Biology has become a data-intensive science. Recent technological advances in single-cell genomics have enabled the measurement of multiple facets of cellular state, producing datasets with millions of single-cell observations. While these data hold great promise for understanding molecular mechanisms in health and disease, analysis challenges arising from sparsity, technical and biological variability, and high dimensionality of the data hinder the derivation of such mechanistic insights. To promote the innovation of algorithms for analysis of multimodal single-cell data, we organized a competition at NeurIPS 2021 applying the Common Task Framework to multimodal single-cell data integration. For this competition we generated the first multimodal benchmarking dataset for single-cell biology and defined three tasks in this domain: prediction of missing modalities, aligning modalities, and learning a joint representation across modalities. We further specified evaluation metrics and developed a cloud-based algorithm evaluation pipeline. Using this setup, 280 competitors submitted over 2600 proposed solutions within a 3 month period, showcasing substantial innovation especially in the modality alignment task. Here, we present the results, describe trends of well performing approaches, and discuss challenges associated with running the competition.

Motivation The transcriptomic data is being frequently used in the research of biomarker genes of different diseases and biological states. The most common tasks there are data harmonization and treatment outcome prediction. Both of them can be addressed via the style transfer approach. Either technical factors or any biological details about the samples which we would like to control (gender, biological state, treatment etc.) can be used as style components. Results The proposed style transfer solution is based on Conditional Variational Autoencoders, Y-Autoencoders and adversarial feature decomposition. In order to quantitatively measure the quality of the style transfer, neural network classifiers which predict the style and semantics after training on real expression were used. Comparison with several existing style-transfer based approaches shows that proposed model has the highest style prediction accuracy on all considered datasets while having comparable or the best semantics prediction accuracy. Availability https://github.com/NRshka/stvae-source Supplementary information FigShare.com (https://dx.doi.org/10.6084/m9.figshare.9925115)

In vitro cellular models are promising tools for studying normal and pathological conditions. One of their important applications is the development of genetically engineered biosensor systems to investigate, in real time, the processes occurring in living cells. At present, there are fluorescence, protein-based, sensory systems for detecting various substances in living cells (for example, hydrogen peroxide, ATP, Ca2+ etc.,) or for detecting processes such as endoplasmic reticulum stress. Such systems help to study the mechanisms underlying the pathogenic processes and diseases and to screen for potential therapeutic compounds. It is also necessary to develop new tools for the processing and analysis of obtained microimages. Here, we present our web-application CellCountCV for automation of microscopic cell images analysis, which is based on fully convolutional deep neural networks. This approach can efficiently deal with non-convex overlapping objects, that are virtually inseparable with conventional image processing methods. The cell counts predicted with CellCountCV were very close to expert estimates (the average error rate was < 4%). CellCountCV was used to analyze large series of microscopic images obtained in experimental studies and it was able to demonstrate endoplasmic reticulum stress development and to catch the dose-dependent effect of tunicamycin.

In this paper, we discuss applications of neural networks to recognizing knots and, in particular, to the unknotting problem. One of the motivations for this study is to understand how neural networks work on the example of a problem for which rigorous mathematical algorithms for its solution are known. We represent knots by rectangular Dynnikov diagrams and apply neural networks to distinguish a given diagram’s class from a finite family of topological types. The data presented to the program is generated by applying Dynnikov moves to initial samples. The significance of using these diagrams and moves is that in this context the problem of determining whether a diagram is unknotted is a finite search of a bounded combinatorial space. In this way, this paper provides a foundation for further work where the neural network itself will learn to use the Dynnikov moves for knot recognition. Source code of the programs is available at https://github.com/nerusskikh/deepknots .

No abstract

The in vitro cellular models are promising tools for studying normal and pathological conditions. One of their important applications is the development of genetically engineered biosensor systems to investigate the processes occurring in living cells in real time. Today, there are fluorescence protein based sensory systems for detecting various substances in living cells (for example, hydrogen peroxide, ATP, Ca 2+ etc.) or for detecting processes such as endoplasmic reticulum stress. Such systems help to study mechanisms underlying the pathogenic processes and diseases and for screening potential therapeutic compounds. It is also necessary to develop new tools for processing and analysis of obtained microimages. Here we present our web-application CellCountCV for automation of microscopy cell images analysis which is based on fully-convolutional deep neural networks. This approach can efficiently deal with non-convex overlapping objects, that are virtually inseparable with conventional image processing methods. The cell counts predicted with CellCountCV were very close to expert estimates (the average error rate was < 4%). CellCountCV was used to analyse large series of microscopy images obtained in experimental studies and it was able to demonstrate the endoplasmic reticulum stress development and to catch the dose-dependent effect of tunicamycin.

In this article we discuss applications of neural networks to recognising knots and, in particular, to the unknotting problem. One of motivations for this study is to understand how neural networks work on the example of a problem for which rigorous mathematical algorithms for its solution are known. We represent knots by rectangular Dynnikov diagrams and apply neural networks to distinguish a given diagram's class from the given finite families of topological types. The data presented to the program is generated by applying Dynnikov moves to initial samples. The significance of using these diagrams and moves is that in this context the problem of determining whether a diagram is unknotted is a finite search of a bounded combinatorial space.

No abstract