HCRNet: high-throughput circRNA-binding event identification from CLIP-seq data using deep temporal convolutional network.

Identifying genome-wide binding events between circular RNAs (circRNAs) and RNA-binding proteins (RBPs) can greatly facilitate our understanding of functional mechanisms within circRNAs. Thanks to the development of cross-linked immunoprecipitation sequencing technology, large amounts of genome-wide circRNA binding event data have accumulated, providing opportunities for designing high-performance computational models to discriminate RBP interaction sites and thus to interpret the biological significance of circRNAs. Unfortunately, there are still no computational models sufficiently flexible to accommodate circRNAs from different data scales and with various degrees of feature representation. Here, we present HCRNet, a novel end-to-end framework for identification of circRNA-RBP binding events. To capture the hierarchical relationships, the multi-source biological information is fused to represent circRNAs, including various natural language sequence features. Furthermore, a deep temporal convolutional network incorporating global expectation pooling was developed to exploit the latent nucleotide dependencies in an exhaustive manner. We benchmarked HCRNet on 37 circRNA datasets and 31 linear RNA datasets to demonstrate the effectiveness of our proposed method. To evaluate further the model's robustness, we performed HCRNet on a full-length dataset containing 740 circRNAs. Results indicate that HCRNet generally outperforms existing methods. In addition, motif analyses were conducted to exhibit the interpretability of HCRNet on circRNAs. All supporting source code and data can be downloaded from https://github.com/yangyn533/HCRNet and https://doi.org/10.6084/m9.figshare.16943722.v1. And the web server of HCRNet is publicly accessible at http://39.104.118.143:5001/.

iDeepSubMito: identification of protein submitochondrial localization with deep learning.

Mitochondria are membrane-bound organelles containing over 1000 different proteins involved in mitochondrial function, gene expression and metabolic processes. Accurate localization of those proteins in the mitochondrial compartments is critical to their operation. A few computational methods have been developed for predicting submitochondrial localization from the protein sequences. Unfortunately, most of these computational methods focus on employing biological features or evolutionary information to extract sequence features, which greatly limits the performance of subsequent identification. Moreover, the efficiency of most computational models is still under explored, especially the deep learning feature, which is promising but requires improvement. To address these limitations, we propose a novel computational method called iDeepSubMito to predict the location of mitochondrial proteins to the submitochondrial compartments. First, we adopted a coding scheme using the ProteinELMo to model the probability distribution over the protein sequences and then represent the protein sequences as continuous vectors. Then, we proposed and implemented convolutional neural network architecture based on the bidirectional LSTM with self-attention mechanism, to effectively explore the contextual information and protein sequence semantic features. To demonstrate the effectiveness of our proposed iDeepSubMito, we performed cross-validation on two datasets containing 424 proteins and 570 proteins respectively, and consisting of four different mitochondrial compartments (matrix, inner membrane, outer membrane and intermembrane regions). Experimental results revealed that our method outperformed other computational methods. In addition, we tested iDeepSubMito on the M187, M983 and MitoCarta3.0 to further verify the efficiency of our method. Finally, the motif analysis and the interpretability analysis were conducted to reveal novel insights into subcellular biological functions of mitochondrial proteins. iDeepSubMito source code is available on GitHub at https://github.com/houzl3416/iDeepSubMito.

iCircRBP-DHN: identification of circRNA-RBP interaction sites using deep hierarchical network.

Circular RNAs (circRNAs) are widely expressed in eukaryotes. The genome-wide interactions between circRNAs and RNA-binding proteins (RBPs) can be probed from cross-linking immunoprecipitation with sequencing data. Therefore, computational methods have been developed for identifying RBP binding sites on circRNAs. Unfortunately, those computational methods often suffer from the low discriminative power of feature representations, numerical instability and poor scalability. To address those limitations, we propose a novel computational method called iCircRBP-DHN using deep hierarchical network for discriminating circRNA-RBP binding sites. The network architecture can be regarded as a deep multi-scale residual network followed by bidirectional gated recurrent units (BiGRUs) with the self-attention mechanism, which can simultaneously extract local and global contextual information. Meanwhile, we propose novel encoding schemes by integrating CircRNA2Vec and the K-tuple nucleotide frequency pattern to represent different degrees of nucleotide dependencies. To validate the effectiveness of our proposed iCircRBP-DHN, we compared its performance with other computational methods on 37 circRNAs datasets and 31 linear RNAs datasets, respectively. The experimental results reveal that iCircRBP-DHN can achieve superior performance over those state-of-the-art algorithms. Moreover, we perform motif analysis on circRNAs bound by those different RBPs, demonstrating that our proposed CircRNA2Vec encoding scheme can be promising. The iCircRBP-DHN method is made available at https://github.com/houzl3416/iCircRBP-DHN.

Genome-wide identification and characterization of DNA enhancers with a stacked multivariate fusion framework.

Enhancers are short non-coding DNA sequences outside of the target promoter regions that can be bound by specific proteins to increase a gene's transcriptional activity, which has a crucial role in the spatiotemporal and quantitative regulation of gene expression. However, enhancers do not have a specific sequence motifs or structures, and their scattered distribution in the genome makes the identification of enhancers from human cell lines particularly challenging. Here we present a novel, stacked multivariate fusion framework called SMFM, which enables a comprehensive identification and analysis of enhancers from regulatory DNA sequences as well as their interpretation. Specifically, to characterize the hierarchical relationships of enhancer sequences, multi-source biological information and dynamic semantic information are fused to represent regulatory DNA enhancer sequences. Then, we implement a deep learning-based sequence network to learn the feature representation of the enhancer sequences comprehensively and to extract the implicit relationships in the dynamic semantic information. Ultimately, an ensemble machine learning classifier is trained based on the refined multi-source features and dynamic implicit relations obtained from the deep learning-based sequence network. Benchmarking experiments demonstrated that SMFM significantly outperforms other existing methods using several evaluation metrics. In addition, an independent test set was used to validate the generalization performance of SMFM by comparing it to other state-of-the-art enhancer identification methods. Moreover, we performed motif analysis based on the contribution scores of different bases of enhancer sequences to the final identification results. Besides, we conducted interpretability analysis of the identified enhancer sequences based on attention weights of EnhancerBERT, a fine-tuned BERT model that provides new insights into exploring the gene semantic information likely to underlie the discovered enhancers in an interpretable manner. Finally, in a human placenta study with 4,562 active distal gene regulatory enhancers, SMFM successfully exposed tissue-related placental development and the differential mechanism, demonstrating the generalizability and stability of our proposed framework.

Advanced aromatic organic compounds removal from refractory coking wastewater in a step-feed three-stage integrated A/O bio-filter: Spectrum characterization and biodegradation mechanism.

Extensive presence of aromatic organic compounds (AOCs) is a major course for the non-biodegradability of coking wastewater (COW). In-depth understanding of bio-degradation of AOCs is crucial for optimizing the design and operation of COW biological treatment systems in practical applications. Herein, the behavior and fate of AOCs were explored in a lab-scale step-feed three-stage integrated A/O biofilter (SFTIAOB) treating synthetic COW. Long-term operation demonstrated that COD, phenol, indole, quinoline and pyridine could be simultaneously removed. Phenol and indole were chiefly removed by anoxic zones, while quinoline and pyridine removal occurred in both anoxic and aerobic zones. Ultraviolet-visible spectrum observed that initial carboxylation and subsequent ring cracking and mineralization. Infrared spectroscopy also confirmed that key functional groups were cracked and produced during AOCs bio-degradation. Three-dimensional fluorescence spectrum indicated that significant transformation and elimination of tryptophan and humic acid with high molecular weight. Ring cleavage, distinct degradation and even complete mineralization of complex AOCs were further verified by gas chromatography-mass spectrometry. Moreover, functional degrading bacteria and aromatic ring-cleavage enzymes was successfully identified. Finally, AOCs biodegradation mechanisms by alternating anoxic and aerobic treatment was unraveled. This research provides thorough insights on AOCs biodegradation using a step-feed multi-stage alternating anoxic/oxic COW treatment process.

SOFB is a comprehensive ensemble deep learning approach for elucidating and characterizing protein-nucleic-acid-binding residues.

Proteins and nucleic-acids are essential components of living organisms that interact in critical cellular processes. Accurate prediction of nucleic acid-binding residues in proteins can contribute to a better understanding of protein function. However, the discrepancy between protein sequence information and obtained structural and functional data renders most current computational models ineffective. Therefore, it is vital to design computational models based on protein sequence information to identify nucleic acid binding sites in proteins. Here, we implement an ensemble deep learning model-based nucleic-acid-binding residues on proteins identification method, called SOFB, which characterizes protein sequences by learning the semantics of biological dynamics contexts, and then develop an ensemble deep learning-based sequence network to learn feature representation and classification by explicitly modeling dynamic semantic information. Among them, the language learning model, which is constructed from natural language to biological language, captures the underlying relationships of protein sequences, and the ensemble deep learning-based sequence network consisting of different convolutional layers together with Bi-LSTM refines various features for optimal performance. Meanwhile, to address the imbalanced issue, we adopt ensemble learning to train multiple models and then incorporate them. Our experimental results on several DNA/RNA nucleic-acid-binding residue datasets demonstrate that our proposed model outperforms other state-of-the-art methods. In addition, we conduct an interpretability analysis of the identified nucleic acid binding residue sequences based on the attention weights of the language learning model, revealing novel insights into the dynamic semantic information that supports the identified nucleic acid binding residues. SOFB is available at https://github.com/Encryptional/SOFB and https://figshare.com/articles/online_resource/SOFB_figshare_rar/25499452 .

Intermittent hydroxylamine dosing to strengthen stability of partial nitrification and nitrogen removal efficiency through continuous-flow anaerobic-aerobic-anoxic reactor treating municipal wastewater.

Intermittent hydroxylamine (NH2OH) dosing strategy was applied to enhance the stability of partial nitrification and total nitrogen (N) removal efficiency (TNRE) in a continuous-flow process. The results showed 2 mg/L of NH2OH dosing (once every 6 h) could maintain stably partial nitrification with nitrite accumulation rate (NAR) of 91.6 % and TNRE of 92.6 %. The typical cycle suggested NH2OH dosing could promote simultaneous nitrification-denitrification (SND) and endogenous denitrification (END) while inhibit exogenous denitrification (EXD). Nitrification characteristics indicated the NH2OH dosing enhanced stability of partial nitrification by suppressing specific nitrite oxidation rate (SNOR), Nitrospira and nitrite oxidoreductase enzyme (Nxr). The microbial community suggested the aerobic denitrfiers, denitrifying glycogen accumulating organisms (DGAOs) and traditional denitrfiers were the potential contributor for advanced N removal. Moreover, NH2OH dosage was positively associated with NAR, SND and END. Overall, this study offers a feasible strategy to maintain sustainably partial nitrification that has great application potential.

Learning the protein language of proteome-wide protein-protein binding sites via explainable ensemble deep learning.

Protein-protein interactions (PPIs) govern cellular pathways and processes, by significantly influencing the functional expression of proteins. Therefore, accurate identification of protein-protein interaction binding sites has become a key step in the functional analysis of proteins. However, since most computational methods are designed based on biological features, there are no available protein language models to directly encode amino acid sequences into distributed vector representations to model their characteristics for protein-protein binding events. Moreover, the number of experimentally detected protein interaction sites is much smaller than that of protein-protein interactions or protein sites in protein complexes, resulting in unbalanced data sets that leave room for improvement in their performance. To address these problems, we develop an ensemble deep learning model (EDLM)-based protein-protein interaction (PPI) site identification method (EDLMPPI). Evaluation results show that EDLMPPI outperforms state-of-the-art techniques including several PPI site prediction models on three widely-used benchmark datasets including Dset_448, Dset_72, and Dset_164, which demonstrated that EDLMPPI is superior to those PPI site prediction models by nearly 10% in terms of average precision. In addition, the biological and interpretable analyses provide new insights into protein binding site identification and characterization mechanisms from different perspectives. The EDLMPPI webserver is available at http://www.edlmppi.top:5002/ .

Response of nitrite accumulation to elevated C/NO- 3-N ratio during partial denitrification process: Insights of extracellular polymeric substance, microbial community and metabolic function.

This study investigated the response of nitrite accumulation to elevated COD/NO3--N ratio (C/N) during partial denitrification (PD). Results indicated nitrite was gradually accumulated and remained stable (C/N = 1.5 âˆ¼ 3.0), while that rapidly declined after reaching the peak (C/N = 4.0 âˆ¼ 5.0). The polysaccharide (PS) and protein (PN) content of tightly-bound extracellular polymeric substances (TB-EPS) reached the maximum at C/N of 2.5 âˆ¼ 3.0, which might be stimulated by high level of nitrite. Illumina MiSeq sequencing showed Thauera and OLB8 were dominated denitrifying genera at C/N of 1.5 âˆ¼ 3.0, while Thauera was further enriched with fading OLB8 at C/N of 4.0 âˆ¼ 5.0. Meanwhile, the highly-enriched Thauera might enhance the activity of nitrite reductase (nirK) promoting further nitrite reduction. Redundancy analysis (RDA) showed positive correlations between nitrite production and PN content of TB-EPS, denitrifying bacteria (Thauera and OLB8) and nitrate reductases (narG/H/I) in low C/N. Finally, their synergistic effects for driving nitrite accumulation were comprehensively elucidated.

Advanced nitrogen removal from low carbon nitrogen ratio domestic sewage via continuous plug-flow anaerobic/oxic/anoxic system: Enhanced by endogenous denitrification.

An anaerobic/oxic/anoxic continuous plug-flow biorereactor was established to derive stable advanced nitrogen removal of oligotrophic domestic wastewater by setting a sludge dual-reflux system and a mixed liquid cross-flow system, while extending the hydraulic retention time in anoxic section. The effluent total inorganic nitrogen was 7.9 ± 2.2 mg N/L, with removal efficiency of 84 ± 3.9%. Results of nitrogen balance calculations indicated that the contribution of simultaneous nitrification and denitrification to total inorganic nitrogen loss in oxic region was 15% during stable stage, and the total inorganic nitrogen removal by endogenous-denitrification and enhanced exogenous-denitrification in the anoxic region was 39.9%. Prolongation of hydraulic retention time in anoxic segment is the critical reason for enhancing endogenous-denitrification, and cross-flow system is an important measure to improve exogenous-denitrification. This study provides new insights into bridging the gap between energy-saving and high-level nitrogen removal from municipal wastewater with low carbon to nitrogen ratios.

Insight into correlation of advanced nitrogen removal with extracellular polymeric substances characterization in a step-feed three-stage integrated anoxic/oxic biofilter system.

As a core component of the biomass, the important role of extracellular polymeric substances (EPS) on treatment performance has been recognized. However, the comprehensive understanding of its correlation with nitrogen removal remains limited in biofilm-based reactors. In this study, the relevance between EPS and advanced nitrogen removal in a novel step-feed three-stage integrated anoxic/oxic biofilter (SFTIAOB) was specifically investigated. The operation showed as high as 81% TN removal was achieved under optimal conditions. Among the whole reactor, 2nd anoxic (A2) zone was the largest contributor for nitrogen removal, followed by the 3rd anoxic (A3) and 2nd oxic (O2) zones. EPS composition analysis found that high content of polysaccharides in tightly bound-EPS (A2 and A3) and protein in loosely bound-EPS and tightly bound-EPS (O2). Fourier transform infrared spectroscopy, three-dimensional fluorescence spectrum further verified stratified EPS subfractions containing different secondary protein structures, while 3-turn helix and tryptophan-like protein was the main reason for nitrogen removal. High-throughput sequencing revealed the co-existence of nitrogen removal-associated genera accomplished nitrification/denitrification combined with aerobic denitrification and anammox. Moreover, the correlation of EPS and microbial composition with nitrogen removal was clarified by redundancy analysis (RDA). Finally, potential mechanism for nitrogen removal was illuminated. This research gives more insight into EPS characteristics in enhancing nitrogen removal during the operation and optimization of a step-feed multi-stage A/O biofilm process.

Electro-Fenton with peroxi-coagulation as a feasible pre-treatment for high-strength refractory coke plant wastewater: Parameters optimization, removal behavior and kinetics analysis.

Electro-Fenton (EF) with peroxi-coagulation (PC) as an emerging electro-chemical advanced oxidation method has been extensively applied to treat refractory wastewater. However, the studies on the pretreatment of the raw coke plant wastewater by EF process were still lacking. In this study, a lab-scale EF system (Fe as anode and graphite as cathode) achieved the highest COD removal of 69.2% based on the preliminary experiments. The process parameters and corresponding COD removal performance were further optimized using response surface methodology (RSM) combined with Box-Behnken experimental design (BBD). The optimal conditions were obtained as: 3.2 mA cm-2 of current density, 2 h of the reaction time and 2.6 of the initial pH value, with the COD removal reaching 70.0%. Fourier infrared (FTIR), fluorescence excitation-emmission matrix (EEM) and gas chromatography-mass spectrometry (GC-MS) also revealed the degradation behaviors of dissolved organic matters (DOMs) by characterizing their structures and compositions before and after EF pretreatment, thus greatly improving the biodegradability of the wastewater. Moreover, the EF process for COD removal well followed third-order kinetics model. These findings give helpful guidance to design, optimize and control the EF process as a favourable pretreatment for actual refractory coking wastewater in practice.