Research on machine learning approaches for upper limb prosthesis control has shown impressive progress. However, translating these results from the lab to patient’s everyday lives remains a challenge, because advanced control schemes tend to break down under everyday disturbances, such as electrode shifts. Recently, it has been suggested to apply adaptive transfer learning to counteract electrode shifts using as little newly recorded training data as possible. In this paper, we present a novel, simple version of transfer learning and provide the first user study demonstrating the effectiveness of transfer learning to counteract electrode shifts. For this purpose, we introduce the novel Box and Beans test to evaluate prosthesis proficiency and compare user performance with an initial simple pattern recognition system, the system under electrode shifts, and the system after transfer learning. Our results show that transfer learning could significantly alleviate the impact of electrode shifts on user performance in the Box and Beans test. INDEX TERMS Electromyography, Electrode Shifts, Transfer Learning.

We give results from a detailed analysis of human Ribosomal Protein (RP) levels in normal and cancer samples and cell lines from large mRNA, copy number variation and ribosome profiling datasets. After normalizing total RP mRNA levels per sample, we find highly consistent tissue specific RP mRNA signatures in normal and tumor samples. Multiple RP mRNA-subtypes exist in several cancers, with significant survival and genomic differences. Some RP mRNA variations among subtypes correlate with copy number loss of RP genes. In kidney cancer, RP subtypes map to molecular subtypes related to cell-of-origin. Pan-cancer analysis of TCGA data showed widespread single/double copy loss of RP genes, without significantly affecting survival. In several cancer cell lines, CRISPR-Cas9 knockout of RP genes did not affect cell viability. Matched RP ribosome profiling and mRNA data in humans and rodents stratified by tissue and development stage and were strongly correlated, showing that RP translation rates were proportional to mRNA levels. In a small dataset of human adult and fetal tissues, RP protein levels showed development stage and tissue specific heterogeneity of RP levels. Our results suggest that heterogeneous RP levels play a significant functional role in cellular physiology, in both normal and disease states.

Background: For a sustainable production of food, research on agricultural soil microbial communities is inevitable. Due to its immense complexity, soil is still some kind of black box. Soil study designs for identifying microbiome members of relevance have various scopes and focus on particular environmental factors. To identify common features of soil microbiomes, data from multiple studies should be compiled and processed. Taxonomic compositions and functional capabilities of microbial communities associated with soils and plants have been identified and characterized in the past few decades. From a fertile Loess–Chernozem-type soil located in Germany, metagenomically assembled genomes (MAGs) classified as members of the phylum Thaumarchaeota/Thermoproteota were obtained. These possibly represent keystone agricultural soil community members encoding functions of relevance for soil fertility and plant health. Their importance for the analyzed microbiomes is corroborated by the fact that they were predicted to contribute to the cycling of nitrogen, feature the genetic potential to fix carbon dioxide and possess genes with predicted functions in plant-growth-promotion (PGP). To expand the knowledge on soil community members belonging to the phylum Thaumarchaeota, we conducted a meta-analysis integrating primary studies on European agricultural soil microbiomes. Results: Taxonomic classification of the selected soil metagenomes revealed the shared agricultural soil core microbiome of European soils from 19 locations. Metadata reporting was heterogeneous between the different studies. According to the available metadata, we separated the data into 68 treatments. The phylum Thaumarchaeota is part of the core microbiome and represents a major constituent of the archaeal subcommunities in all European agricultural soils. At a higher taxonomic resolution, 2074 genera constituted the core microbiome. We observed that viral genera strongly contribute to variation in taxonomic profiles. By binning of metagenomically assembled contigs, Thaumarchaeota MAGs could be recovered from several European soil metagenomes. Notably, many of them were classified as members of the family Nitrososphaeraceae, highlighting the importance of this family for agricultural soils. The specific Loess-Chernozem Thaumarchaeota MAGs were most abundant in their original soil, but also seem to be of importance in other agricultural soil microbial communities. Metabolic reconstruction of Switzerland_1_MAG_2 revealed its genetic potential i.a. regarding carbon dioxide (CO $$_2$$2 ) fixation, ammonia oxidation, exopolysaccharide production and a beneficial effect on plant growth. Similar genetic features were also present in other reconstructed MAGs. Three Nitrososphaeraceae MAGs are all most likely members of a so far unknown genus. Conclusions: On a broad view, European agricultural soil microbiomes are similarly structured. Differences in community structure were observable, although analysis was complicated by heterogeneity in metadata recording. Our study highlights the need for standardized metadata reporting and the benefits of networking open data. Future soil sequencing studies should also consider high sequencing depths in order to enable reconstruction of genome bins. Intriguingly, the family Nitrososphaeraceae commonly seems to be of importance in agricultural microbiomes.

Albeit automated classifiers offer a standard tool in many application areas, there exists hardly a generic possibility to directly inspect their behavior, which goes beyond the mere classification of (sets of) data points. In this contribution, we propose a general framework how to visualize a given classifier and its behavior as concerns a given data set in two dimensions. More specifically, we use modern nonlinear dimensionality reduction (DR) techniques to project a given set of data points and their relation to the classification decision boundaries. Furthermore, since data are usually intrinsically more than two-dimensional and hence cannot be projected to two dimensions without information loss, we propose to use discriminative DR methods which shape the projection according to given class labeling as is the case for a classification setting. With a given data set, this framework can be used to visualize any trained classifier which provides a probability or certainty of the classification together with the predicted class label. We demonstrate the suitability of the framework in the context of different dimensionality reduction techniques, in the context of different attention foci as concerns the visualization, and as concerns different classifiers which should be visualized.

Machine learning algorithms using deep architectures have been able to implement increasingly powerful and successful models. However, they also become increasingly more complex, more difficult to comprehend and easier to fool. So far, most methods in the literature investigate the decision of the model for a single given input datum. In this paper, we propose to visualize a part of the decision function of a deep neural network together with a part of the data set in two dimensions with discriminative dimensionality reduction. This enables us to inspect how different properties of the data are treated by the model, such as outliers, adversaries or poisoned data. Further, the presented approach is complementary to the mentioned interpretation methods from the literature and hence might be even more useful in combination with those. Code is available at https://github.com/LucaHermes/DeepView