DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning.

It is now known that RNAs play more active roles in cellular pathways beyond simply serving as transcription templates. These biological mechanisms might be mediated by higher RNA stereo conformations, triggering the need to understand RNA secondary structures first. However, experimental protocols for solving RNA structures are unavailable for large-scale investigation due to their high costs and time-consuming nature. Various computational tools were thus developed to predict the RNA secondary structures from sequences. Recently, deep networks have been investigated to help predict RNA structures directly from their sequences. However, existing deep-learning-based tools are more or less suffering from model overfitting due to their complicated problem formulation and defective model training processes, limiting their applications across sequences from different structural families. In this research, we designed a two-stage RNA structure prediction strategy called DEBFold (deep ensemble boosting and folding) based on convolution encoding/decoding and self-attention mechanisms to enhance the existing thermodynamic structure models. Moreover, the model training process followed rigorous steps to achieve an acceptable prediction generalization. On the family-wise reserved test sets and the PDB-derived test set, DEBFold achieves better structure prediction performance over traditional tools and existing deep-learning methods. In summary, we obtained a cutting-edge deep-learning-based structure prediction tool with supreme across-family generalization performance. The DEBFold tool can be accessed at https://cobis.bme.ncku.edu.tw/DEBFold/.

Identifying Human miRNA Target Sites via Learning the Interaction Patterns between miRNA and mRNA Segments.

miRNAs (microRNAs) target specific mRNA (messenger RNA) sites to regulate their translation expression. Although miRNA targeting can rely on seed region base pairing, animal miRNAs, including human miRNAs, typically cooperate with several cofactors, leading to various noncanonical pairing rules. Therefore, identifying the binding sites of animal miRNAs remains challenging. Because experiments for mapping miRNA targets are costly, computational methods are preferred for extracting potential miRNA-mRNA fragment binding pairs first. However, existing prediction tools can have significant false positives due to the prevalent noncanonical miRNA binding behaviors and the information-biased training negative sets that were used while constructing these tools. To overcome these obstacles, we first prepared an information-balanced miRNA binding pair ground-truth data set. A miRNA-mRNA interaction-aware model was then designed to help identify miRNA binding events. On the test set, our model (auROC = 94.4%) outperformed existing models by at least 2.8% in auROC. Furthermore, we showed that this model can suggest potential binding patterns for miRNA-mRNA sequence interacting pairs. Finally, we made the prepared data sets and the designed model available at http://cosbi2.ee.ncku.edu.tw/mirna_binding/download.

Identifying piRNA targets on mRNAs in C. elegans using a deep multi-head attention network.

BACKGROUND: Piwi-interacting RNAs (piRNAs) are the small non-coding RNAs (ncRNAs) that silence genomic transposable elements. And researchers found out that piRNA also regulates various endogenous transcripts. However, there is no systematic understanding of the piRNA binding patterns and how piRNA targets genes. While various prediction methods have been developed for other similar ncRNAs (e.g., miRNAs), piRNA holds distinctive characteristics and requires its own computational model for binding target prediction. RESULTS: Recently, transcriptome-wide piRNA binding events in C. elegans were probed by PRG-1 CLASH experiments. Based on the probed piRNA-messenger RNAs (mRNAs) binding pairs, in this research, we devised the first deep learning architecture based on multi-head attention to computationally identify piRNA targeting mRNA sites. In the devised deep network, the given piRNA and mRNA segment sequences are first one-hot encoded and undergo a combined operation of convolution and squeezing-extraction to unravel motif patterns. And we incorporate a novel multi-head attention sub-network to extract the hidden piRNA binding rules that can simulate the biological piRNA target recognition process. Finally, the true piRNA-mRNA binding pairs are identified by a deep fully connected sub-network. Our model obtains a supreme discriminatory power of AUC [Formula: see text] 93.3% on an independent test set and successfully extracts the verified binding pattern of a synthetic piRNA. These results demonstrated that the devised model achieves high prediction performance and suggests testable potential biological piRNA binding rules. CONCLUSIONS: In this research, we developed the first deep learning method to identify piRNA targeting sites on C. elegans mRNAs. And the developed deep learning method is demonstrated to be of high accuracy and can provide biological insights into piRNA-mRNA binding patterns. The piRNA binding target identification network can be downloaded from http://cosbi2.ee.ncku.edu.tw/data_download/piRNA_mRNA_binding .

Role of the Inflammatory Response of RAW 264.7 Cells in the Metastasis of Novel Cancer Stem-Like Cells.

Background and objectives: Tumor progression and the immune response are intricately linked. Additionally, the presence of macrophages in the microenvironment is essential for carcinogenesis, but regulation of the polarization of M1- and M2-like macrophages and their role in metastasis remain unclear. Based on previous studies, both reactive oxygen species (ROS) and the endoplasmic reticulum (ER) are emerging as key players in macrophage polarization. While it is known that cancers alter macrophage inflammatory responses to promote tumor progression, there is limited knowledge regarding how they affect the macrophage-dependent innate host defense. Materials and methods: We detected the levels of ROS, the ability of chemotaxis, the expressions of markers of M1-/M2-like macrophages in RAW264.7 in presence of T2- and T2C-conditioned medium. Results: The results of this study indicated that ROS levels were decreased in RAW 264.7 cells when cultured with T2C-conditioned medium, while there was an improvement in chemotaxis abilities. We also found that the M2-like macrophages were characterized by an elongated shape in RAW 264.7 cells cultured in T2C-conditioned medium, which had increased CD206 expression but decreased expression of CD86 and inducible nitric oxide synthase. Suppression of ER stress shifted polarized M1-like macrophages toward an M2-like phenotype in RAW 264.7 cells cultured in T2C-conditioned medium. Conclusions: Taken together, we conclude that the polarization of macrophages is associated with the alteration of cell shape, ROS accumulation, and ER stress.

Transcription factor regulatory modules provide the molecular mechanisms for functional redundancy observed among transcription factors in yeast.

BACKGROUND: Current technologies for understanding the transcriptional reprogramming in cells include the transcription factor (TF) chromatin immunoprecipitation (ChIP) experiments and the TF knockout experiments. The ChIP experiments show the binding targets of TFs against which the antibody directs while the knockout techniques find the regulatory gene targets of the knocked-out TFs. However, it was shown that these two complementary results contain few common targets. Researchers have used the concept of TF functional redundancy to explain the low overlap between these two techniques. But the detailed molecular mechanisms behind TF functional redundancy remain unknown. Without knowing the possible molecular mechanisms, it is hard for biologists to fully unravel the cause of TF functional redundancy. RESULTS: To mine out the molecular mechanisms, a novel algorithm to extract TF regulatory modules that help explain the observed TF functional redundancy effect was devised and proposed in this research. The method first searched for candidate TF sets from the TF binding data. Then based on these candidate sets the method utilized the modified Steiner Tree construction algorithm to construct the possible TF regulatory modules from protein-protein interaction data and finally filtered out the noise-induced results by using confidence tests. The mined-out regulatory modules were shown to correlate to the concept of functional redundancy and provided testable hypotheses of the molecular mechanisms behind functional redundancy. And the biological significance of the mined-out results was demonstrated in three different biological aspects: ontology enrichment, protein interaction prevalence and expression coherence. About 23.5% of the mined-out TF regulatory modules were literature-verified. Finally, the biological applicability of the proposed method was shown in one detailed example of a verified TF regulatory module for pheromone response and filamentous growth in yeast. CONCLUSION: In this research, a novel method that mined out the potential TF regulatory modules which elucidate the functional redundancy observed among TFs is proposed. The extracted TF regulatory modules not only correlate the molecular mechanisms to the observed functional redundancy among TFs, but also show biological significance in inferring TF functional binding target genes. The results provide testable hypotheses for biologists to further design subsequent research and experiments.

iPhos: a toolkit to streamline the alkaline phosphatase-assisted comprehensive LC-MS phosphoproteome investigation.

BACKGROUND: Comprehensive characterization of the phosphoproteome in living cells is critical in signal transduction research. But the low abundance of phosphopeptides among the total proteome in cells remains an obstacle in mass spectrometry-based proteomic analysis. To provide a solution, an alternative analytic strategy to confidently identify phosphorylated peptides by using the alkaline phosphatase (AP) treatment combined with high-resolution mass spectrometry was provided. While the process is applicable, the key integration along the pipeline was mostly done by tedious manual work. RESULTS: We developed a software toolkit, iPhos, to facilitate and streamline the work-flow of AP-assisted phosphoproteome characterization. The iPhos tookit includes one assister and three modules. The iPhos Peak Extraction Assister automates the batch mode peak extraction for multiple liquid chromatography mass spectrometry (LC-MS) runs. iPhos Module-1 can process the peak lists extracted from the LC-MS analyses derived from the original and dephosphorylated samples to mine out potential phosphorylated peptide signals based on mass shift caused by the loss of some multiples of phosphate groups. And iPhos Module-2 provides customized inclusion lists with peak retention time windows for subsequent targeted LC-MS/MS experiments. Finally, iPhos Module-3 facilitates to link the peptide identifications from protein search engines to the quantification results from pattern-based label-free quantification tools. We further demonstrated the utility of the iPhos toolkit on the data of human metastatic lung cancer cells (CL1-5). CONCLUSIONS: In the comparison study of the control group of CL1-5 cell lysates and the treatment group of dasatinib-treated CL1-5 cell lysates, we demonstrated the applicability of the iPhos toolkit and reported the experimental results based on the iPhos-facilitated phosphoproteome investigation. And further, we also compared the strategy with pure DDA-based LC-MS/MS phosphoproteome investigation. The results of iPhos-facilitated targeted LC-MS/MS analysis convey more thorough and confident phosphopeptide identification than the results of pure DDA-based analysis.

The Yeast Nucleosome Atlas (YNA) database: an integrative gene mining platform for studying chromatin structure and its regulation in yeast.

BACKGROUND: Histone modification and remodeling play crucial roles in regulating gene transcription. These post-translational modifications of histones function in a combinatorial fashion and can be recognized by specific histone-binding proteins, thus regulating gene transcription. Therefore, understanding the combinatorial patterns of the histone code is vital to understanding the associated biological processes. However, most of the datasets regarding histone modification and chromatin regulation are scattered across various studies, and no comprehensive search and query tool has yet been made available to retrieve genes bearing specific histone modification patterns and regulatory proteins. DESCRIPTION: For this reason, we developed the Yeast Nucleosome Atlas database, or the YNA database, which integrates the available experimental data on nucleosome occupancy, histone modifications, the binding occupancy of regulatory proteins, and gene expression data, and provides the genome-wide gene miner to retrieve genes with a specific combination of these chromatin-related datasets. Moreover, the biological significance analyzer, which analyzes the enrichments of histone modifications, binding occupancy, transcription rate, and functionality of the retrieved genes, was constructed to help researchers to gain insight into the correlation among chromatin regulation and transcription. CONCLUSIONS: Compared to previously established genome browsing databases, YNA provides a powerful gene mining and retrieval interface, and is an investigation tool that can assist users to generate testable hypotheses for studying chromatin regulation during transcription. YNA is available online at http://cosbi3.ee.ncku.edu.tw/yna/.

DMLS: an automated pipeline to extract the Drosophila modular transcription regulators and targets from massive literature articles.

Transcription regulation in multicellular species is mediated by modular transcription factor (TF) binding site combinations termed cis-regulatory modules (CRMs). Such CRM-mediated transcription regulation determines the gene expression patterns during development. Biologists frequently investigate CRM transcription regulation on gene expressions. However, the knowledge of the target genes and regulatory TFs participating in the CRMs under study is mostly fragmentary throughout the literature. Researchers need to afford tremendous human resources to fully surf through the articles deposited in biomedical literature databases in order to obtain the information. Although several novel text-mining systems are now available for literature triaging, these tools do not specifically focus on CRM-related literature prescreening, failing to correctly extract the information of the CRM target genes and regulatory TFs from the literature. For this reason, we constructed a supportive auto-literature prescreener called Drosophila Modular transcription-regulation Literature Screener (DMLS) that achieves the following: (i) prescreens articles describing experiments on modular transcription regulation, (ii) identifies the described target genes and TFs of the CRMs under study for each modular transcription-regulation-describing article and (iii) features an automated and extendable pipeline to perform the task. We demonstrated that the final performance of DMLS in extracting the described target gene and regulatory TF lists of CRMs under study for given articles achieved test macro area under the ROC curve (auROC) = 89.7% and area under the precision-recall curve (auPRC) = 77.6%, outperforming the intuitive gene name-occurrence-counting method by at least 19.9% in auROC and 30.5% in auPRC. The web service and the command line versions of DMLS are available at https://cobis.bme.ncku.edu.tw/DMLS/  and  https://github.com/cobisLab/DMLS/, respectively. Database Tool URL: https://cobis.bme.ncku.edu.tw/DMLS/.

Magnetic resonance imaging-based deep learning imaging biomarker for predicting functional outcomes after acute ischemic stroke.

PURPOSE: Clinical risk scores are essential for predicting outcomes in stroke patients. The advancements in deep learning (DL) techniques provide opportunities to develop prediction applications using magnetic resonance (MR) images. We aimed to develop an MR-based DL imaging biomarker for predicting outcomes in acute ischemic stroke (AIS) and evaluate its additional benefit to current risk scores. METHOD: This study included 3338 AIS patients. We trained a DL model using deep neural network architectures on MR images and radiomics to predict poor functional outcomes at three months post-stroke. The DL model generated a DL score, which served as the DL imaging biomarker. We compared the predictive performance of this biomarker to five risk scores on a holdout test set. Additionally, we assessed whether incorporating the imaging biomarker into the risk scores improved the predictive performance. RESULTS: The DL imaging biomarker achieved an area under the receiver operating characteristic curve (AUC) of 0.788. The AUCs of the five studied risk scores were 0.789, 0.793, 0.804, 0.810, and 0.826, respectively. The imaging biomarker's predictive performance was comparable to four of the risk scores but inferior to one (p = 0.038). Adding the imaging biomarker to the risk scores improved the AUCs (p-values) to 0.831 (0.003), 0.825 (0.001), 0.834 (0.003), 0.836 (0.003), and 0.839 (0.177), respectively. The net reclassification improvement and integrated discrimination improvement indices also showed significant improvements (all p < 0.001). CONCLUSIONS: Using DL techniques to create an MR-based imaging biomarker is feasible and enhances the predictive ability of current risk scores.

BAPCP: A comprehensive and user-friendly web tool for identifying biomarkers from protein microarray technologies.

BACKGROUND AND OBJECTIVE: Proteome microarrays are one of the popular high-throughput screening methods for large-scale investigation of protein interactions in cells. These interactions can be measured on protein chips when coupled with fluorescence-labeled probes, helping indicate potential biomarkers or discover drugs. Several computational tools were developed to help analyze the protein chip results. However, existing tools fail to provide a user-friendly interface for biologists and present only one or two data analysis methods suitable for limited experimental designs, restricting the use cases. METHODS: In order to facilitate the biomarker examination using protein chips, we implemented a user-friendly and comprehensive web tool called BAPCP (Biomarker Analysis tool for Protein Chip Platforms) in this research to deal with diverse chip data distributions. RESULTS: BAPCP is well integrated with standard chip result files and includes 7 data normalization methods and 7 custom-designed quality control/differential analysis filters for biomarker extraction among experiment groups. Moreover, it can handle cost-efficient chip designs that repeat several blocks/samples within one single slide. Using experiments of the human coronavirus (HCoV) protein microarray and the E. coli proteome chip that helps study the immune response of Kawasaki disease as examples, we demonstrated that BAPCP can accelerate the time-consuming week-long manual biomarker identification process to merely 3 min. CONCLUSIONS: The developed BAPCP tool provides substantial analysis support for protein interaction studies and conforms to the necessity of expanding computer usage and exchanging information in bioscience and medicine. The web service of BAPCP is available at https://cosbi.ee.ncku.edu.tw/BAPCP/.

Associations of diabetes status and glucose measures with outcomes after endovascular therapy in patients with acute ischemic stroke: an analysis of the nationwide TREAT-AIS registry.

Background: Hyperglycemia affects the outcomes of endovascular therapy (EVT) for acute ischemic stroke (AIS). This study compares the predictive ability of diabetes status and glucose measures on EVT outcomes using nationwide registry data. Methods: The study included 1,097 AIS patients who underwent EVT from the Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke. The variables analyzed included diabetes status, admission glucose, glycated hemoglobin (HbA1c), admission glucose-to-HbA1c ratio (GAR), and outcomes such as 90-day poor functional outcome (modified Rankin Scale score ≥ 2) and symptomatic intracranial hemorrhage (SICH). Multivariable analyses investigated the independent effects of diabetes status and glucose measures on outcomes. A receiver operating characteristic (ROC) analysis was performed to compare their predictive abilities. Results: The multivariable analysis showed that individuals with known diabetes had a higher likelihood of poor functional outcomes (odds ratios [ORs] 2.10 to 2.58) and SICH (ORs 3.28 to 4.30) compared to those without diabetes. Higher quartiles of admission glucose and GAR were associated with poor functional outcomes and SICH. Higher quartiles of HbA1c were significantly associated with poor functional outcomes. However, patients in the second HbA1c quartile (5.6-5.8%) showed a non-significant tendency toward good functional outcomes compared to those in the lowest quartile (<5.6%). The ROC analysis indicated that diabetes status and admission glucose had higher predictive abilities for poor functional outcomes, while admission glucose and GAR were better predictors for SICH. Conclusion: In AIS patients undergoing EVT, diabetes status, admission glucose, and GAR were associated with 90-day poor functional outcomes and SICH. Admission glucose was likely the most suitable glucose measure for predicting outcomes after EVT.

Co-modulated behavior and effects of differentially expressed miRNA in colorectal cancer.

BACKGROUND: MicroRNAs (miRNAs) are short noncoding RNAs (approximately 22 nucleotides in length) that play important roles in colorectal cancer (CRC) progression through silencing gene expression. Numerous dysregulated miRNAs simultaneously participate in the process of colon cancer development. However, the detailed mechanisms and biological functions of co-expressed miRNA in colorectal carcinogenesis have yet to be fully elucidated. RESULTS: The objective of this study was to identify the dysfunctional miRNAs and their target mRNAs using a wet-lab experimental and dry-lab bioinformatics approach. The differentially expressed miRNA candidates were identified from 2 miRNA profiles, and were confirmed in CRC clinical samples using reported target genes of dysfunctional miRNAs to perform functional pathway enrichment analysis. Potential target gene candidates were predicted by an in silico search, and their expression levels between normal and colorectal tumor tissues were further analyzed using real-time polymerase chain reaction (RT-PCR). CONCLUSION: Fifteen dysfunctional miRNAs were engaged in metastasis-associated pathways through comodulating 7 target genes, which were identified by using a multi-step approach. The roles of these candidate genes are worth further exploration in the progression of colon cancer, and could potentially be targets in future therapy.

CFA: An explainable deep learning model for annotating the transcriptional roles of cis-regulatory modules based on epigenetic codes.

Metazoa gene expression is controlled by modular DNA segments called cis-regulatory modules (CRMs). CRMs can convey promoter/enhancer/insulator roles, generating additional regulation layers in transcription. Experiments for understanding CRM roles are low-throughput and costly. Large-scale CRM function investigation still depends on computational methods. However, existing in silico tools only recognize enhancers or promoters exclusively, thus accumulating errors when considering CRM promoter/enhancer/insulator roles altogether. Currently, no algorithm can concurrently consider these CRM roles. In this research, we developed the CRM Function Annotator (CFA) model. CFA provides complete CRM transcriptional role labeling based on epigenetic profiling interpretation. We demonstrated that CFA achieves high performance (test macro auROC/auPRC = 94.1%/90.3%) and outperforms existing tools in promoter/enhancer/insulator identification. CFA is also inspected to recognize explainable epigenetic codes consistent with previous findings when labeling CRM roles. By considering the higher-order combinations of the epigenetic codes, CFA significantly reduces false-positive rates in CRM transcriptional role annotation. CFA is available at https://github.com/cobisLab/CFA/.

RDDL: A systematic ensemble pipeline tool that streamlines balancing training schemes to reduce the effects of data imbalance in rare-disease-related deep-learning applications.

Identifying lowly prevalent diseases, or rare diseases, in their early stages is key to disease treatment in the medical field. Deep learning techniques now provide promising tools for this purpose. Nevertheless, the low prevalence of rare diseases entangles the proper application of deep networks for disease identification due to the severe class-imbalance issue. In the past decades, some balancing methods have been studied to handle the data-imbalance issue. The bad news is that it is verified that none of these methods guarantees superior performance to others. This performance variation causes the need to formulate a systematic pipeline with a comprehensive software tool for enhancing deep-learning applications in rare disease identification. We reviewed the existing balancing schemes and summarized a systematic deep ensemble pipeline with a constructed tool called RDDL for handling the data imbalance issue. Through two real case studies, we showed that rare disease identification could be boosted with this systematic RDDL pipeline tool by lessening the data imbalance problem during model training. The RDDL pipeline tool is available at https://github.com/cobisLab/RDDL/.

Precisely Closed Reduction of Nasal Bone Fracture Assisted With Plain Film Measurements Under the Picture Archiving and Communication System.

OBJECTIVES: To prevent aesthetic and functional deformities, precisely closed reduction is crucial in the management of nasal fractures. Plain film radiography (PF), ultrasonography (USG), and computed tomography can help confirm the diagnosis and classification of fractures and assist in performing closed reduction. However, no study in the literature reports on precisely closed reduction assisted with PF measurements under the picture archiving and communication system (PACS). METHODS: We retrospectively evaluated 153 patients with nasal bone fracture between January 2013 and December 2017. Surgeons conducted precisely closed reduction assisted with PF measurement of the distance between the fracture site and nasal tip under PACS on 34 patients (group A). Another group on 119 patients were reduced under surgeon's experience (group B). RESULTS: No significant differences in age, gender, Arbeitsgemeinschaft fur Osteosynthesefragen (AO) classification, and reduction outcome were observed between group A and group B (P > .05). The operative time of the group A was significantly lower (12.50 ± 4.64 minutes) compared to group B (23.78 ± 11.20 minutes; P < .001). After adjusted age, gender, and AO classification, patients in group A scored 10.46 minutes less on the operative time than those in group B (P < .001). In addition, the severity of nasal bone fracture (AO classification, ß = 3.37, P = .002) was positive associated with the operative time. CONCLUSIONS: In this study, closed reduction in nasal bone fracture assisted with PF measurements under PACS was performed precisely, thereby effectively decreasing operative time and the occurrence of complications. This procedure requires neither the use of new instruments or C-arm nor USG or navigation experience. Moreover, reduction can be easily performed using this method, and it requires short operative time, helps achieve great reduction, less radiation exposures, and is cost-effective.

Mechanical Behaviors of Microwave-Assisted Pyrolysis Recycled Carbon Fiber-Reinforced Concrete with Early-Strength Cement.

This study aimed to investigate the mechanical performance of early-strength carbon fiber-reinforced concrete (ECFRC) by incorporating original carbon fiber (OCF), recycled carbon fiber (RCF), and sizing-removed carbon fiber (SCF). Compressive, flexural, and splitting tensile strength were tested under three fiber-to-cement weight ratios (5‱, 10‱, and 15‱). The RCF was produced from waste bicycle parts made of carbon fiber-reinforced polymer (CFRP) through microwave-assisted pyrolysis (MAP). The sizing-removed fiber was obtained through a heat-treatment method applied to the OCF. The results of scanning electron microscopy (SEM) analysis with energy dispersive X-ray spectrometry (EDS) indicated the successful removal of sizing and impurities from the surface of the RCF and SCF. The mechanical test results showed that ECFRC with a 10‱ fiber-to-cement weight ratio of carbon fiber had the greatest improvement in its mechanical strengths. Moreover, the ECFRC with 10‱ RCF exhibited higher compressive, flexural, and splitting tensile strength than that of benchmark specimen by 14.2%, 56.5%, and 22.5%, respectively. The ECFRC specimens with a 10‱ fiber-to-cement weight ratio were used to analyze their impact resistance under various impact energies in the impact test. At 50 joules of impact energy, the impact number of the ECFRC with SCF was over 23 times that of the benchmark specimen (early-strength concrete without fiber) and was also greater than that of ECFRC with OCF and RCF.

An Aggregation Method to Identify the RNA Meta-Stable Secondary Structure and its Functionally Interpretable Structure Ensemble.

RNA can provide vital cellular functions through its secondary or tertiary structure. Due to the low-throughput nature of experimental approaches, studies on RNA structures mainly resort to computational methods. However, current existing tools fail to consider RNA structure ensembles and do not provide ways to decipher functional hypotheses for the new predictions. In this research, a novel method was proposed to identify the functionally interpretable structure ensemble of a given RNA sequence and provide the meta-stable structure, or the most frequently observed functional RNA cellular conformation, based on the ensemble. In the prediction of meta-stable structures, the proposed method outperformed existing tools on a yeast test set. The inferred functional aspects were then manually checked and demonstrated a micro-averaging F1 value of 0.92. Further, a biological example of the yeast ASH1-E1 element was discussed to articulate that these functional aspects can also suggest testable hypotheses. Then the proposed method was verified to be well applicable to other species through a human test set. Finally, the proposed method was demonstrated to show resistance to sequence length-dependent performance deterioration.

regCNN: identifying Drosophila genome-wide cis-regulatory modules via integrating the local patterns in epigenetic marks and transcription factor binding motifs.

Transcription regulation in metazoa is controlled by the binding events of transcription factors (TFs) or regulatory proteins on specific modular DNA regulatory sequences called cis-regulatory modules (CRMs). Understanding the distributions of CRMs on a genomic scale is essential for constructing the metazoan transcriptional regulatory networks that help diagnose genetic disorders. While traditional reporter-assay CRM identification approaches can provide an in-depth understanding of functions of some CRM, these methods are usually cost-inefficient and low-throughput. It is generally believed that by integrating diverse genomic data, reliable CRM predictions can be made. Hence, researchers often first resort to computational algorithms for genome-wide CRM screening before specific experiments. However, current existing in silico methods for searching potential CRMs were restricted by low sensitivity, poor prediction accuracy, or high computation time from TFBS composition combinatorial complexity. To overcome these obstacles, we designed a novel CRM identification pipeline called regCNN by considering the base-by-base local patterns in TF binding motifs and epigenetic profiles. On the test set, regCNN shows an accuracy/auROC of 84.5%/92.5% in CRM identification. And by further considering local patterns in epigenetic profiles and TF binding motifs, it can accomplish 4.7% (92.5%-87.8%) improvement in the auROC value over the average value-based pure multi-layer perceptron model. We also demonstrated that regCNN outperforms all currently available tools by at least 11.3% in auROC values. Finally, regCNN is verified to be robust against its resizing window hyperparameter in dealing with the variable lengths of CRMs. The model of regCNN can be downloaded athttp://cobisHSS0.im.nuk.edu.tw/regCNN/.

SSRTool: A web tool for evaluating RNA secondary structure predictions based on species-specific functional interpretability.

RNA secondary structures can carry out essential cellular functions alone or interact with one another to form the hierarchical tertiary structures. Experimental structure identification approa ches can show the in vitro structures of RNA molecules. However, they usually have limits in the resolution and are costly. In silico structure prediction tools are thus primarily relied on for pre-experiment analysis. Various structure prediction models have been developed over the decades. Since these tools are usually used before knowing the actual RNA structures, evaluating and ranking the pile of secondary structure predictions of a given sequence is essential in computational analysis. In this research, we implemented a web service called SSRTool (RNA Secondary Structure prediction Ranking Tool) to assist in the ranking and evaluation of the generated predicted structures of a given sequence. Based on the computed species-specific interpretability significance in four common RNA structure-function aspects, SSRTool provides three functions along with visualization interfaces: (1) Rank user-generated predictions. (2) Provide an automated streamline of structure prediction and ranking for a given sequence. (3) Infer the functional aspects of a given structure. We demonstrated the applicability of SSRTool via real case studies and reported the similar trends between computed species-specific rankings and the corresponding prediction F1 values. The SSRTool web service is available online at https://cobisHSS0.im.nuk.edu.tw/SSRTool/, http://cosbi3.ee.ncku.edu.tw/SSRTool/, or the redirecting site https://github.com/cobisLab/SSRTool/.

YTLR: Extracting yeast transcription factor-gene associations from the literature using automated literature readers.

Cells adapt to environmental stresses mainly via transcription reprogramming. Correct transcription control is mediated by the interactions between transcription factors (TF) and their target genes. These TF-gene associations can be probed by chromatin immunoprecipitation techniques and knockout experiments, revealing TF binding (TFB) and regulatory (TFR) evidence, respectively. Nevertheless, most evidence is still fragmentary in the literature and requires tremendous human resources to curate. We developed the first pipeline called YTLR (Yeast Transcription-regulation Literature Reader) to automate TF-gene relation extraction from the literature. YTLR first identifies articles with TFB and TFR information. Then TF-gene binding pairs are extracted from the TFB articles, and TF-gene regulatory associations are recognized from the TFR papers. On gathered test sets, YTLR achieves an AUC value of 98.8% in identifying articles with TFB evidence and AUC = 83.4% in extracting the detailed TF-gene binding pairs. And similarly, YTLR also obtains an AUC value of 98.2% in identifying TFR articles and AUC = 80.4% in extracting the detailed TF-gene regulatory associations. Furthermore, YTLR outperforms previous methods in both tasks. To facilitate researchers in extracting TF-gene transcriptional relations from large-scale queried articles, an automated and easy-to-use software tool based on the YTLR pipeline is constructed. In summary, YTLR aims to provide easier literature pre-screening for curators and help researchers gather yeast TF-gene transcriptional relation conclusions from articles in a high-throughput fashion. The YTLR pipeline software tool can be downloaded at https://github.com/cobisLab/YTLR/.