CRISPR/Cas9 is a hot genomic editing tool, but its success limited by the widely varying target efficiencies among different single guide RNAs (sgRNAs). In this study, we proposed C-RNNCrispr, hybrid convolutional neural networks (CNNs) and bidirectional gate recurrent unit network (BGRU) framework, to predict sgRNA on-target activity. C-RNNCrispr consists of two branches: branch epigenetic branch. The receives encoded binary matrix sequence four features as inputs, produces regression...

Off-target effects of CRISPR/Cas9 can lead to suboptimal genome editing outcomes. Numerous deep learning-based approaches have achieved excellent performance for off-target prediction; however, few predict the activities with both mismatches and indels between single guide RNA (sgRNA) target DNA sequence pair. In addition, data imbalance is a common pitfall prediction. Moreover, due complexity genomic contexts, generating an interpretable model also remains challenged. To address these...

CRISPR/Cas9 is a preferred genome editing tool and has been widely adapted to ranges of disciplines, from molecular biology gene therapy. A key prerequisite for the success its capacity distinguish between single guide RNAs (sgRNAs) on target homologous off-target sites. Thus, optimized design sgRNAs by maximizing their on-target activity minimizing potential mutations are crucial concerns this system. Several deep learning models have developed comprehensive understanding sgRNA cleavage...

Accurate prediction of guide RNA (gRNA) on-target efficacy is critical for effective application CRISPR/Cas9 system. Although some machine learning-based and convolutional neural network (CNN)-based methods have been proposed, accuracy remains to be improved. Here, we proposed a novel hybrid system which combines CNNs with support vector regression (SVR) predicting gRNA efficacy. This CNN-SVR composed two major components: merged CNN as the front-end extracting feature an SVR back-end...

Marine microorganisms are considered to be an important source of bioactive molecules against various diseases and have great potential increase the number lead in clinical trials. Progress novel microbial culturing techniques as well greater accessibility unique oceanic habitats has placed marine environment a new frontier field natural product drug discovery. A total 24 extracts from deep-sea brine pools Red Sea been evaluated for their anticancer three human cancer cell lines. Downstream...

CRISPR/Cas9 is a powerful genome-editing tool in biology, but its wide applications are challenged by lack of knowledge governing single-guide RNA (sgRNA) activity. Several deep-learning-based methods have been developed for the prediction on-target However, there still room improvement. Here, we proposed hybrid neural network named CrnnCrispr, which integrates convolutional and recurrent activity prediction. We performed unbiased experiments with four mainstream on nine public datasets...

Abstract Metabolic syndrome (MetS) is a group of physiological states metabolic disorders, which may increase the risk diabetes, cardiovascular and other diseases. Therefore, it great significance to predict onset MetS corresponding factors. In this study, we investigate prediction for using data set 67,730 samples with physical examination records three consecutive years provided by Department Health Management, Nanfang Hospital, Southern Medical University, P.R. China. Specifically, takes...

Circular RNA (circRNA) is a closed long non-coding (lncRNA) formed by covalently loops through back-splicing. Emerging evidence indicates that circRNA can influence cellular physiology various molecular mechanisms. Thus, accurate identification and prediction of its regulatory information are critical for understanding biogenesis. Although several computational tools based on machine learning have been proposed identification, the accuracy remains to be improved. Here, first we present...

Chemical exchange saturation transfer (CEST) is an emerging MRI contrast mechanism that capable of noninvasively imaging dilute CEST agents and local properties such as pH temperature, augmenting the routine methods. However, includes a long RF pulse followed by fast image readout, which associated with high specific absorption rate limited spatial resolution. In addition, echo planar (EPI)-based readout prone to distortion, particularly severe at field. To address these limitations, we...

The aim of this study is to describe the acute effects EtOH on brain edema and cerebral metabolites, using diffusion weight imaging (DWI) proton magnetic resonance spectroscopy ((1)H-MRS) at a 7.0T MR define changes in apparent coefficient (ADC) values concentration metabolites rat after intoxication. ADC each ROI decreased significantly 1 h 3 ethanol administration. frontal lobe were compared with other regions h. For EtOH/Cr+PCr (Cho, Tau, Glu) differing over time, no significant...

Aim To characterize the abnormal metabolic profile of all-trans-retinoic acid (ATRA)–induced craniofacial development in mouse embryos using proton magnetic resonance spectroscopy (1H-MRS). Methods Timed-pregnant mice were treated by oral gavage on morning embryonic gestation day 11 (E11) with (ATRA). Dosing solutions adjusted maternal body weight to provide 30, 70, or 100 mg/kg RA. The control group was given an equivalent volume carrier alone. Using Agilent 7.0 T MR system and a...

The present study aimed to explore the influence of sirtuin 1 (SIRT1) polymorphisms (rs12778366 and rs3758391) on diabetic foot (DF) susceptibility severity in patients with type 2 diabetes mellitus (T2DM). This case–control recruited 142 DF, 148 T2DM, healthy controls. SIRT1 gene were sequenced by polymerase chain reaction (PCR) direct sequencing method. relative expression mRNA was estimated using quantitative real-time PCR (qRT-PCR) assay. Odds ratio (OR) 95% confidence interval (95% CI)...

The commercial polymeric anhydride poly(methyl vinyl ether-alt-maleic anhydride) (PVM/MA) is converted by reaction with NaOH to give ether-alt-mono-sodium maleate) (PVM/Na-MA). By addition of AgNO3-solution, the formation silver(i) supramolecular polymer hydrogel poly[methyl maleate]·AgNO3 reported. Freeze-dried samples show a mesoporous network polycarboxylate ligands that are crosslinked cations. In intact hydrogel, ion-exchange studies reported and it shown Ag+ ions can be exchanged...

Glioma is a malignant neoplasm affecting the central nervous system. The conventional approaches to diagnosis, such as T1-weighted imaging (T1WI), T2-weighted (T2WI), and contrast-enhanced T1WI, give an oversimplified representation of anatomic structures. Nuclear Overhauser enhancement (NOE) special form magnetization transfer (MT) that provides new way detect small solute pools through indirect measurement attenuated water signals, makes it possible probe semisolid macromolecular protons....

Copper is a trace element which exerts an important role in neuronal functions. Excessive Cu exposure associated with central nervous system dysfunction, including memory loss. The present study examined the effects of CuCl2 on spatial learning and rats, metabolites hippocampus. A total 60 male Sprague‑Dawley rats (10 rats/group) were intraperitoneally injected various doses (0, 0.5, 1.0, 2.0, 4.0 6.0 mg/kg) three times every other day for 6 days. Rats administered 1.0 ml/kg sterile saline...

The detection of short exons is a challenging open problem in the field bioinformatics. Due to fact that weakness existing model-independent methods lies their inability reliably detect small exons, method based on singularity with wavelet transform modulus maxima has been developed for detecting coding sequences (exons) eukaryotic DNA sequences. In analysis our method, local can capture and characterize singularities which helps yield significant patterns are rarely observed traditional...

CRISPR/Cas9 is a popular genome editing technology, yet its clinical application hindered by off-target effects. Many deep learning-based methods are available for prediction. However, few can predict activities with insertions or deletions (indels) between single guide RNA and DNA sequence pairs. Additionally, the analysis of data challenged due to imbalance issue. Moreover, prediction accuracy interpretability remain be improved. Here, we introduce framework, named Crispr-SGRU, mismatches...

Stroke is a serious medical condition that requires emergency care. In the case of ischemic stroke, ischemia may lead to damage blood–brain barrier (BBB); in turn exacerbate condition. Therefore, noninvasive detection BBB represents challenge for experimental and clinical researchers. this study, we assessed onset disruption by means T1-weighted images with administration contrast enhancement agent gadolinium-diethylenetriamine pentaacetic acid (Gd-DTPA) related breakdown brain metabolite...

Abstract Magnetic resonance spectroscopy (MRS) allows the assessment of metabolic contents and biochemical information in vivo. It provides essential compositional diagnosis monitoring central nervous system (CNS) diseases, especially brain tumors. Conventional MRS is usually confined to endogenous metabolites that may lack specificity for certain disease such as differentiating glioma from other tumor non‐tumorous lesions. Therefore, exogenous contrast agents (CAs) improve sensitivity are...

Compressed sensing (CS) has been applied to the field of sub-sampled magnetic resonance imaging (MRI) reconstruction (CS-MRI). Fast iterative shrinkage-thresholding algorithm (FISTA) is an effective method for CS-MR images reconstruction. To investigate accuracy and efficiency proposed algorithm, we it under-sampling MR gained by different MRI scanning sequences. We found peak signal noise ratio (PSNR) reconstructed with varying sampling ratios diminished from Axial T1 weighted (Ax T1)...

Emerging evidence indicates that circRNA can regulate various diseases. However, the mechanisms of in these diseases have not been fully understood. Therefore, detecting potential circRNA-disease associations has far-reaching significance for pathological development and treatment In recent years, deep learning models are used association analysis circRNA-disease, but a lack data limits further improvement. there is an urgent need to mine more semantic information from data. this paper, we...

Clustered regularly interspaced short palindromic repeat/CRISPR-associated protein 9 (CRISPR/Cas9) is a new generation of gene editing technology, which relies on single guide RNA to identify specific sites and Cas9 nuclease edit location in the genome. However, off-target effect this technology hampers its development. In recent years, several deep learning models have been developed for predicting CRISPR/Cas9 activity, contributes more efficient safe therapy. prediction accuracy remains be...

CRISPR/Cas9 has been applied to edit the genome of various organisms, but our understanding editing outcomes at specific sites after Cas9-mediated DNA cleavage is still limited. Several deep learning-based methods have proposed for repair outcome prediction; however, there room improvement in terms performance regarding frameshifts and model interpretability. Here, we present DeepIndel, an end-to-end multi-label regression predicting based on BERT-base module. We demonstrate that outperforms...