Search

Until date, several machine learning approaches have been proposed for the dynamic modeling of temporal omics data. Although they have yielded impressive results in terms of model accuracy and predictive ability, most of these applications are based on “Black-box” algorithms and more interpretable models have been claimed by the research community. The recent eXplainable Artificial Intelligence (XAI) revolution offers a solution for this issue, were rule-based approaches are highly suitable for explanatory purposes. The further integration of the data mining process along with functional-annotation and pathway analyses is an additional way towards more explanatory and biologically soundness models. In this paper, we present a novel rule-based XAI strategy (including pre-processing, knowledge-extraction and functional validation) for finding biologically relevant sequential patterns from longitudinal human gene expression data (GED). To illustrate the performance of our pipeline, we work on in vivo temporal GED collected within the course of a long-term dietary intervention in 57 subjects with obesity (GSE77962). As validation populations, we employ three independent datasets following the same experimental design. As a result, we validate primarily extracted gene patterns and prove the goodness of our strategy for the mining of biologically relevant gene-gene temporal relations. Our whole pipeline has been gathered under open-source software and could be easily extended to other human temporal GED applications., Author summary Biological processes in humans are not single-gene based mechanisms, but complex systems controlled by regulatory interactions between thousands of genes. Within these gene regulatory networks, time-delay is a common phenomenon and genes interact each other within a four-dimension space. Hence, to fully understand or to control biological processes we need to unravel the principles of gene-gene temporal interactions. Until date, several approaches based on Artificial Intelligence methods have tried to address this issue. Nevertheless, the research community has claimed for more interpretable and biologically meaningful models. Particularly, scientists claim for methods able to infer gene-gene temporal interactions that could be later validated with real-life experiments at the lab. The recent revolution known as “eXplainable Artificial Intelligence” offers a solution for this issue, where a range of highly interpretable and explicable models has become available. Many of these methods could be applied to temporal gene expression data in order to decipher mentioned temporal gene-gene relationships in humans. Here, we propose and validate a new pipeline analysis including an eXplainable artificial intelligence method for the identification of comprehensible gene-gene temporal relationships from human intervention studies. Our method has been validated in six datasets from obesity research (consisting of low calorie diets interventions), where it was able to extract meaningful gene-gene temporal interactions with relevance the etiology of the disease. The application of our pipeline to other type of human temporal gene profiles would greatly expand our knowledge for complex biological processes, with a special interest for drug clinical trials, in which identified gene-gene regulatory interactions could reveal new therapeutic targets.

There has been a spate of interest in association networks in biological and medical research, for example, genetic interaction networks. In this paper, we propose a novel method, the extended joint hub graphical lasso (EDOHA), to estimate multiple related interaction networks for high dimensional omics data across multiple distinct classes. To be specific, we construct a convex penalized log likelihood optimization problem and solve it with an alternating direction method of multipliers (ADMM) algorithm. The proposed method can also be adapted to estimate interaction networks for high dimensional compositional data such as microbial interaction networks. The performance of the proposed method in the simulated studies shows that EDOHA has remarkable advantages in recognizing class-specific hubs than the existing comparable methods. We also present three applications of real datasets. Biological interpretations of our results confirm those of previous studies and offer a more comprehensive understanding of the underlying mechanism in disease., Author summary Reconstruction of multiple association networks from high dimensional omics data is an important topic, especially in biology. Previous studies focused on estimating different networks and detecting common hubs among all classes. Integration of information over different classes of data while allowing the difference in the hub nodes is also biologically plausible. Therefore, we propose a method, EDOHA, to jointly construct multiple interaction networks with the capacity in finding different hub networks for each class of data. Simulation studies show better performance over conventional methods. The method has been demonstrated in three real-world data.

The relationship between the underlying contact network over which a pathogen spreads and the pathogen phylogenetic trees that are obtained presents an opportunity to use sequence data to learn about contact networks that are difficult to study empirically. However, this relationship is not explicitly known and is usually studied in simulations, often with the simplifying assumption that the contact network is static in time, though human contact networks are dynamic. We simulate pathogen phylogenetic trees on dynamic Erdős-Renyi random networks and on two dynamic networks with skewed degree distribution, of which one is additionally clustered. We use tree shape features to explore how adding dynamics changes the relationships between the overall network structure and phylogenies. Our tree features include the number of small substructures (cherries, pitchforks) in the trees, measures of tree imbalance (Sackin index, Colless index), features derived from network science (diameter, closeness), as well as features using the internal branch lengths from the tip to the root. Using principal component analysis we find that the network dynamics influence the shapes of phylogenies, as does the network type. We also compare dynamic and time-integrated static networks. We find, in particular, that static network models like the widely used Barabasi-Albert model can be poor approximations for dynamic networks. We explore the effects of mis-specifying the network on the performance of classifiers trained identify the transmission rate (using supervised learning methods). We find that both mis-specification of the underlying network and its parameters (mean degree, turnover rate) have a strong adverse effect on the ability to estimate the transmission parameter. We illustrate these results by classifying HIV trees with a classifier that we trained on simulated trees from different networks, infection rates and turnover rates. Our results point to the importance of correctly estimating and modelling contact networks with dynamics when using phylodynamic tools to estimate epidemiological parameters., Author summary Understanding whether and how transmission patterns are revealed by branching patterns in phylogenetic trees for pathogens remains a challenging research question. Besides the diversification of the pathogen, branching patterns depend strongly on the host contact structure as it shapes opportunities for the pathogen to reproduce. However, the host contact network is often difficult to study, in particular as it evolves in time. In this paper we perform a simulation study on three different dynamic networks, on which we simulate transmission trees. We use a simple Erdős-Renyi random network and two more realistic networks with skewed degree distribution, where one is also clustered. We convert transmission trees into phylogenetic trees and analyze them with different tree statistics like imbalance measures, counts of small substructures, and measures containing the branch lengths. We study the tree features with principal component analysis and with supervised learning methods, and find that network dynamics and network type can strongly influence the shape of phylogenetic trees. This implies that using phylogenetic trees from a mis-specified network type and dynamic can lead to poor phylodynamic estimation of transmission parameters. We illustrate this with HIV phylogenetic trees constructed from viral sequences of patients in the Dutch ATHENA cohort, and from sequences of the Los Alamos Sequence database.

A streaming assembly pipeline utilising real-time Oxford Nanopore Technology (ONT) sequencing data is important for saving sequencing resources and reducing time-to-result. A previous approach implemented in npScarf provided an efficient streaming algorithm for hybrid assembly but was relatively prone to mis-assemblies compared to other graph-based methods. Here we present npGraph, a streaming hybrid assembly tool using the assembly graph instead of the separated pre-assembly contigs. It is able to produce more complete genome assembly by resolving the path finding problem on the assembly graph using long reads as the traversing guide. Application to synthetic and real data from bacterial isolate genomes show improved accuracy while still maintaining a low computational cost. npGraph also provides a graphical user interface (GUI) which provides a real-time visualisation of the progress of assembly. The tool and source code is available at https://github.com/hsnguyen/assembly., Author summary Hybrid genome assembly algorithms combine high accuracy short reads with error-prone long reads with the goal of generating highly contiguous assemblies with low error rates. Short read sequence data is relatively inexpensive in comparison to long-read sequence data, and, moreover short-read sequence data has already been collected for many bacterial species, thus motivating development of methods wh ich are frugal with respect to acquisition of long-read sequence data. One of the attractive features of the Oxford Nanopore Technology’s sequencers is that they generate sequence data in real-time, and in principle sequencing can be stopped once enough data is acquired. However, there is only one previous attempt for greedy genome scaffolding of contigs in real-time, which was prone to assembly errors. In this paper we describe a new tool—npGraph—which resolves the assembly graph in real-time as sequence is generated; coupled with assembly visualisation showing assembly graph resolution in real-time. We show that npGraph generates completed bacterial assemblies which are as accurate as state-of-the-art batch hybrid assembly pipelines, and also provides substantial computational speed-up.

Human endogenous retroviruses (HERVs) encode active retroviral proteins, which may be involved in the progression of cancer and other diseases. Matrix protein (MA), in group-specific antigen genes (gag) of retroviruses, is associated with the virus envelope glycoproteins in most mammalian retroviruses and may be involved in virus particle assembly, transport and budding. However, the amount of annotated MAs in ERVs is still at a low level so far. No computational method to predict the exact start and end coordinates of MAs in gags has been proposed yet. In this paper, a computational method to identify MAs in ERVs is proposed. A divide and conquer technique was designed and applied to the conventional prediction model to acquire better results when dealing with gene sequences with various lengths. Initiation sites and termination sites were predicted separately and then combined according to their intervals. Three different algorithms were applied and compared: weighted support vector machine (WSVM), weighted extreme learning machine (WELM) and random forest (RF). G - mean (geometric mean of sensitivity and specificity) values of initiation sites and termination sites under 5-fold cross validation generated by random forest models are 0.9869 and 0.9755 respectively, highest among the algorithms applied. Our prediction models combine RF & WSVM algorithms to achieve the best prediction results. 98.4% of all the collected ERV sequences with complete MAs (125 in total) could be predicted exactly correct by the models. 94,671 HERV sequences from 118 families were scanned by the model, 104 new putative MAs were predicted in human chromosomes. Distributions of the putative MAs and optimizations of model parameters were also analyzed. The usage of our predicting method was also expanded to other retroviruses and satisfying results were acquired.

With the recent technological developments a vast amount of high-throughput data has been profiled to understand the mechanism of complex diseases. The current bioinformatics challenge is to interpret the data and underlying biology, where efficient algorithms for analyzing heterogeneous high-throughput data using biological networks are becoming increasingly valuable. In this paper, we propose a software package based on the Prize-collecting Steiner Forest graph optimization approach. The PCSF package performs fast and user-friendly network analysis of high-throughput data by mapping the data onto a biological networks such as protein-protein interaction, gene-gene interaction or any other correlation or coexpression based networks. Using the interaction networks as a template, it determines high-confidence subnetworks relevant to the data, which potentially leads to predictions of functional units. It also interactively visualizes the resulting subnetwork with functional enrichment analysis., Swiss National Science Foundation ((205321-147138/1), National Institutes of Health (U.S.) (U54-NS-091046), National Institutes of Health (U.S.) (U54-NS-091046) )

Profilin 1 (PFN1) protein plays key roles in neuronal growth and differentiation, membrane trafficking, and regulation of the actin cytoskeleton. Four natural variants of PFN1 were described as related to ALS, the most common adult-onset motor neuron disorder. However, the pathological mechanism of PFN1 in ALS is not yet completely understood. The goal of this work is to thoroughly analyze the effects of the ALS-related mutations on PFN1 structure and function using computational simulations. Here, PhD-SNP, PMUT, PolyPhen-2, SIFT, SNAP, SNPS&GO, SAAP, nsSNPAnalyzer, SNPeffect4.0 and I-Mutant2.0 were used to predict the functional and stability effects of PFN1 mutations. ConSurf was used for the evolutionary conservation analysis, and GROMACS was used to perform the MD simulations. The mutations C71G, M114T, and G118V, but not E117G, were predicted as deleterious by most of the functional prediction algorithms that were used. The stability prediction indicated that the ALS-related mutations could destabilize PFN1. The ConSurf analysis indicated that the mutation C71G, M114T, E117G, and G118V occur in highly conserved positions. The MD results indicated that the studied mutations could affect the PFN1 flexibility at the actin and PLP-binding domains, and consequently, their intermolecular interactions. It may be therefore related to the functional impairment of PFN1 upon C71G, M114T, E117G and G118V mutations, and their involvement in ALS development. We also developed a database, SNPMOL (http://www.snpmol.org/), containing the results presented on this paper for biologists and clinicians to exploit PFN1 and its natural variants.

Well-performed Video quality assessment (VQA) method should be consistent with human visual systems for better prediction accuracy. In this paper, we propose a VQA method using motion-compensated temporal filtering (MCTF) and manifold feature similarity. To be more specific, a group of frames (GoF) is first decomposed into a temporal high-pass component (HPC) and a temporal low-pass component (LPC) by MCTF. Following this, manifold feature learning (MFL) and phase congruency (PC) are used to predict the quality of temporal LPC and temporal HPC respectively. The quality measures of the LPC and the HPC are then combined as GoF quality. A temporal pooling strategy is subsequently used to integrate GoF qualities into an overall video quality. The proposed VQA method appropriately processes temporal information in video by MCTF and temporal pooling strategy, and simulate human visual perception by MFL. Experiments on publicly available video quality database showed that in comparison with several state-of-the-art VQA methods, the proposed VQA method achieves better consistency with subjective video quality and can predict video quality more accurately.

In big data area a significant challenge about string similarity join is to find all similar pairs more efficiently. In this paper, we propose a parallel processing framework for efficient string similarity join. First, the input is split into some disjoint small subsets according to the joint frequency distribution and the interval distribution of strings. Then the filter-verification strategy is adopted in the computation of string similarity for each subset so that the number of candidate pairs is reduced before an effective pruning strategy is used to improve the performance. Finally, the operation of string join is executed in parallel. Para-Join algorithm based on the multi-threading technique is proposed to implement the framework in a multi-core system while Pada-Join algorithm based on Spark platform is proposed to implement the framework in a cluster system. We prove that Para-Join and Pada-Join cannot only avoid reduplicate computation but also ensure the completeness of the result. Experimental results show that Para-Join can achieve high efficiency and significantly outperform than state-of-the-art approaches, meanwhile, Pada-Join can work on large datasets.