing cellulose membranes.

The removal of bacteria and other pathogenic micro-organisms from drinking water is usually carried out by boiling; however, when this is not a feasible option, a combination of treatment based on filtration and disinfection is recommended. In this work, we produced cellulose filters grafted with silver nanoparticles (AgNPs) and silver nanowires (AgNWs) by covalent attachment of separately prepared Ag nanostructures on thiol- and amine-modified commercially available cellulosic filters. Results obtained from scanning electron microscopy (SEM), scanning transmission electron microscopy (STEM), and energy-dispersive X-ray spectroscopy (EDS) all revealed that such modified cellulose membranes contained large amounts of homogeneously dispersed AgNPs, whereas X-ray photoelectron spectroscopy (XPS) analysis demonstrated that the aforementioned nanostructures were immobilized on the membrane with a strong and stable covalent bond between the thiol or amine groups and the surface of the Ag nanofillers. This durable and robust covalent attachment facilitated outstanding suppression of the uncontrolled release of the nanostructures from the membranes, even under strong ultrasonication. Those membranes also demonstrated high permeance and antimicrobial activity in excess of 99.9% growth inhibition against Escherichia coli, which was used as a model of gram-negative coliform bacteria. Bacteria percolated throughout the tortuous silver-loaded filters, thus increasing the chances of contact between the Ag nanostructures (wires or nanoparticles) and the passing bacteria. Thus, we anticipate that these filters, with their high antibacterial activity and robustness, can be produced in a cost-effective manner and that they would be capable of producing affordable, clean, and safe drinking water in a short period of time without producing an uncontrolled silver release into the percolated water.

Multi-Label Conditional Generation From Pre-Trained Models.

Although modern generative models achieve excellent quality in a variety of tasks, they often lack the essential ability to generate examples with requested properties, such as the age of the person in the photo or the weight of the generated molecule. To overcome these limitations we propose PluGeN (Plugin Generative Network), a simple yet effective generative technique that can be used as a plugin for pre-trained generative models. The idea behind our approach is to transform the entangled latent representation using a flow-based module into a multi-dimensional space where the values of each attribute are modeled as an independent one-dimensional distribution. In consequence, PluGeN can generate new samples with desired attributes as well as manipulate labeled attributes of existing examples. Due to the disentangling of the latent representation, we are even able to generate samples with rare or unseen combinations of attributes in the dataset, such as a young person with gray hair, men with make-up, or women with beards. In contrast to competitive approaches, PluGeN can be trained on partially labeled data. We combined PluGeN with GAN and VAE models and applied it to conditional generation and manipulation of images, chemical molecule modeling and 3D point clouds generation.

General Hypernetwork Framework for Creating 3D Point Clouds.

In this work, we propose a novel method for generating 3D point clouds that leverages the properties of hypernetworks. Contrary to the existing methods that learn only the representation of a 3D object, our approach simultaneously finds a representation of the object and its 3D surface. The main idea of our HyperCloud method is to build a hypernetwork that returns weights of a particular neural network (target network) trained to map points from prior distribution into a 3D shape. As a consequence, a particular 3D shape can be generated using point-by-point sampling from the prior distribution and transforming the sampled points with the target network. Since the hypernetwork is based on an auto-encoder architecture trained to reconstruct realistic 3D shapes, the target network weights can be considered to be a parametrization of the surface of a 3D shape, and not a standard representation of point cloud usually returned by competitive approaches. We also show that relying on hypernetworks to build 3D point cloud representations offers an elegant and flexible framework. To that point, we further extend our method by incorporating flow-based models, which results in a novel HyperFlow approach.

Service-oriented medical system for supporting decisions with missing and imbalanced data.

In this paper, we propose a service-oriented support decision system (SOSDS) for diagnostic problems that is insensitive to the problems of the imbalanced data and missing values of the attributes, which are widely observed in the medical domain. The system is composed of distributed Web services, which implement machine-learning solutions dedicated to constructing the decision models directly from the datasets impaired by the high percentage of missing values of the attributes and imbalanced class distribution. The issue of the imbalanced data is solved by the application of a cost-sensitive support vector machine and the problem of missing values of attributes is handled by proposing the novel ensemble-based approach that splits the incomplete data space into complete subspaces that are further used to construct base learners. We evaluate the quality of the SOSDS components using three ontological datasets.