sgRNACNN: identifying sgRNA on-target activity in four crops using ensembles of convolutional neural networks

DeepMEns: an ensemble model for predicting sgRNA on-target activity based on multiple features

The CRISPR/Cas9 system developed from Streptococcus pyogenes (SpCas9) has high potential in gene editing. However, its successful application is hindered by the considerable variability in target efficiencies across different single guide RNAs (sgRNAs). Although several deep learning models have been created to predict sgRNA on-target activity, the intrinsic mechanisms of these models are difficult to explain, and there is still scope for improvement in prediction performance. To overcome these issues, we propose an ensemble interpretable model termed DeepMEns based on deep learning to predict sgRNA on-target activity. By using five different training and validation datasets, we constructed five sub-regressors, each comprising three parts. The first part uses one-hot encoding, wherein 0-1 representation of the secondary structure is used as the input to the convolutional neural network (CNN) with Transformer encoder. The second part uses the DNA shape feature matrix as the input to the CNN with Transformer encoder. The third part uses positional encoding feature matrices as the proposed input into a long short-term memory network with an attention mechanism. These three parts are concatenated through the flattened layer, and the final prediction result is the average of the five sub-regressors. Extensive benchmarking experiments indicated that DeepMEns achieved the highest Spearman correlation coefficient for 6 of 10 independent test datasets as compared to previous predictors, this finding confirmed that DeepMEns can accomplish state-of-the-art performance. Moreover, the ablation analysis also indicated that the ensemble strategy may improve the performance of the prediction model.

GBMPhos: A Gating Mechanism and Bi-GRU-Based Method for Identifying Phosphorylation Sites of SARS-CoV-2 Infection

Phosphorylation, a reversible and widespread post-translational modification of proteins, is essential for numerous cellular processes. However, due to technical limitations, large-scale detection of phosphorylation sites, especially those infected by SARS-CoV-2, remains a challenging task. To address this gap, we propose a method called GBMPhos, a novel method that combines convolutional neural networks (CNNs) for extracting local features, gating mechanisms to selectively focus on relevant information, and a bi-directional gated recurrent unit (Bi-GRU) to capture long-range dependencies within protein sequences. GBMPhos leverages a comprehensive set of features, including sequence encoding, physicochemical properties, and structural information, to provide an in-depth analysis of phosphorylation sites. We conducted an extensive comparison of GBMPhos with traditional machine learning algorithms and state-of-the-art methods. Experimental results demonstrate the superiority of GBMPhos over existing methods. The visualization analysis further highlights its effectiveness and efficiency. Additionally, we have established a free web server platform to help researchers explore phosphorylation in SARS-CoV-2 infections. The source code of GBMPhos is publicly available on GitHub.

Optimizing protein sequence classification: integrating deep learning models with Bayesian optimization for enhanced biological analysis

Efforts to enhance the accuracy of protein sequence classification are of utmost importance in driving forward biological analyses and facilitating significant medical advancements. This study presents a cutting-edge model called ProtICNN-BiLSTM, which combines attention-based Improved Convolutional Neural Networks (ICNN) and Bidirectional Long Short-Term Memory (BiLSTM) units seamlessly. Our main goal is to improve the accuracy of protein sequence classification by carefully optimizing performance through Bayesian Optimisation. ProtICNN-BiLSTM combines the power of CNN and BiLSTM architectures to effectively capture local and global protein sequence dependencies. In the proposed model, the ICNN component uses convolutional operations to identify local patterns. Captures long-range associations by analyzing sequence data forward and backwards. In advanced biological studies, Bayesian Optimisation optimizes model hyperparameters for efficiency and robustness. The model was extensively confirmed with PDB-14,189 and other protein data. We found that ProtICNN-BiLSTM outperforms traditional categorization models. Bayesian Optimization's fine-tuning and seamless integration of local and global sequence information make it effective. The precision of ProtICNN-BiLSTM improves comparative protein sequence categorization. The study improves computational bioinformatics for complex biological analysis. Good results from the ProtICNN-BiLSTM model improve protein sequence categorization. This powerful tool could improve medical and biological research. The breakthrough protein sequence classification model is ProtICNN-BiLSTM. Bayesian optimization, ICNN, and BiLSTM analyze biological data accurately.

Deep-STP: a deep learning-based approach to predict snake toxin proteins by using word embeddings

Snake venom contains many toxic proteins that can destroy the circulatory system or nervous system of prey. Studies have found that these snake venom proteins have the potential to treat cardiovascular and nervous system diseases. Therefore, the study of snake venom protein is conducive to the development of related drugs. The research technologies based on traditional biochemistry can accurately identify these proteins, but the experimental cost is high and the time is long. Artificial intelligence technology provides a new means and strategy for large-scale screening of snake venom proteins from the perspective of computing. In this paper, we developed a sequence-based computational method to recognize snake toxin proteins. Specially, we utilized three different feature descriptors, namely g-gap, natural vector and word 2 vector, to encode snake toxin protein sequences. The analysis of variance (ANOVA), gradient-boost decision tree algorithm (GBDT) combined with incremental feature selection (IFS) were used to optimize the features, and then the optimized features were input into the deep learning model for model training. The results show that our model can achieve a prediction performance with an accuracy of 82.00% in 10-fold cross-validation. The model is further verified on independent data, and the accuracy rate reaches to 81.14%, which demonstrated that our model has excellent prediction performance and robustness.

Construction of transcription factor mutagenesis population in tomato using a pooled CRISPR/Cas9 plasmid library

Adequate mutant materials are the prerequisite for conducting gene function research or screening novel functional genes in plants. The strategy of constructing a large-scale mutant population using the pooled CRISPR/Cas9-sgRNA library has been implemented in several crops. However, the effective application of this CRISPR/Cas9 large-scale screening strategy to tomato remains to be attempted. Here, we identified 990 transcription factors in the tomato genome, designed and synthesized a CRISPR/Cas9 plasmid library containing 4379 sgRNAs. Using this pooled library, 487 T0 positive plants were obtained, among which 92 plants harbored a single sgRNA sequence, targeting 65 different transcription factors, with a mutation rate of 23%. In the T0 mutant population, the occurrence of homozygous and biallelic mutations was observed at higher frequencies. Additionally, the utilization of a small-scale CRISPR/Cas9 library targeting 30 transcription factors could enhance the efficacy of single sgRNA recognition in positive plants, increasing it from 19% to 42%. Phenotypic characterization of several mutants identified from the mutant population demonstrated the utility of our CRISPR/Cas9 mutant library. Taken together, our study offers insights into the implementation and optimization of CRISPR/Cas9-mediated large-scale knockout library in tomato.

Benchmarking deep learning methods for predicting CRISPR/Cas9 sgRNA on- and off-target activities

In silico design of single guide RNA (sgRNA) plays a critical role in clustered regularly interspaced, short palindromic repeats/CRISPR-associated protein 9 (CRISPR/Cas9) system. Continuous efforts are aimed at improving sgRNA design with efficient on-target activity and reduced off-target mutations. In the last 5 years, an increasing number of deep learning-based methods have achieved breakthrough performance in predicting sgRNA on- and off-target activities. Nevertheless, it is worthwhile to systematically evaluate these methods for their predictive abilities. In this review, we conducted a systematic survey on the progress in prediction of on- and off-target editing. We investigated the performances of 10 mainstream deep learning-based on-target predictors using nine public datasets with different sample sizes. We found that in most scenarios, these methods showed superior predictive power on large- and medium-scale datasets than on small-scale datasets. In addition, we performed unbiased experiments to provide in-depth comparison of eight representative approaches for off-target prediction on 12 publicly available datasets with various imbalanced ratios of positive/negative samples. Most methods showed excellent performance on balanced datasets but have much room for improvement on moderate- and severe-imbalanced datasets. This study provides comprehensive perspectives on CRISPR/Cas9 sgRNA on- and off-target activity prediction and improvement for method development.

Deep learning in CRISPR-Cas systems: a review of recent studies

In genetic engineering, the revolutionary CRISPR-Cas system has proven to be a vital tool for precise genome editing. Simultaneously, the emergence and rapid evolution of deep learning methodologies has provided an impetus to the scientific exploration of genomic data. These concurrent advancements mandate regular investigation of the state-of-the-art, particularly given the pace of recent developments. This review focuses on the significant progress achieved during 2019-2023 in the utilization of deep learning for predicting guide RNA (gRNA) activity in the CRISPR-Cas system, a key element determining the effectiveness and specificity of genome editing procedures. In this paper, an analytical overview of contemporary research is provided, with emphasis placed on the amalgamation of artificial intelligence and genetic engineering. The importance of our review is underscored by the necessity to comprehend the rapidly evolving deep learning methodologies and their potential impact on the effectiveness of the CRISPR-Cas system. By analyzing recent literature, this review highlights the achievements and emerging trends in the integration of deep learning with the CRISPR-Cas systems, thus contributing to the future direction of this essential interdisciplinary research area.

CRISPR-mediated technology for seed oil improvement in rapeseed: Challenges and future perspectives

Rapeseed not only provide considerable amount of edible oil with high nutritional properties but can also be used as a raw material for biofuel production in many industries. It is therefore in high demand to bring genetic changes in order to fulfill the need of human and of industries. Though traditional breeding techniques such as hybridization and mutagenesis remained the top methods for long time to create improved varieties in oilseed rape. Clustered regularly interspaced short palindromic repeats (CRISPR) is becoming one of the most valuable gene editing technologies that allow precise genome engineering, and open new ways for research in plant functional genomics. Though CRISPR has been used in many other crops for genetic improvement it is expected to be an effective tool for genome editing and molecular design in oilseed rape for seed oil improvement. This mini review will discuss and summarize the past and ongoing research and development in rapeseed in terms of seed oil improvement and fatty acid composition using CRISPR technology. In addition, the factors that hinder the efficiency of this tool and how to eliminate those factors will be briefly summarized. The improvement of CRISPR technology for getting better results in oilseed rape will also be considered here. This minireview will open new windows for researchers in Brassica napus oil improvement research and genetic improvement using CRISPR technology.

Empirical comparison and recent advances of computational prediction of hormone binding proteins using machine learning methods

Hormone binding proteins (HBPs) belong to the group of soluble carrier proteins. These proteins selectively and non-covalently interact with hormones and promote growth hormone signaling in human and other animals. The HBPs are useful in many medical and commercial fields. Thus, the identification of HBPs is very important because it can help to discover more details about hormone binding proteins. Meanwhile, the experimental methods are time-consuming and expensive for hormone binding proteins recognition. Computational prediction methods have played significant roles in the correct recognition of hormone binding proteins with the use of sequence information and ML algorithms. In this review, we compared and assessed the implementation of ML-based tools in recognition of HBPs in a unique way. We hope that this study will give enough awareness and knowledge for research on HBPs.

sgRNA-2wPSM: Identify sgRNAs on-target activity by combining two-window-based position specific mismatch and synthetic minority oversampling technique

MOTIVATION

sgRNAs on-target activity prediction is a critical step in the CRISPR-Cas9 system. Due to its importance to RNA function research and genome editing application, some computational methods were introduced, treating it as a binary classification task or a regression task. Among these methods, sgRNA-PSM is a state-of-the-art method. In this work, we improved this method by proposing a new feature extraction method called two-window-based PSM, which divides the DNA sequences into two non-overlapping segments so as to extract different patterns in the two different segments. The two-window-based PSM were fed into Support Vector Machines (SVMs), and a new method called sgRNA-2wPSM was proposed. Furthermore, a new oversampling method called SCORE-SVM-SMOTE was proposed to solve the imbalanced training set problem based on the SVM-SMOTE algorithm. Results on the benchmark datasets indicated that sgRNA-2wPSM is superior to other methods.

An efficient deep learning based predictor for identifying miRNA-triggered phasiRNA loci in plant

Phasic small interfering RNAs are plant secondary small interference RNAs that typically generated by the convergence of miRNAs and polyadenylated mRNAs. A growing number of studies have shown that miRNA-initiated phasiRNA plays crucial roles in regulating plant growth and stress responses. Experimental verification of miRNA-initiated phasiRNA loci may take considerable time, energy and labor. Therefore, computational methods capable of processing high throughput data have been proposed one by one. In this work, we proposed a predictor (DIGITAL) for identifying miRNA-initiated phasiRNAs in plant, which combined a multi-scale residual network with a bi-directional long-short term memory network. The negative dataset was constructed based on positive data, through replacing 60% of nucleotides randomly in each positive sample. Our predictor achieved the accuracy of 98.48% and 94.02% respectively on two independent test datasets with different sequence length. These independent testing results indicate the effectiveness of our model. Furthermore, DIGITAL is of robustness and generalization ability, and thus can be easily extended and applied for miRNA target recognition of other species. We provide the source code of DIGITAL, which is freely available at https://github.com/yuanyuanbu/DIGITAL.

Machine learning in the estimation of CRISPR-Cas9 cleavage sites for plant system

CRISPR-Cas9 system is one of the recent most used genome editing techniques. Despite having a high capacity to alter the precise target genes and genomic regions that the planned guide RNA (or sgRNA) complements, the off-target effect still exists. But there are already machine learning algorithms for people, animals, and a few plant species. In this paper, an effort has been made to create models based on three machine learning-based techniques [namely, artificial neural networks (ANN), support vector machines (SVM), and random forests (RF)] for the prediction of the CRISPR-Cas9 cleavage sites that will be cleaved by a particular sgRNA. The plant dataset was the sole source of inspiration for all of these machine learning-based algorithms. 70% of the on-target and off-target dataset of various plant species that was gathered was used to train the models. The remaining 30% of the data set was used to evaluate the model's performance using a variety of evaluation metrics, including specificity, sensitivity, accuracy, precision, F1 score, F2 score, and AUC. Based on the aforementioned machine learning techniques, eleven models in all were developed. Comparative analysis of these produced models suggests that the model based on the random forest technique performs better. The accuracy of the Random Forest model is 96.27%, while the AUC value was found to be 99.21%. The SVM-Linear, SVM-Polynomial, SVM-Gaussian, and SVM-Sigmoid models were trained, making a total of six ANN-based models (ANN1-Logistic, ANN1-Tanh, ANN1-ReLU, ANN2-Logistic, ANN2-Tanh, and ANN-ReLU) and Support Vector Machine models (SVM-Linear, SVM-Polynomial, SVM-Gaussian However, the overall performance of Random Forest is better among all other ML techniques. ANN1-ReLU and SVM-Linear model performance were shown to be better among Artificial Neural Network and Support Vector Machine-based models, respectively.

ACP_MS: prediction of anticancer peptides based on feature extraction

Anticancer peptides (ACPs) are bioactive peptides with antitumor activity and have become the most promising drugs in the treatment of cancer. Therefore, the accurate prediction of ACPs is of great significance to the research of cancer diseases. In the paper, we developed a more efficient prediction model called ACP_MS. Firstly, the monoMonoKGap method is used to extract the characteristic of anticancer peptide sequences and form the digital features. Then, the AdaBoost model is used to select the most discriminating features from the digital features. Finally, a stochastic gradient descent algorithm is introduced to identify anticancer peptide sequences. We adopt 7-fold cross-validation and independent test set validation, and the final accuracy of the main dataset reached 92.653% and 91.597%, respectively. The accuracy of the alternate dataset reached 98.678% and 98.317%, respectively. Compared with other advanced prediction models, the ACP_MS model improves the identification ability of anticancer peptide sequences. The data of this model can be downloaded from the public website for free https://github.com/Zhoucaimao1998/Zc.

Predicting colorectal cancer tumor mutational burden from histopathological images and clinical information using multi-modal deep learning

MOTIVATION

Tumor mutational burden (TMB) is an indicator of the efficacy and prognosis of immune checkpoint therapy in colorectal cancer (CRC). In general, patients with higher TMB values are more likely to benefit from immunotherapy. Though whole-exome sequencing is considered the gold standard for determining TMB, it is difficult to be applied in clinical practice due to its high cost. There are also a few DNA panel-based methods to estimate TMB; however, their detection cost is also high, and the associated wet-lab experiments usually take days, which emphasize the need for faster and cheaper alternatives.

RESULTS

In this study, we propose a multi-modal deep learning model based on a residual network (ResNet) and multi-modal compact bilinear pooling to predict TMB status (i.e. TMB high (TMB_H) or TMB low(TMB_L)) directly from histopathological images and clinical data. We applied the model to CRC data from The Cancer Genome Atlas and compared it with four other popular methods, namely, ResNet18, ResNet50, VGG19 and AlexNet. We tested different TMB thresholds, namely, percentiles of 10%, 14.3%, 15%, 16.3%, 20%, 30% and 50%, to differentiate TMB_H and TMB_L.For the percentile of 14.3% (i.e. TMB value 20) and ResNet18, our model achieved an area under the receiver operating characteristic curve of 0.817 after 5-fold cross-validation, which was better than that of other compared models. In addition, we also found that TMB values were significantly associated with the tumor stage and N and M stages. Our study shows that deep learning models can predict TMB status from histopathological images and clinical information only, which is worth clinical application.

CRISPR for accelerating genetic gains in under-utilized crops of the drylands: Progress and prospects

Technologies and innovations are critical for addressing the future food system needs where genetic resources are an essential component of the change process. Advanced breeding tools like "genome editing" are vital for modernizing crop breeding to provide game-changing solutions to some of the "must needed" traits in agriculture. CRISPR/Cas-based tools have been rapidly repurposed for editing applications based on their improved efficiency, specificity and reduced off-target effects. Additionally, precise gene-editing tools such as base editing, prime editing, and multiplexing provide precision in stacking of multiple traits in an elite variety, and facilitating specific and targeted crop improvement. This has helped in advancing research and delivery of products in a short time span, thereby enhancing the rate of genetic gains. A special focus has been on food security in the drylands through crops including millets, teff, fonio, quinoa, Bambara groundnut, pigeonpea and cassava. While these crops contribute significantly to the agricultural economy and resilience of the dryland, improvement of several traits including increased stress tolerance, nutritional value, and yields are urgently required. Although CRISPR has potential to deliver disruptive innovations, prioritization of traits should consider breeding product profiles and market segments for designing and accelerating delivery of locally adapted and preferred crop varieties for the drylands. In this context, the scope of regulatory environment has been stated, implying the dire impacts of unreasonable scrutiny of genome-edited plants on the evolution and progress of much-needed technological advances.

ConSIG: consistent discovery of molecular signature from OMIC data

The discovery of proper molecular signature from OMIC data is indispensable for determining biological state, physiological condition, disease etiology, and therapeutic response. However, the identified signature is reported to be highly inconsistent, and there is little overlap among the signatures identified from different biological datasets. Such inconsistency raises doubts about the reliability of reported signatures and significantly hampers its biological and clinical applications. Herein, an online tool, ConSIG, was constructed to realize consistent discovery of gene/protein signature from any uploaded transcriptomic/proteomic data. This tool is unique in a) integrating a novel strategy capable of significantly enhancing the consistency of signature discovery, b) determining the optimal signature by collective assessment, and c) confirming the biological relevance by enriching the disease/gene ontology. With the increasingly accumulated concerns about signature consistency and biological relevance, this online tool is expected to be used as an essential complement to other existing tools for OMIC-based signature discovery. ConSIG is freely accessible to all users without login requirement at https://idrblab.org/consig/.

FDCNet: Presentation of the Fuzzy CNN and Fractal Feature Extraction for Detection and Classification of Tumors

The detection of brain tumors using magnetic resonance imaging is currently one of the biggest challenges in artificial intelligence and medical engineering. It is important to identify these brain tumors as early as possible, as they can grow to death. Brain tumors can be classified as benign or malignant. Creating an intelligent medical diagnosis system for the diagnosis of brain tumors from MRI imaging is an integral part of medical engineering as it helps doctors detect brain tumors early and oversee treatment throughout recovery. In this study, a comprehensive approach to diagnosing benign and malignant brain tumors is proposed. The proposed method consists of four parts: image enhancement to reduce noise and unify image size, contrast, and brightness, image segmentation based on morphological operators, feature extraction operations including size reduction and selection of features based on the fractal model, and eventually, feature improvement according to segmentation and selection of optimal class with a fuzzy deep convolutional neural network. The BraTS data set is used as magnetic resonance imaging data in experimental results. A series of evaluation criteria is also compared with previous methods, where the accuracy of the proposed method is 98.68%, which has significant results.

Actin gamma 1 is a critical regulator of pancreatic ductal adenocarcinoma

Background

Pancreatic ductal adenocarcinoma (PDAC) accounts for about 90% of pancreatic cancers, which represents one of the most lethal malignancies with a 5-year overall survival less than 10%. Identifying molecular biomarkers is invaluable in helping to predict clinical outcomes and developing targeted chemotherapies. Actin gamma 1 (ACTG1) is a kind of actin isoform that exists in almost all cell types as a component of the cytoskeleton, thus mediating cell viability. Although there have been studies revealing the prognostic significance of ACTG1 in several malignancies such as glioblastoma and hepatocellular carcinoma, its involvement and function in pancreatic cancer needs to be elucidated.

Methods

We retrospectively enrolled a cohort of PDAC patients after surgical resection (n = 149) and conducted immunohistochemistry experiments to explore the expression profile of ACTG1. Univariate and multivariate analyses were performed to investigate the clinical relevance of ACTG1. The functional role of ACTG1 in PDAC progression was further validated via both in vitro and in vivo studies.

Results

ACTG1 presented a higher expression in PDAC tissues than in nontumorous pancreatic tissues. ACTG1 level positively correlated with tumor stage, implying its potential role as a tumor promoter. Univariate and multivariate analyses identified that patients with lower ACTG1 showed a better overall survival compared to those with higher ACTG1 expression. Cellular and xenograft experiments confirmed the role of ACTG1 on facilitating tumor proliferation both in vitro and in vivo.

Conclusions

Our study revealed a pro-oncogenic role of ACTG1 in PDAC, which may help predict prognosis and serve as a novel therapeutic target.

GMNN2CD: identification of circRNA-disease associations based on variational inference and graph Markov neural networks

MOTIVATION

With the analysis of the characteristic and function of circular RNAs (circRNAs), people have realized that they play a critical role in the diseases. Exploring the relationship between circRNAs and diseases is of far-reaching significance for searching the etiopathogenesis and treatment of diseases. Nevertheless, it is inefficient to learn new associations only through biotechnology.

RESULTS

Consequently, we present a computational method, GMNN2CD, which employs a graph Markov neural network (GMNN) algorithm to predict unknown circRNA-disease associations. First, used verified associations, we calculate semantic similarity and Gaussian interactive profile kernel similarity (GIPs) of the disease and the GIPs of circRNA and then merge them to form a unified descriptor. After that, GMNN2CD uses a fusion feature variational map autoencoder to learn deep features and uses a label propagation map autoencoder to propagate tags based on known associations. Based on variational inference, GMNN alternate training enhances the ability of GMNN2CD to obtain high-efficiency high-dimensional features from low-dimensional representations. Finally, 5-fold cross-validation of five benchmark datasets shows that GMNN2CD is superior to the state-of-the-art methods. Furthermore, case studies have shown that GMNN2CD can detect potential associations.

AVAILABILITY AND IMPLEMENTATION

The source code and data are available at https://github.com/nmt315320/GMNN2CD.git.

Electronic and structural computing features of some chromene derivatives and evaluating their anticancer activities

Electronic and structural features of some of representative chromene derivatives were investigated in this work towards recognizing their anticancer roles. Density functional theory (DFT) calculations were performed to obtain five structures of chromene derivatives with the same skeleton of original structure. In addition to obtaining optimized structural geometries, electronic molecular orbital features were evaluated for the models. Energy levels of the highest occupied molecular orbital (HOMO) and the lowest unoccupied molecular orbital (LUMO) indicated effects of additional R group pf chromene derivatives on electronic features. Based on such results, it was predicted that one of derivatives, L5, could better participate in interactions with other substances in comparison with other ligand structures. This achievement was obtained based on availability of HOMO and LUMO levels in lower energies easily catchable for electron transferring. On the other hand, L5 was assumed to interact in the weakest mode with other substances. Indeed, the main goal of this work was to examine anticancer activity of the investigated chromene derivatives, in which each of L1–L5 chromene derivatives were analyzed first to recognized electronic and structural features. Next, molecular docking (MD) simulations were performed to examine anticancer role of L1–L5 against methyltransferase cancerous enzyme target. The results indicated that formations of ligand-target complexes could be occurred within different types of interactions and surrounding amino acids of central ligand. In agreement with the achievements of analyses of single-standing L1–L5 compounds, L4-Target was seen as the strongest complex among possible complex formations. Moreover, values of binding energies and inhibition constant indicated that all five chromene derivatives could work as inhibitors of methyltransferase cancerous enzyme by the most advantage for L4 ligand. And as a final remark, details of such anticancer activity were recognized by graphical representations of ligand-target complexes showing types of interactions and involving amino acids in interactions.

PFmulDL: a novel strategy enabling multi-class and multi-label protein function annotation by integrating diverse deep learning methods

Bioinformatic annotation of protein function is essential but extremely sophisticated, which asks for extensive efforts to develop effective prediction method. However, the existing methods tend to amplify the representativeness of the families with large number of proteins by misclassifying the proteins in the families with small number of proteins. That is to say, the ability of the existing methods to annotate proteins in the 'rare classes' remains limited. Herein, a new protein function annotation strategy, PFmulDL, integrating multiple deep learning methods, was thus constructed. First, the recurrent neural network was integrated, for the first time, with the convolutional neural network to facilitate the function annotation. Second, a transfer learning method was introduced to the model construction for further improving the prediction performances. Third, based on the latest data of Gene Ontology, the newly constructed model could annotate the largest number of protein families comparing with the existing methods. Finally, this newly constructed model was found capable of significantly elevating the prediction performance for the 'rare classes' without sacrificing that for the 'major classes'. All in all, due to the emerging requirements on improving the prediction performance for the proteins in 'rare classes', this new strategy would become an essential complement to the existing methods for protein function prediction. All the models and source codes are freely available and open to all users at: https://github.com/idrblab/PFmulDL.

Underlying Causes and Co-existence of Malnutrition and Infections: An Exceedingly Common Death Risk in Cancer

In nutrition science, malnutrition is a state of imbalance between intake and the needs of the organism, leading to metabolic changes, impaired physiological functions, and weight loss. Regardless of the countless efforts being taken and researched for years, the burden of malnutrition is still alarming and considered a significant agent of mortality across the globe. Around 45% of 12 million children deaths (0–5 years old) annually are due to malnutrition, mostly from developing countries. Malnutrition develops associations with other infections and leads to substantial clinical outcomes, such as mortality, more visits to hospitals, poor quality of life and physical frailty, and socioeconomic issues. Here, in this review, we intend to provide an overview of the current burden, underlying risk factors, and co-existence of malnutrition and other infections, such as cancer. Following the rising concern of the vicious interplay of malnutrition and other medical illnesses, we believed that this narrative review would highlight the need to re-make and re-define the future strategies by giving comprehensive and sustainable programs to alleviate poverty and combat the rampant infectious diseases and those nutrition-related health problems. Furthermore, the study also raises the concern for hospitalized malnourished cancer patients as it is crucially important to knowledge the caregiver healthcare staff for early interventions of providing nutritional support to delay or prevent the onset of malnutrition.

Loss of ATP5A1 enhances proliferation and predicts poor prognosis of colon adenocarcinoma

BACKGROUND

ATP Synthase F1 Subunit Alpha (ATP5F1A), also named as ATP5A1, is a subunit of mitochondrial ATP synthase. Dysregulated expression of ATP5A1 has been reported in several malignancies, nevertheless it showed either oncogenic or tumor-suppressing roles in different cancer types. Here we aimed to initially investigate the expression and role of ATP5A1 in colon adenocarcinoma.

METHODS

We firstly evaluated the transcription and mRNA levels of ATP5A1 using data from The Cancer Genome Atlas (TCGA). Besides, we tested its mRNA and protein expression in our enrolled retrospective cohort (n = 115). Univariate and multivariate analyzes were conducted to assess its prognostic value. Cellular experiments and xenografts in mice model were performed to validate the role of ATP5A1 in colon cancer.

RESULTS

ATP5A1 showed a significant lower level in colon adenocarcinoma than in adjacent nontumorous tissue. Advanced tumor stage was characterized with lower ATP5A1 level. Lower ATP5A1 was associated with poor prognosis in both TCGA dataset (P = 0.041) and our cohort (P = 0.001). Furthermore, Cox regression analysis demonstrated that ATP5A1 was a novel independent prognostic factor for colon cancer patients (HR=0.43, P = 0.018). Finally, cellular and xenografts data confirmed that overexpressing ATP5A1 can remarkably attenuate colon cancer growth.

CONCLUSION

Low expression of ATP5A1 may be a potential molecular marker for poor prognosis in colon cancer.

DATA AVAILABILITY

Data will be available upon request.

Zinc Finger Protein 24 is a Prognostic Factor in Ovarian Serous Carcinoma

OBJECTIVE

As a member of the zinc finger protein family, zinc finger protein 24 (ZNF24) contains a Cys2His2 zinc finger domain and acts as a transcription factor. ZNF24 has been reported to be downregulated in gastric cancer and breast cancer. However, little is known about its expression and function in ovarian serous carcinoma (OSC).

PATIENTS AND METHODS

We collected 117 OSC patients during 2011 to 2017 and retrospectively retrieved their clinicopathologic characteristics as well as their survival data. Protein level was analyzed by immunohistochemistry, mRNA level was evaluated by RT-qPCR assay, and transcriptional data was obtained from TCGA data sets. The correlations between ZNF24 expression and patients' features were assessed using χ2 test. Univariate and multivariate analyses were used to identify the prognosis predicative potential of ZNF24 in OSC. The function of ZNF24 in the epithelial ovarian cancer cells was also verified by in vitro cellular experiments.

RESULTS

Among the 117 cases, ZNF24 was downregulated in 52 OSC samples (44.6%) and significantly correlated with tumor stages. According to univariate and multivariate analyses, ZNF24 can act as an independent prognostic indicator for the overall survival of OSC patients, whose lower expression was associated with poorer clinical outcomes. Ectopic overexpression and knockdown assays indicated that ZNF24 can negatively regulate the OSC cell viability.

CONCLUSIONS

OSC patients with low level of ZNF24 have worse overall survival compared with those possess high-ZNF24 expression. Downregulated ZNF24 may be involved in the proliferation of OSC, and ZNF24 expression can serve as an independent survival predictor.

Deep-4mCGP: A Deep Learning Approach to Predict 4mC Sites in Geobacter pickeringii by Using Correlation-Based Feature Selection Technique

4mC is a type of DNA alteration that has the ability to synchronize multiple biological movements, for example, DNA replication, gene expressions, and transcriptional regulations. Accurate prediction of 4mC sites can provide exact information to their hereditary functions. The purpose of this study was to establish a robust deep learning model to recognize 4mC sites in Geobacter pickeringii. In the anticipated model, two kinds of feature descriptors, namely, binary and k-mer composition were used to encode the DNA sequences of Geobacter pickeringii. The obtained features from their fusion were optimized by using correlation and gradient-boosting decision tree (GBDT)-based algorithm with incremental feature selection (IFS) method. Then, these optimized features were inserted into 1D convolutional neural network (CNN) to classify 4mC sites from non-4mC sites in Geobacter pickeringii. The performance of the anticipated model on independent data exhibited an accuracy of 0.868, which was 4.2% higher than the existing model.

A systematic mapping study on machine learning techniques for the prediction of CRISPR/Cas9 sgRNA target cleavage

CRISPR/Cas9 technology has greatly accelerated genome engineering research. The CRISPR/Cas9 complex, a bacterial immune response system, is widely adopted for RNA-driven targeted genome editing. The systematic mapping study presented in this paper examines the literature on machine learning (ML) techniques employed in the prediction of CRISPR/Cas9 sgRNA on/off-target cleavage, focusing on improving support in sgRNA design activities and identifying areas currently being researched.

This area of research has greatly expanded recently, and we found it appropriate to work on a Systematic Mapping Study (SMS), an investigation that has proven to be an effective secondary study method. Unlike a classic review, in an SMS, no comparison of methods or results is made, while this task can instead be the subject of a systematic literature review that chooses one theme among those highlighted in this SMS. The study is illustrated in this paper. To the best of the authors' knowledge, no other SMS studies have been published on this topic.

Fifty-seven papers published in the period 2017–2022 (April, 30) were analyzed. This study reveals that the most widely used ML model is the convolutional neural network (CNN), followed by the feedforward neural network (FNN), while the use of other models is marginal. Other interesting information has emerged, such as the wide availability of both open code and platforms dedicated to supporting the activity of researchers or the fact that there is a clear prevalence of public funds that finance research on this topic.

CRBPDL: Identification of circRNA-RBP interaction sites using an ensemble neural network approach

Circular RNAs (circRNAs) are non-coding RNAs with a special circular structure produced formed by the reverse splicing mechanism. Increasing evidence shows that circular RNAs can directly bind to RNA-binding proteins (RBP) and play an important role in a variety of biological activities. The interactions between circRNAs and RBPs are key to comprehending the mechanism of posttranscriptional regulation. Accurately identifying binding sites is very useful for analyzing interactions. In past research, some predictors on the basis of machine learning (ML) have been presented, but prediction accuracy still needs to be ameliorated. Therefore, we present a novel calculation model, CRBPDL, which uses an Adaboost integrated deep hierarchical network to identify the binding sites of circular RNA-RBP. CRBPDL combines five different feature encoding schemes to encode the original RNA sequence, uses deep multiscale residual networks (MSRN) and bidirectional gating recurrent units (BiGRUs) to effectively learn high-level feature representations, it is sufficient to extract local and global context information at the same time. Additionally, a self-attention mechanism is employed to train the robustness of the CRBPDL. Ultimately, the Adaboost algorithm is applied to integrate deep learning (DL) model to improve prediction performance and reliability of the model. To verify the usefulness of CRBPDL, we compared the efficiency with state-of-the-art methods on 37 circular RNA data sets and 31 linear RNA data sets. Moreover, results display that CRBPDL is capable of performing universal, reliable, and robust. The code and data sets are obtainable at https://github.com/nmt315320/CRBPDL.git.

More and more evidences show that circular RNA can directly bind to proteins and participate in countless different biological processes. The calculation method can quickly and accurately predict the binding site of circular RNA and RBP. In order to identify the interaction of circRNA with 37 different types of circRNA binding proteins, we developed an integrated deep learning network based on hierarchical network, called CRBPDL. It can effectively learn high-level feature representations. The performance of the model was verified through comparative experiments of different feature extraction algorithms, different deep learning models and classifier models. Moreover, the CRBPDL model was applied to 31 linear RNAs, and the effectiveness of our method was proved by comparison with the results of current excellent algorithms. It is expected that the CRBPDL model can effectively predict the binding site of circular RNA-RBP and provide reliable candidates for further biological experiments.

iAIPs: Identifying Anti-Inflammatory Peptides Using Random Forest

Recently, several anti-inflammatory peptides (AIPs) have been found in the process of the inflammatory response, and these peptides have been used to treat some inflammatory and autoimmune diseases. Therefore, identifying AIPs accurately from a given amino acid sequences is critical for the discovery of novel and efficient anti-inflammatory peptide-based therapeutics and the acceleration of their application in therapy. In this paper, a random forest-based model called iAIPs for identifying AIPs is proposed. First, the original samples were encoded with three feature extraction methods, including g-gap dipeptide composition (GDC), dipeptide deviation from the expected mean (DDE), and amino acid composition (AAC). Second, the optimal feature subset is generated by a two-step feature selection method, in which the feature is ranked by the analysis of variance (ANOVA) method, and the optimal feature subset is generated by the incremental feature selection strategy. Finally, the optimal feature subset is inputted into the random forest classifier, and the identification model is constructed. Experiment results showed that iAIPs achieved an AUC value of 0.822 on an independent test dataset, which indicated that our proposed model has better performance than the existing methods. Furthermore, the extraction of features for peptide sequences provides the basis for evolutionary analysis. The study of peptide identification is helpful to understand the diversity of species and analyze the evolutionary history of species.

DrugHybrid_BS: Using Hybrid Feature Combined With Bagging-SVM to Predict Potentially Druggable Proteins

Drug targets are biological macromolecules or biomolecule structures capable of specifically binding a therapeutic effect with a particular drug or regulating physiological functions. Due to the important value and role of drug targets in recent years, the prediction of potential drug targets has become a research hotspot. The key to the research and development of modern new drugs is first to identify potential drug targets. In this paper, a new predictor, DrugHybrid_BS, is developed based on hybrid features and Bagging-SVM to identify potentially druggable proteins. This method combines the three features of monoDiKGap (k = 2), cross-covariance, and grouped amino acid composition. It removes redundant features and analyses key features through MRMD and MRMD2.0. The cross-validation results show that 96.9944% of the potentially druggable proteins can be accurately identified, and the accuracy of the independent test set has reached 96.5665%. This all means that DrugHybrid_BS has the potential to become a useful predictive tool for druggable proteins. In addition, the hybrid key features can identify 80.0343% of the potentially druggable proteins combined with Bagging-SVM, which indicates the significance of this part of the features for research.

In vitro and in vivo anticancer effect of pH-responsive paclitaxel-loaded niosomes

In this study, paclitaxel (PTX)-loaded pH-responsive niosomes modified with ergosterol were developed. This new formulation was characterized in terms of size, morphology, encapsulation efficiency (EE), and in vitro release at pH 5.2 and 7.4. The in vitro efficacy of free PTX and niosome/PTX was assessed using MCF7, Hela, and HUVEC cell lines. In order to evaluate the in vivo efficacy of niosomal PTX in rats as compared to free PTX, the animals were intraperitoneally administered with 2.5 mg/kg and 5 mg/kg niosomal PTX for two weeks. Results showed that the pH-responsive niosomes had a nanometric size, spherical morphology, 77% EE, and pH-responsive release in pH 5.2 and 7.4. Compared with free PTX, we found markedly lower IC50s when cancer cells were treated for 48 h with niosomal PTX, which also showed high efficacy against human cancers derived from cervix and breast tumors. Moreover, niosomal PTX induced evident morphological changes in these cell lines. In vivo administration of free PTX at the dose of 2.5 mg/kg significantly increased serum biochemical parameters and liver lipid peroxidation in rats compared to the control rats. The situation was different when niosomal PTX was administered to the rats: the 5 mg/kg dosage of niosomal PTX significantly increased serum biochemical parameters, but the group treated with the 2.5 mg/kg dose of niosomal PTX showed fewer toxic effects than the group treated with free PTX at the same dosage. Overall, our results provide proof of concept for encapsulating PTX in niosomal formulation to enhance its therapeutic efficacy.

Taguchi-Assisted Optimization Technique and Density Functional Theory for Green Synthesis of a Novel Cu-MOF Derived From Caffeic Acid and Its Anticancerious Activities

In this paper, we have reported an innovative greener method for developing copper-metal organic frameworks (Cu-MOFs) using caffeic acid (CA) as a linker extracted from Satureja hortensis using ultrasonic bath. The density functional theory is used to discuss the Cu-MOF-binding reaction mechanism. In order to achieve a discrepancy between the energy levels of the interactive precursor orbitals, the molecules have been optimized using the B3LYP/6-31G method. The Taguchi method was used to optimize the key parameters for the synthesis of Cu-MOF. FT-IR, XRD, nitrogen adsorption, and SEM analyses are used to characterize it. The adsorption/desorption and SEM analyses suggested that Cu-MOF has a larger surface area of 284.94 m2/g with high porosity. Cu-MOF has shown anticancer activities against the human breast cancer (MDA-MB-468) cell lines, and it could be a potent candidate for clinical applications.

Iron Chelation by thiocytosine: Investigating electronic and structural features for describing tautomerism and metal chelation processes

This work was performed regarding the importance of iron (Fe) chelation for biological systems. This goal was investigated by assistance of a model of thiocytosine (TC) for participating in Fe-chelation processes. First, formations of tautomeric conformations were investigated to explore existence of possible structures of TC. Next, Fe-chelation processes were examined for all four obtained tautomers of TC. The results indicated that thiol tautomers could be seen at higher stability than thio tautomers, in which one of such thiol tautomers yielded the strongest Fe-chelation process to build FeTC3 model. As a consequence, parallel to the results of original TC tautomers, Fe-chelated models were found to be achievable for meaningful chelation processes or sensing the existence of Fe in media. Examining molecular orbital features could help for sensing purposes. The results of this work were obtained by performing density functional theory (DFT) calculations proposing TC compounds suitable for Fe-chelation purposes.

ReRF-Pred: predicting amyloidogenic regions of proteins based on their pseudo amino acid composition and tripeptide composition

BACKGROUND

Amyloids are insoluble fibrillar aggregates that are highly associated with complex human diseases, such as Alzheimer's disease, Parkinson's disease, and type II diabetes. Recently, many studies reported that some specific regions of amino acid sequences may be responsible for the amyloidosis of proteins. It has become very important for elucidating the mechanism of amyloids that identifying the amyloidogenic regions. Accordingly, several computational methods have been put forward to discover amyloidogenic regions. The majority of these methods predicted amyloidogenic regions based on the physicochemical properties of amino acids. In fact, position, order, and correlation of amino acids may also influence the amyloidosis of proteins, which should be also considered in detecting amyloidogenic regions.

RESULTS

To address this problem, we proposed a novel machine-learning approach for predicting amyloidogenic regions, called ReRF-Pred. Firstly, the pseudo amino acid composition (PseAAC) was exploited to characterize physicochemical properties and correlation of amino acids. Secondly, tripeptides composition (TPC) was employed to represent the order and position of amino acids. To improve the distinguishability of TPC, all possible tripeptides were analyzed by the binomial distribution method, and only those which have significantly different distribution between positive and negative samples remained. Finally, all samples were characterized by PseAAC and TPC of their amino acid sequence, and a random forest-based amyloidogenic regions predictor was trained on these samples. It was proved by validation experiments that the feature set consisted of PseAAC and TPC is the most distinguishable one for detecting amyloidosis. Meanwhile, random forest is superior to other concerned classifiers on almost all metrics. To validate the effectiveness of our model, ReRF-Pred is compared with a series of gold-standard methods on two datasets: Pep-251 and Reg33. The results suggested our method has the best overall performance and makes significant improvements in discovering amyloidogenic regions.

CONCLUSIONS

The advantages of our method are mainly attributed to that PseAAC and TPC can describe the differences between amyloids and other proteins successfully. The ReRF-Pred server can be accessed at http://106.12.83.135:8080/ReRF-Pred/.

Substitution effects via aromaticity, polarizability, APT, AIM, IR analysis, and hydrogen adsorption in C20-nTin nanostructures: a DFT survey

In this paper, the substitution effects of titanium heteroatom(s) on aromaticity, the average isotropic polarizability (< α >), the atomic polar tensor (APT) charge, the electrostatic potential (ESP) map, and the atoms in molecule (AIM) analysis along with infrared (IR) spectroscopy of C₂₀ fullerene and its C_20-nTi_n derivatives (n = 1-5) are probed via density functional theory (DFT). The nucleus-independent chemical shifts (NICS) specify that substitution effect causes more aromaticity character of the optimized heterofullerenes than benzene molecule and higher APT charge distribution upon surfaces of them than pure cage. The highest negative and positive APT charge distribution on carbons of C₁₅Ti₅ and titanium substitutions of C₁₆Ti_4-2 implies that these sites can be attacked more readily by electrophilic and nucleophilic regents, respectively. We are very pleased to state that isolating the Ti-Ti single bonds by intermediacy of one or two C atoms is an applicable strategy for attaining the highest APT charge distribution on Ti atoms of C₁₆Ti_4-2 as suitable hydrogen storage. AIM analysis of the studied C_20-nAl_n derivatives signifies the highest electron density (ρ (r)) of 0.294 a.u. and the highest positive Laplacian of electron density (∇²ρ (r)) of 0.190 a.u., at bond critical points (BCPs) of C-Ti bond in the most stable C₁₉Ti₁ species. This heterofullerene shows the lowest < α > between the studied structures. IR spectroscopy shows that exclusive of C₁₆Ti_4-1 (as transition state), the other optimized hollow cages (as global minima) have no imaginary frequency.