Search

It is well-known that the major reason for the rapid proliferation of cancer cells are the hypomethylation of the whole cancer genome and the hypermethylation of the promoter of particular tumor suppressor genes. Locating 5-methylcytosine (5mC) sites in promoters is therefore a crucial step in further understanding of the relationship between promoter methylation and the regulation of mRNA gene expression. High throughput identification of DNA 5mC in wet lab is still time-consuming and labor-extensive. Thus, finding the 5mC site of genome-wide DNA promoters is still an important task. We compared the effectiveness of the most popular and strong machine learning techniques namely XGBoost, Random Forest, Deep Forest, and Deep Feedforward Neural Network in predicting the 5mC sites of genome-wide DNA promoters. A feature extraction method based on k-mers embeddings learned from a language model were also applied. Overall, the performance of all the surveyed models surpassed deep learning models of the latest studies on the same dataset employing other encoding scheme. Furthermore, the best model achieved AUC scores of 0.962 on both cross-validation and independent test data. We concluded that our approach was efficient for identifying 5mC sites of promoters with high performance.

Glycosylation is a dynamic enzymatic process that attaches glycan to proteins or other organic molecules such as lipoproteins. Research has shown that such a process in ion channel proteins plays a fundamental role in modulating ion channel functions. This study used a computational method to predict N-linked glycosylation sites, the most common type, in ion channel proteins. From segments of ion channel proteins centered around N-linked glycosylation sites, the amino acid embedding vectors of each residue were concatenated to create features for prediction. We experimented with two different models for converting amino acids to their corresponding embeddings: one was fed with ion channel sequences and the other with a large dataset composed of more than one million protein sequences. The latter model stemmed from the idea of transfer learning technique and emerged as a more efficient feature extractor. Our best model was obtained from this transfer learning approach and a hyperparameter tuning process with a random search on 5-fold cross-validation data. It achieved an accuracy, specificity, sensitivity, and Matthews correlation coefficient of 93.4%, 92.8%, 98.6%, and 0.726, respectively. Corresponding scores on an independent test were 92.9%, 92.2%, 99%, and 0.717. These results outperform the position-specific scoring matrix features that are predominantly employed in post-translational modification site predictions. Furthermore, compared to N-GlyDE, GlycoEP, SPRINT-Gly, the most recent N-linked glycosylation site predictors, our model yields higher scores on the above 4 metrics, thus further demonstrating the efficiency of our approach., (Copyright © 2021. Published by Elsevier Ltd.)

Background: Cytokines are a class of small proteins that act as chemical messengers and play a significant role in essential cellular processes including immunity regulation, hematopoiesis, and inflammation. As one important family of cytokines, tumor necrosis factors have association with the regulation of a various biological processes such as proliferation and differentiation of cells, apoptosis, lipid metabolism, and coagulation. The implication of these cytokines can also be seen in various diseases such as insulin resistance, autoimmune diseases, and cancer. Considering the interdependence between this kind of cytokine and others, classifying tumor necrosis factors from other cytokines is a challenge for biological scientists., Methods: In this research, we employed a word embedding technique to create hybrid features which was proved to efficiently identify tumor necrosis factors given cytokine sequences. We segmented each protein sequence into protein words and created corresponding word embedding for each word. Then, word embedding-based vector for each sequence was created and input into machine learning classification models. When extracting feature sets, we not only diversified segmentation sizes of protein sequence but also conducted different combinations among split grams to find the best features which generated the optimal prediction. Furthermore, our methodology follows a well-defined procedure to build a reliable classification tool., Results: With our proposed hybrid features, prediction models obtain more promising performance compared to seven prominent sequenced-based feature kinds. Results from 10 independent runs on the surveyed dataset show that on an average, our optimal models obtain an area under the curve of 0.984 and 0.998 on 5-fold cross-validation and independent test, respectively., Conclusions: These results show that biologists can use our model to identify tumor necrosis factors from other cytokines efficiently. Moreover, this study proves that natural language processing techniques can be applied reasonably to help biologists solve bioinformatics problems efficiently.

Land degradation encompasses ecological, biological, and physical deterioration of land resulting from natural or anthropogenic factors, including soil erosion. Piping erosion, specifically in arid and semi-arid regions, is recognized as a significant cause of land degradation. Therefore, it is crucial to identify the influential factors and spatially model this phenomenon to effectively control it. This investigation aims to study the spatial modeling and evaluation of piping erosion using machine learning models: random forest (RF) and two hybrid models, regularized random forest (RRF) and weighted subspace random forest (WSRF), in the Khoshkrood watershed of Markazi Province, Iran. In this study, 70% of the 179 recorded locations of piping erosion were randomly selected for model construction, while the remaining 30% were used for model validation. Fourteen geo-environmental variables affecting piping erosion were used as independent factors for modeling. The performance of the machine learning models was evaluated using five criteria, including sensitivity, specificity, and area under the curve (AUC). The results demonstrated that all three models performed well in predicting piping erosion. The AUC values for the WSRF, RRF, and RF models were 80.93%, 80.43%, and 79.11%, respectively. Moreover, the analysis of relative variable importance revealed that elevation was the most influential variable across all three models. The findings emphasize the significance of utilizing machine learning models for predicting and managing land degradation phenomena. By identifying influential geo-environmental and employing accurate spatial models, effective control measures can be implemented to mitigate the adverse impacts of piping erosion in arid and semi-arid regions. [ABSTRACT FROM AUTHOR]

In cellular transportation mechanisms, the movement of ions across the cell membrane and its proper control are important for cells, especially for life processes. Ion transporters/pumps and ion channel proteins work as border guards controlling the incessant traffic of ions across cell membranes. We revisited the study of classification of transporters and ion channels from membrane proteins with a more efficient deep learning approach. Specifically, we applied multi‐window scanning filters of convolutional neural networks on almost full‐length position‐specific scoring matrices for extracting useful information. In this way, we were able to retain important evolutionary information of the proteins. Our experiment results show that a convolutional neural network with a minimum number of convolutional layers can be enough to extract the conserved information of proteins which leads to higher performance. Our best prediction models were obtained after examining different data imbalanced handling techniques, and different protein encoding methods. We also showed that our models were superior to traditional deep learning approaches on the same datasets as well as other machine learning classification algorithms. [ABSTRACT FROM AUTHOR]

Living organisms receive necessary energy substances directly from cellular respiration. The completion of electron storage and transportation requires the process of cellular respiration with the aid of electron transport chains. Therefore, the work of deciphering electron transport proteins is inevitably needed. The identification of these proteins with high performance has a prompt dependence on the choice of methods for feature extraction and machine learning algorithm. In this study, protein sequences served as natural language sentences comprising words. The nominated word embedding-based feature sets, hinged on the word embedding modulation and protein motif frequencies, were useful for feature choosing. Five word embedding types and a variety of conjoint features were examined for such feature selection. The support vector machine algorithm consequentially was employed to perform classification. The performance statistics within the 5-fold cross-validation including average accuracy, specificity, sensitivity, as well as MCC rates surpass 0.95. Such metrics in the independent test are 96.82, 97.16, 95.76 percent, and 0.9, respectively. Compared to state-of-the-art predictors, the proposed method can generate more preferable performance above all metrics indicating the effectiveness of the proposed method in determining electron transport proteins. Furthermore, this study reveals insights about the applicability of various word embeddings for understanding surveyed sequences. [ABSTRACT FROM AUTHOR]

Since 2015, a fast growing number of deep learning–based methods have been proposed for protein–ligand binding site prediction and many have achieved promising performance. These methods, however, neglect the imbalanced nature of binding site prediction problems. Traditional data-based approaches for handling data imbalance employ linear interpolation of minority class samples. Such approaches may not be fully exploited by deep neural networks on downstream tasks. We present a novel technique for balancing input classes by developing a deep neural network–based variational autoencoder (VAE) that aims to learn important attributes of the minority classes concerning nonlinear combinations. After learning, the trained VAE was used to generate new minority class samples that were later added to the original data to create a balanced dataset. Finally, a convolutional neural network was used for classification, for which we assumed that the nonlinearity could be fully integrated. As a case study, we applied our method to the identification of FAD- and FMN-binding sites of electron transport proteins. Compared with the best classifiers that use traditional machine learning algorithms, our models obtained a great improvement on sensitivity while maintaining similar or higher levels of accuracy and specificity. We also demonstrate that our method is better than other data imbalance handling techniques, such as SMOTE, ADASYN, and class weight adjustment. Additionally, our models also outperform existing predictors in predicting the same binding types. Our method is general and can be applied to other data types for prediction problems with moderate-to-heavy data imbalances. [ABSTRACT FROM AUTHOR]

Recently, language representation models have drawn a lot of attention in the natural language processing field due to their remarkable results. Among them, bidirectional encoder representations from transformers (BERT) has proven to be a simple, yet powerful language model that achieved novel state-of-the-art performance. BERT adopted the concept of contextualized word embedding to capture the semantics and context of the words in which they appeared. In this study, we present a novel technique by incorporating BERT-based multilingual model in bioinformatics to represent the information of DNA sequences. We treated DNA sequences as natural sentences and then used BERT models to transform them into fixed-length numerical matrices. As a case study, we applied our method to DNA enhancer prediction, which is a well-known and challenging problem in this field. We then observed that our BERT-based features improved more than 5–10% in terms of sensitivity, specificity, accuracy and Matthews correlation coefficient compared to the current state-of-the-art features in bioinformatics. Moreover, advanced experiments show that deep learning (as represented by 2D convolutional neural networks; CNN) holds potential in learning BERT features better than other traditional machine learning techniques. In conclusion, we suggest that BERT and 2D CNNs could open a new avenue in biological modeling using sequence information. [ABSTRACT FROM AUTHOR]

Membrane proteins, the most important drug targets, account for around 30% of total proteins encoded by the genome of living organisms. An important role of these proteins is to bind adenosine triphosphate (ATP), facilitating crucial biological processes such as metabolism and cell signaling. There are several reports elucidating ATP-binding sites within proteins. However, such studies on membrane proteins are limited. Our prediction tool, DeepATP, combines evolutionary information in the form of Position Specific Scoring Matrix and two-dimensional Convolutional Neural Network to predict ATP-binding sites in membrane proteins with an MCC of 0.89 and an AUC of 99%. Compared to recently published ATP-binding site predictors and classifiers that use traditional machine learning algorithms, our approach performs significantly better. We suggest this method as a reliable tool for biologists for ATP-binding site prediction in membrane proteins. In this study, we approach a deep learning technique via convolutional neural network on position specific scoring matrix to identify ATP-binding sites in membrane proteins, which is the most important drug targets. We also addressed the imbalanced dataset issue, which can be seen in most binding site prediction problems. With an MCC of 0.89 and an AUC of 99%, our proposed technique can serve as a powerful tool for biologists to identify ATP-binding sites in membrane proteins. Moreover, this study provides a basis for further research that can enrich a field of applying deep learning in bioinformatics. Image 1 • Many life-essential biology mechanisms can be understood by identifying accurately ATP-binding sites in membrane proteins. • Existing predictors can be used to predict ATP-binding membrane proteins but lack of specificity reduces their potential. • The specific and greatly imbalanced dataset issue of ATP-binding sites in membrane proteins was also address. [ABSTRACT FROM AUTHOR]

Motivation Efflux protein plays a key role in pumping xenobiotics out of the cells. The prediction of efflux family proteins involved in transport process of compounds is crucial for understanding family structures, functions and energy dependencies. Many methods have been proposed to classify efflux pump transporters without considerations of any pump specific of efflux protein families. In other words, efflux proteins protect cells from extrusion of foreign chemicals. Moreover, almost all efflux protein families have the same structure based on the analysis of significant motifs. The motif sequences consisting of the same amount of residues will have high degrees of residue similarity and thus will affect the classification process. Consequently, it is challenging but vital to recognize the structures and determine energy dependencies of efflux protein families. In order to efficiently identify efflux protein families with considering about pump specific, we developed a 2 D convolutional neural network (2 D CNN) model called DeepEfflux. DeepEfflux tried to capture the motifs of sequences around hidden target residues to use as hidden features of families. In addition, the 2 D CNN model uses a position-specific scoring matrix (PSSM) as an input. Three different datasets, each for one family of efflux protein, was fed into DeepEfflux, and then a 5-fold cross validation approach was used to evaluate the training performance. Results The model evaluation results show that DeepEfflux outperforms traditional machine learning algorithms. Furthermore, the accuracy of 96.02%, 94.89% and 90.34% for classes A, B and C, respectively, in the independent test results show that our model can perform well and can be used as a reliable tool for identifying families of efflux proteins in transporters. Availability and implementation The online version of deepefflux is available at http://deepefflux.irit.fr. The source code of deepefflux is available both on the deepefflux website and at http://140.138.155.216/deepefflux/. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

• The first model to classify adaptor proteins into different molecular functions. • Interpretable AI has been implemented using deep learning, t -SNE, UMAP, and SHAP analyses. • Our combination is superior to other sequence-based features as well as conventional computational approaches. Adaptor proteins (APs) are a family of proteins that aids in intracellular membrane trafficking, and their impairments or defects are closely related to various disorders. Traditional methods to identify and classify APs require time and complex techniques, which were then advanced by machine learning and computational approaches to facilitate the APs recognition task. However, most studies focused on recognizing separate ones in the APs family or the APs in general with non-APs, lacking one comprehensive strategy to distinguish the complexes of AP subtypes. Herein, we proposed a novel method to implement one novel task as discriminating the AP complexes in the APs family, utilizing an interpretable deep neural network architecture on sequence-based encoding features. This work also introduced a benchmark data set of AP complexes originating from the UniProt and GeneOntology databases. To assess the robustness of our proposed method, we compared our performance to various machine learning algorithms and feature extraction strategies. Furthermore, the interpretation of the model's prediction performance was implemented using t -distributed stochastic neighbor embedding (t -SNE), uniform manifold approximation and projection (UMAP), and SHapley Additive exPlanations (SHAP) analysis to show the distribution of AP complexes on optimal features. The promising performance of our architecture can assist scientists not only in AP complexes distinction but also in general protein sequences. Moreover, we have also made our work publicly on GitHub https://github.com/khanhlee/adaptor-dnn. [ABSTRACT FROM AUTHOR]

Coastal water bodies are susceptible to high levels of pollution as a result of population growth, rapid urbanization, the expansion of industrial activities, including ports, and expanding tourism-related activities. Untreated sewage disposal from municipalities, industrial wastewater, and numerous recreational and commercial activities along the coast not only deteriorates the water quality but also poses a significant threat to the marine ecosystem, food chain, and public health. Therefore, continuous monitoring of coastal water quality is essential for the sustainable upkeep of marine and aquatic ecosystems. The study aims to assess the intra- and interannual variability of coastal water quality in the Sundarbans estuarine system, straddling the borders of India and Bangladesh. The study employed Landsat 8 OLI satellite data and in-situ measurements of water quality parameters, including temperature, pH, dissolved oxygen, phosphate, total phosphate, nitrate, and nitrite. These measurements were obtained from 100 sampling locations across the entire Sundarban estuarine ecosystem. The data collection spanned the pre-monsoon, monsoon, and post-monsoon periods in the years 2021 and 2022. Several sophisticated machine learning models, including Random Forest (RF), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Artificial Neural Network (ANN), were employed to precisely forecast various crucial water quality indicators. Cross-validation results showed that the random forest model is most promising, with R2 values ranging between 0.50 and 0.96, followed by the artificial neural network (R2 values ranging between 0.36 and 0.97), the support vector machine (R2 values ranging between 0.29 and 0.97), and the KNN (R2 values ranging between 0.26 and 0.94). Subsequently, a random forest algorithm was customized for the study area to compute the coastal water quality index on a seasonal scale for the years 2021 and 2022. Results reveal that the concentrations of dissolved oxygen, phosphate, total phosphate, nitrate, nitrite, pH, and water temperature were relatively higher during the pre-monsoon and post-monsoon seasons compared to the monsoon season. In situ and remote sensing data analysis confirmed that Sundarbans estuarine water quality was relatively good during the monsoon period as compared to the rest of the year. In addition, research also highlighted the significance of monsoonal rainfall in the watershed for maintaining coastal water quality. It is estimated that the coastal water was particularly vulnerable due to the combined effects of industrial waste water and municipal sewage discharge. Ultimately, the study demonstrates the effectiveness of machine learning models and remote sensing in predicting the condition of coastal waters. The findings of this research can offer significant perspectives to decision-makers in developing a sustainable strategy for the management of coastal water resources. [Display omitted] [ABSTRACT FROM AUTHOR]

• Mapping distributions of dominant tree species using SDM and RS in Hyrcanian forest. • Improve SDMs by adding useful RS variables in mountainous forests. • topographic variables, Sentinel-2 bands, and vegetation and soil indices, gave the best fit for the four tree species. • result of our DSDMs supports conservation management of forest biodiversity in this region. Species distribution models (SDMs) are useful for predictive and explanatory purposes, allowing biologists to identify how human and environmental factors influence distributions of plants and animals. Lack of high-resolution climatic variables is one of the challenges for accurately predicting distributions of organisms at local or landscape scales. This study used SDMs to predict four dominant tree species distributions in northern Iran temperate forests (400km2 area) using high-resolution Sentinel-2 data (20 m) and topographic variables. We divided the explanatory variables into four datasets with increasing complexity of Sentinel-2 data and modelled distributions using four statistical and machine learning algorithms: random forest (RF), generalized boosting model (GBM), generalized linear model (GLM), and generalized additive model (GAM). Our results suggested differences in the predictive performance of the four algorithms. We found the most complex dataset, including topographic variables, Sentinel-2 bands, and vegetation and soil indices, gave the best fit for the four tree species, improving the accuracy of models for the different species between 5 and 16%. We then selected the most complex dataset to produce an ensemble model of the modeling algorithms where evaluation criteria were varied for tree species. Our result showed that the performance of SDMs improved using different satellite remote sensing data including raw bands, topographic variables and indices in the Hyrcanian forest, northern Iran. Elevation was a more significant variable than Sentinel bands and Sentinel vegetation indices variables for predicting the tree species distributions. With the Hyrcanian Forest included in this study region of northern Iran recently declared a UNESCO World Heritage site, a key result of our improved species distribution maps for these four dominant tree species is to support conservation management of forest biodiversity in this region. [ABSTRACT FROM AUTHOR]