Comparative analysis and prediction of quorum-sensing peptides using feature representation learning and machine learning algorithms.

PSRQSP: An effective approach for the interpretable prediction of quorum sensing peptide using propensity score representation learning

SummaryAccurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.

Acyl-homoserine-lactones (AHLs), as the major quorum sensing (QS) signalling molecules in Gram-negative bacteria, have shown great application potential in regulating biological nutrient removal process. The identification of AHLs synthases plays an essential role in in-depth research on QS mechanisms and applications of biological wastewater treatment processes. This work proposed the first prediction model for AHLs synthases based on machine learning algorithms, namely, AHLS-pred. The training dataset AHLS1400 and the independent testing dataset AHLS132 for AHLSs prediction were first established. Three sequence-based feature extraction methods are utilized to generate feature descriptors, namely, amino acid composition, dipeptide composition and G-gap dipeptide composition respectively. Subsequently, the optimal features were obtained based on the sorted feature descriptors (in F-score order) and the sequential forward search strategy. By comparing five different machine learning algorithms, the final prediction model is trained with support vector machine classifier on AHLS1400 in fivefold cross-validation with the best performance (ACC=99.43%, MCC=0.989, AUC= 0.997). The results show that AHLS-pred achieves an ACC of 94.70%, MCC of 0.894 and AUC of 0.995 on the independent testing dataset AHLS132. It demonstrates that AHLS-pred is a promising and powerful prediction method for accelerating the process of AHLSs computational identification.

Low back pain (LBP) is a prevalent health problem worldwide that affects over 80% of adults during their lifetime. Intervertebral disc degeneration (IDD) is a well-recognized leading cause of LBP. IDD is classified into five grades according to the Pfirrmann classification system. The purpose of this study was to identify potential biomarkers in different IDD grades through an integrated analysis of proteome sequencing (PRO-seq), bulk RNA sequencing (bRNA-seq) and single-cell RNA sequencing (scRNA-seq) data. Eight cases of grade I-IV IDD were obtained. Grades I and II were considered non-degenerative discs (relatively normal), whereas grades III and IV were considered degenerative discs. PRO-seq analysis was performed to identify differentially expressed proteins (DEPs) in various IDD grades. Variation analysis was performed on bRNA-seq data to differentiate expressed genes (DEGs) in normal and degenerated discs. In addition, scRNA-seq was performed to validate DEGs in degenerated and non-degenerated nucleus pulposus (NP). Machine learning (ML) algorithms were used to screen hub genes. The receiver operating characteristic (ROC) curve was used to validate the efficiency of the screened hub genes to predict IDD. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were performed to analyze function enrichment and signaling pathways. Protein-protein interaction (PPI) network was used to prioritize disease-related proteins. SERPINA1, ORM2, FGG and COL1A1 were identified through PRO-seq as the hub proteins involved in regulating IDD. ML algorithms selected ten hub genes, including IBSP, COL6A2, MMP2, SERPINA1, ACAN, FBLN7, LAMB2, TTLL7, COL9A3, and THBS4 in bRNA-seq. Since serine protease inhibitor clade A member 1 (SERPINA1) was the only common gene, its accuracy in degenerated and non-degenerated NP cells was validated using scRNA-seq. Then, the rat degeneration model of caudal vertebra was established. The expression of SERPINA1 and ORM2 was detected using immunohistochemical staining of human and rat intervertebral discs. The results showed that SERPINA1 was poorly expressed in the degenerative group. We further explored the potential function of SERPINA1 by Gene Set Enrichment Analysis (GSEA) and cell-cell communication. Therefore, SERPINA1 can be used as a biomarker to regulate or predict the progress of disc degeneration.

Weight embedding autoencoder as feature representation learning in an intrusion detection systems

Quorum sensing and the regulation of virulence gene expression in pathogenic bacteria

State representation learning for control: An overview

We propose novel deep speaker representation learning that considers perceptual similarity among speakers for multi-speaker generative modeling. Following its success in accurate discriminative modeling of speaker individuality, knowledge of deep speaker representation learning (i.e., speaker representation learning using deep neural networks) has been introduced to multi-speaker generative modeling. However, the conventional discriminative algorithm does not necessarily learn speaker embeddings suitable for such generative modeling, which may result in lower quality and less controllability of synthetic speech. We propose three representation learning algorithms that utilize a perceptual speaker similarity matrix obtained by large-scale perceptual scoring of speaker-pair similarity. The algorithms train a speaker encoder to learn speaker embeddings with three different representations of the matrix: a set of vectors, the Gram matrix, and a graph. Furthermore, we propose an active learning algorithm that iterates the perceptual scoring and speaker encoder training. To obtain accurate embeddings while reducing costs of scoring and training, the algorithm selects unscored speaker-pairs to be scored next on the basis of the sequentially-trained speaker encoder's similarity prediction results. Experimental evaluation results show that 1) the proposed representation learning algorithms learn speaker embeddings strongly correlated with perceptual speaker-pair similarity, 2) the embeddings improve synthetic speech quality in speech autoencoding tasks better than conventional d-vectors learned by discriminative modeling, 3) the proposed active learning algorithm achieves higher synthetic speech quality while reducing costs of scoring and training, and 4) among the proposed similarity {vector, matrix, graph} embedding algorithms, the first achieves the best speaker similarity for synthetic speech and the third gives the most improvement in the synthetic speech naturalness.

AIMAFE: Autism spectrum disorder identification with multi-atlas deep feature representation and ensemble learning

A meta-learning framework using representation learning to predict drug-drug interaction

The oligopeptide ABC-importers are essential communication channels in Gram-positive bacteria

Sparse coding is an active research topic in machine learning and signal processing community. In this paper, we propose a novel local sparse model for multi-label image annotation. Existing feature descriptors and extraction algorithms pay less attention to semantic information and extracted feature dimension usually is high, which leads to heavy computation. Noise and redundant information often reduce the performance of sparse model. To address these issues, we combine label and visual information for feature selection while most previous work only utilizes labels and ignores visual information itself. First of all, we make use of label sets to seek images neighbor relations and generate the Gaussian kernel matrix over these neighbor images, then use LLP(Local Learning Projection) algorithm to get minimal local estimation error. After that, for each query image, we find its K nearest neighbors in the transformed space and use these neighbors to reconstruct it via sparse coding. Moreover, during coding, we penalize the corresponding reconstruction coefficients to implicitly reflect the neighbor relations. Finally, propagating tags from training data to test data. Image annotation experiments on the Corel5k dataset show the performance of our approach is comparable to several state-of-the-art algorithms.

Learning feature representations from unlabeled data for volcano-seismic event classification

Semi-supervised learning (SSL), as one of the dominant methods, aims at leveraging the unlabeled data to deal with the annotation dilemma of supervised learning, which has attracted much attentions in the medical image segmentation. Most of the existing approaches leverage a unitary network by convolutional neural networks (CNNs) with compulsory consistency of the predictions through small perturbations applied to inputs or models. The penalties of such a learning paradigm are that (1) CNN-based models place severe limitations on global learning; (2) rich and diverse class-level distributions are inhibited. In this paper, we present a novel CNN-Transformer learning framework in the manifold space for semi-supervised medical image segmentation. First, at intra-student level, we propose a novel class-wise consistency loss to facilitate the learning of both discriminative and compact target feature representations. Then, at inter-student level, we align the CNN and Transformer features using a prototype-based optimal transport method. Extensive experiments show that our method outperforms previous state-of-the-art methods on three public medical image segmentation benchmarks.

Quorum sensing peptides (QSPs) are bacterial peptides produced by Gram-positive bacteria to communicate with their peers in a cell-density dependent manner. These peptides do not only act as interbacterial communication signals, but can also have effects on the host. Compelling evidence demonstrates the presence of a gut-brain axis and more specifically, the role of the gut microbiota in microglial functioning. The aim of this study is to investigate microglial activating properties of a selected QSP (PapRIV) which is produced by Bacillus cereus species. PapRIV showed in vitro activating properties of BV-2 microglia cells and was able to cross the in vitro Caco-2 cell model and reach the brain. In vivo peptide presence was also demonstrated in mouse plasma. The peptide caused induction of IL-6, TNFα and ROS expression and increased the fraction of ameboid BV-2 microglia cells in an NF-κB dependent manner. Different metabolites were identified in serum, of which the main metabolite still remained active. PapRIV is thus able to cross the gastro-intestinal tract and the blood–brain barrier and shows in vitro activating properties in BV-2 microglia cells, hereby indicating a potential role of this quorum sensing peptide in gut-brain interaction.