DrivAER: Identification of driving transcriptional programs in single-cell RNA sequencing data

Background Single-cell RNA sequencing (scRNA-seq) unfolds complex transcriptomic datasets into detailed cellular maps. Despite recent success, there is a pressing need for specialized methods tailored towards the functional interpretation of these cellular maps. Findings Here, we present DrivAER, a machine learning approach for the identification of driving transcriptional programs using autoencoder-based relevance scores. DrivAER scores annotated gene sets on the basis of their relevance to user-specified outcomes such as pseudotemporal ordering or disease status. DrivAER iteratively evaluates the information content of each gene set with respect to the outcome variable using autoencoders. We benchmark our method using extensive simulation analysis as well as comparison to existing methods for functional interpretation of scRNA-seq data. Furthermore, we demonstrate that DrivAER extracts key pathways and transcription factors that regulate complex biological processes from scRNA-seq data. Conclusions By quantifying the relevance of annotated gene sets with respect to specified outcome variables, DrivAER greatly enhances our ability to understand the underlying molecular mechanisms.

DrivAER: Identification of driving transcriptional programs in single-cell RNA sequencing data

Single cell RNA sequencing (scRNA-seq) unfolds complex transcriptomic data sets into detailed cellular maps. Despite recent success, there is a pressing need for specialized methods tailored towards the functional interpretation of these cellular maps. Here, we present DrivAER, a machine learning approach that scores annotated gene sets based on their relevance to user-specified outcomes such as pseudotemporal ordering or disease status. We demonstrate that DrivAER extracts the key driving pathways and transcription factors that regulate complex biological processes from scRNA-seq data.

Evolution of multiple-access networks — cellular and non-cellular — in historical perspective. Part 4

Introduction:The goal of this issue is the analysis of evolution of the current and novel wireless networks, from second generation (2G) to fifth generation (5G), as well as changes in technologies and their corresponding theoretical background and protocols — from Bluetooth, WLAN, WiFi and WiMAX to LTE, OFDM/OFDMA, MIMO and LTE/MIMO advanced technologies with new hierarchy of cellular maps design — femto/pico/micro/macro.Methods:We use new theoretical frameworks for description of the advanced technologies, such as multicarrier diversity technique, OFDM and OFDM novel approach, MIMO aspects description based on multi-beam antennas approach, various cellular maps design based on a new algorithms of femto/pico/micro/macrocell deployment, and a new methodology of a new MIMO/LTE system integration based on multi-beam antennas.Results:We have created a new methodology of multi-carrier diversity description for novel multiple-access networks, of usage of OFDM/OFDMA modulation to obey inter-user and inter-symbol interference in multiple-access networks, of how to obey the multiplicative noises occurring in the multiple-access wireless networks, caused by multi-ray phenomena, and finally, of how to overcome propagation effects occurring in the terrestrial communication links by use combination of MIMO and LTE technologies based on multi-beam antennas. For these purposes we present new stochastic approach that accounts for the terrain features, such as buildings’ overlay profile, buildings’ density around the base station and each user antennas, and so forth. These parameters allow us to estimate for each situation occurs at the built-up terrain area the effects of fading, as a source of multiplicative noise.Practical relevance:New methodology of how to estimate effects of multiplicative noise, inter-user and inter-symbol interference, occurring in the terrestrial wireless networks, allows us to predict a-priory practical aspects of the current and new multiple-access wireless communication networks, such as: the users’ capacity and user’s links spectral efficiency for various configurations of cells deployment — femto, pico, micro, and macro, as well as the novel MIMO/LTE system configuration for future networks of 4th and 5th generation deployment.

Evolution of multiple-access networks - cellular and non-cellular - in historical perspective. Part 3

Introduction:The goal of this issue is the analysis of evolution of the current and novel wireless networks, from second generation (2D) to fifth generation (5G), as well as changes in technologies and their corresponding theoretical background and protocols — from Bluetooth, WLAN, WiFi and WiMAX to LTE, OFDM/OFDMA, MIMO and LTE/MIMO advanced technologies with new hierarchy of cellular maps design — femto/plco/mlcro/macro.Methods:We use new theoretical frameworks for description of the advanced technologies, such as multicarrier diversity technique, OFDM and OFDM novel approach, MIMO aspects description based on multi-beam antennas approach, various cellular maps design based on a new algorithms offemto/pico/micro/macrocell deployment, and a new methodology of a new MIMO/LTEsystem integration based on multi-beam antennas.Results:We have created a new methodology of multi-carrier diversity description for novel multiple-access networks, of usage of OFDM/OFDMA modulation to obey inter-user and inter-symbol interference in multiple-access networks, of how to obey the multiplicative noises occurring in the multiple-access wireless networks, caused by multi-ray phenomena, and finally, of how to overcome propagation effects occurring in the terrestrial communication links by use combination of MIMO and LTE technologies based on multi-beam antennas. For these purposes we present new stochastic approach that accounts for the terrain features, such as buildings' overlay profile, buildings' density around the base station and each user antennas, and so forth. These parameters allow us to estimate for each situation occurs at the built-up terrain area the effects of fading, as a source of multiplicative noise.Practical relevance:New methodology of how to estimate effects of multiplicative noise, inter-user and inter-symbol interference, occurring in the terrestrial wireless networks, allows us to predict a-priory practical aspects of the current and new multiple-access wireless communication networks, such as: the users' capacity and user's links spectral efficiency for various configurations of cells deployment — femto, pico, micro, and macro, as well as the novel MIMO/LTEsystem configuration for future networks of 4thand 5thgeneration deployment.

Evolution of multiple-access networks cellular and non-cellular — in historical perspective. Part 1

Introduction:The goal of this review is the analysis of evolution of the current and novel wireless networks, from secondgeneration (2D)tofifth generation(5G),as well as changes in technologies and their corresponding theoretical background andprotocols -from Bluetooth, WLAN, WiFi and WiMAXtoLTE, OFDM/OFDMA, MIMO and LTE/MIMO advanced technologies with new hierarchy of cellular maps design — femto/pico/micro/macro.Methods:We use new theoretical frameworkstodescribe advanced technologies, such as multicarrier diversity technique, OFDM and OFDM novel approach, new aspects ofMIMO description based on multi-beam antennas, design of various cellular maps based on new algorithms of femto/pico/micro/macrocell deployment, and the methodology of a new MIMO/LTE system integration based on multi-beam antennas.Results:We have created a new methodology for multi-carrier diversity description of novel multiple-access networks, forthe usage of OFDM/OFDMA modulation in ordertoovercome inter-user and inter-symbol interference in multiple-access networks, as well as multiplicative noises in multiple-access wireless networks caused by multi-ray phenomena. Finally, wehave suggested howtoovercome the propagation effects occurring in the terrestrial communication channels by using acombination of MIMO and LTE technologies based on multi-beam antennas. For these purposes, we present a new stochasticapproach which takes into account the terrain features, such as buildings' overlay profile, buildings' density around the base station and each user's antennas, andsoforth. These parameters allow ustoestimate the effects of fading as a multiplicativenoise source.Practical relevance:The new methodology of estimating the effects created by multiplicative noise and inter-user and inter-symbol interference in terrestrial wireless networks allows ustopredict a-priory practical aspects of the currentand new multiple-access wireless communication systems, like the potential number of users or the spectral efficiency ofuser channels for various configurations of cell deployment: femto, pico, micro, and macro, as well as the novel MIMO/LTE system configurations for future networks of the 4th and 5th generations.