SPRED: A machine learning approach for the identification of classical and non-classical secretory proteins in mammalian genomes

Deepstacked-AVPs: predicting antiviral peptides using tri-segment evolutionary profile and word embedding based multi-perspective features with deep stacking model

BACKGROUND

Viral infections have been the main health issue in the last decade. Antiviral peptides (AVPs) are a subclass of antimicrobial peptides (AMPs) with substantial potential to protect the human body against various viral diseases. However, there has been significant production of antiviral vaccines and medications. Recently, the development of AVPs as an antiviral agent suggests an effective way to treat virus-affected cells. Recently, the involvement of intelligent machine learning techniques for developing peptide-based therapeutic agents is becoming an increasing interest due to its significant outcomes. The existing wet-laboratory-based drugs are expensive, time-consuming, and cannot effectively perform in screening and predicting the targeted motif of antiviral peptides.

METHODS

In this paper, we proposed a novel computational model called Deepstacked-AVPs to discriminate AVPs accurately. The training sequences are numerically encoded using a novel Tri-segmentation-based position-specific scoring matrix (PSSM-TS) and word2vec-based semantic features. Composition/Transition/Distribution-Transition (CTDT) is also employed to represent the physiochemical properties based on structural features. Apart from these, the fused vector is formed using PSSM-TS features, semantic information, and CTDT descriptors to compensate for the limitations of single encoding methods. Information gain (IG) is applied to choose the optimal feature set. The selected features are trained using a stacked-ensemble classifier.

RESULTS

The proposed Deepstacked-AVPs model achieved a predictive accuracy of 96.60%%, an area under the curve (AUC) of 0.98, and a precision-recall (PR) value of 0.97 using training samples. In the case of the independent samples, our model obtained an accuracy of 95.15%, an AUC of 0.97, and a PR value of 0.97.

CONCLUSION

Our Deepstacked-AVPs model outperformed existing models with a ~ 4% and ~ 2% higher accuracy using training and independent samples, respectively. The reliability and efficacy of the proposed Deepstacked-AVPs model make it a valuable tool for scientists and may perform a beneficial role in pharmaceutical design and research academia.

A random forest model for predicting exosomal proteins using evolutionary information and motifs

Non-invasive diagnostics and therapies are crucial to prevent patients from undergoing painful procedures. Exosomal proteins can serve as important biomarkers for such advancements. In this study, we attempted to build a model to predict exosomal proteins. All models are trained, tested, and evaluated on a non-redundant dataset comprising 2831 exosomal and 2831 non-exosomal proteins, where no two proteins have more than 40% similarity. Initially, the standard similarity-based method Basic Local Alignment Search Tool (BLAST) was used to predict exosomal proteins, which failed due to low-level similarity in the dataset. To overcome this challenge, machine learning (ML) based models were developed using compositional and evolutionary features of proteins achieving an area under the receiver operating characteristics (AUROC) of 0.73. Our analysis also indicated that exosomal proteins have a variety of sequence-based motifs which can be used to predict exosomal proteins. Hence, we developed a hybrid method combining motif-based and ML-based approaches for predicting exosomal proteins, achieving a maximum AUROC of 0.85 and MCC of 0.56 on an independent dataset. This hybrid model performs better than presently available methods when assessed on an independent dataset. A web server and a standalone software ExoProPred (https://webs.iiitd.edu.in/raghava/exopropred/) have been created to help scientists predict and discover exosomal proteins and find functional motifs present in them.

Challenges in Serologic Diagnostics of Neglected Human Systemic Mycoses: An Overview on Characterization of New Targets

Systemic mycoses have been viewed as neglected diseases and they are responsible for deaths and disabilities around the world. Rapid, low-cost, simple, highly-specific and sensitive diagnostic tests are critical components of patient care, disease control and active surveillance. However, the diagnosis of fungal infections represents a great challenge because of the decline in the expertise needed for identifying fungi, and a reduced number of instruments and assays specific to fungal identification. Unfortunately, time of diagnosis is one of the most important risk factors for mortality rates from many of the systemic mycoses. In addition, phenotypic and biochemical identification methods are often time-consuming, which has created an increasing demand for new methods of fungal identification. In this review, we discuss the current context of the diagnosis of the main systemic mycoses and propose alternative approaches for the identification of new targets for fungal pathogens, which can help in the development of new diagnostic tests.

ECM-LSE: Prediction of Extracellular Matrix Proteins Using Deep Latent Space Encoding of k-Spaced Amino Acid Pairs

Extracelluar matrix (ECM) proteins create complex networks of macromolecules which fill-in the extracellular spaces of living tissues. They provide structural support and play an important role in maintaining cellular functions. Identification of ECM proteins can play a vital role in studying various types of diseases. Conventional wet lab-based methods are reliable; however, they are expensive and time consuming and are, therefore, not scalable. In this research, we propose a sequence-based novel machine learning approach for the prediction of ECM proteins. In the proposed method, composition of k-spaced amino acid pair (CKSAAP) features are encoded into a classifiable latent space (LS) with the help of deep latent space encoding (LSE). A comprehensive ablation analysis is conducted for performance evaluation of the proposed method. Results are compared with other state-of-the-art methods on the benchmark dataset, and the proposed ECM-LSE approach has shown to comprehensively outperform the contemporary methods.

Prediction of unconventional protein secretion by exosomes

MOTIVATION

In eukaryotes, proteins targeted for secretion contain a signal peptide, which allows them to proceed through the conventional ER/Golgi-dependent pathway. However, an important number of proteins lacking a signal peptide can be secreted through unconventional routes, including that mediated by exosomes. Currently, no method is available to predict protein secretion via exosomes.

RESULTS

Here, we first assembled a dataset including the sequences of 2992 proteins secreted by exosomes and 2961 proteins that are not secreted by exosomes. Subsequently, we trained different random forests models on feature vectors derived from the sequences in this dataset. In tenfold cross-validation, the best model was trained on dipeptide composition, reaching an accuracy of 69.88% ± 2.08 and an area under the curve (AUC) of 0.76 ± 0.03. In an independent dataset, this model reached an accuracy of 75.73% and an AUC of 0.840. After these results, we developed ExoPred, a web-based tool that uses random forests to predict protein secretion by exosomes.

CONCLUSION

ExoPred is available for free public use at http://imath.med.ucm.es/exopred/ . Datasets are available at http://imath.med.ucm.es/exopred/datasets/ .

Evolution, role in inflammation, and redox control of leaderless secretory proteins

Members of the interleukin (IL)-1 family are key determinants of inflammation. Despite their role as intercellular mediators, most lack the leader peptide typically required for protein secretion. This lack is a characteristic of dozens of other proteins that are actively and selectively secreted from living cells independently of the classical endoplasmic reticulum-Golgi exocytic route. These proteins, termed leaderless secretory proteins (LLSPs), comprise proteins directly or indirectly involved in inflammation, including cytokines such as IL-1β and IL-18, growth factors such as fibroblast growth factor 2 (FGF2), redox enzymes such as thioredoxin, and proteins most expressed in the brain, some of which participate in the pathogenesis of neurodegenerative disorders. Despite much effort, motifs that promote LLSP secretion remain to be identified. In this review, we summarize the mechanisms and pathophysiological significance of the unconventional secretory pathways that cells use to release LLSPs. We place special emphasis on redox regulation and inflammation, with a focus on IL-1β, which is secreted after processing of its biologically inactive precursor pro-IL-1β in the cytosol. Although LLSP externalization remains poorly understood, some possible mechanisms have emerged. For example, a common feature of LLSP pathways is that they become more active in response to stress and that they involve several distinct excretion mechanisms, including direct plasma membrane translocation, lysosome exocytosis, exosome formation, membrane vesiculation, autophagy, and pyroptosis. Further investigations of unconventional secretory pathways for LLSP secretion may shed light on their evolution and could help advance therapeutic avenues for managing pathological conditions, such as diseases arising from inflammation.

Nglyc: A Random Forest Method for Prediction of N-Glycosylation Sites in Eukaryotic Protein Sequence

Background:

N-Glycosylation is one of the most important post-translational mechanisms in eukaryotes. N-glycosylation predominantly occurs in N-X-[S/T] sequon where X is any amino acid other than proline. However, not all N-X-[S/T] sequons in proteins are glycosylated. Therefore, accurate prediction of N-glycosylation sites is essential to understand Nglycosylation mechanism.

Objective:

In this article, our motivation is to develop a computational method to predict Nglycosylation sites in eukaryotic protein sequences.

Methods:

In this article, we report a random forest method, Nglyc, to predict N-glycosylation site from protein sequence, using 315 sequence features. The method was trained using a dataset of 600 N-glycosylation sites and 600 non-glycosylation sites and tested on the dataset containing 295 Nglycosylation sites and 253 non-glycosylation sites. Nglyc prediction was compared with NetNGlyc, EnsembleGly and GPP methods. Further, the performance of Nglyc was evaluated using human and mouse N-glycosylation sites.

Results:

Nglyc method achieved an overall training accuracy of 0.8033 with all 315 features. Performance comparison with NetNGlyc, EnsembleGly and GPP methods shows that Nglyc performs better than the other methods with high sensitivity and specificity rate.

Conclusion:

Our method achieved an overall accuracy of 0.8248 with 0.8305 sensitivity and 0.8182 specificity. Comparison study shows that our method performs better than the other methods. Applicability and success of our method was further evaluated using human and mouse N-glycosylation sites. Nglyc method is freely available at https://github.com/bioinformaticsML/ Ngly.

SubmitoLoc: Identification of mitochondrial sub cellular locations of proteins using support vector machine

Mitochondria are important sub-cellular organelles in eukaryotes. Defects in mitochondrial system lead to a variety of disease. Therefore, detailed knowledge of mitochondrial proteome is vital to understand mitochondrial system and their function. Sequence databases contain large number of mitochondrial proteins but they are mostly not annotated. In this study, we developed a support vector machine approach, SubmitoLoc, to predict mitochondrial sub cellular locations of proteins based on various sequence derived properties. We evaluated the predictor using 10-fold cross validation. Our method achieved 88.56 % accuracy using all features. Average sensitivity and specificity for four-subclass prediction is 85.37% and 87.25% respectively. High prediction accuracy suggests that SubmitoLoc will be useful for researchers studying mitochondrial biology and drug discovery.

OutCyte: a novel tool for predicting unconventional protein secretion

The prediction of protein localization, such as in the extracellular space, from high-throughput data is essential for functional downstream inference. It is well accepted that some secreted proteins go through the classic endoplasmic reticulum-Golgi pathway with the guidance of a signal peptide. However, a large number of proteins have been found to reach the extracellular space by following unconventional secretory pathways. There remains a demand for reliable prediction of unconventional protein secretion (UPS). Here, we present OutCyte, a fast and accurate tool for the prediction of UPS, which for the first time has been built upon experimentally determined UPS proteins. OutCyte mediates the prediction of protein secretion in two steps: first, proteins with N-terminal signals are accurately filtered out; second, proteins without N-terminal signals are classified as UPS or intracellular proteins based on physicochemical features directly generated from their amino acid sequences. We are convinced that OutCyte will play a relevant role in the annotation of experimental data and will therefore contribute to further characterization of the extracellular nature of proteins by considering the commonly neglected UPS proteins.

OutCyte has been implemented as a web server atwww.outcyte.com.

Predicting FAD Interacting Residues with Feature Selection and Comprehensive Sequence Descriptors

The function of a flavoprotein is determined to a great extent by the binding sites on its surface that interacts with flavin adenine dinucleotide (FAD). Malfunction or dysregulation of FAD binding leads to a series of diseases. Therefore, accurately identifying FAD interacting residues (FIRs) provides insights into the molecular mechanisms of flavoprotein-related biological processes and disease progression. In this paper, a new computational method is proposed for identifying FIRs from protein sequences. Various sequence-derived discriminative features are explored. We analyze the distinctions of these features between FIRs and non-FIRs. We also investigate the predictive capabilities of both individual features and combinations of features. A relief algorithm followed by incremental feature selection (relief-IFS) is then adopted to search the optimal features. Finally, a random forest (RF) module is used to predict FIRs based on the optimal features. Using a 5-fold cross-validation test, the proposed method performs well, with a sensitivity of 0.847, a specificity of 0.933, an accuracy of 0.890, and a Matthews correlation coefficient (MCC) of 0.782, thereby outperforming previous methods. These results indicate that our method is relatively successful at predicting FIRs.

A Two-Step Feature Selection Method to Predict Cancerlectins by Multiview Features and Synthetic Minority Oversampling Technique

Cancerlectins have an inhibitory effect on the growth of cancer cells and are currently being employed as therapeutic agents. The accurate identification of the cancerlectins should provide insight into the molecular mechanisms of cancers. In this study, a new computational method based on the RF (Random Forest) algorithm is proposed for further improving the performance of identifying cancerlectins. Hybrid feature space before feature selection is developed by combining different individual feature spaces, CTD (Composition, Transition, and Distribution), PseAAC (Pseudo Amino Acid Composition), PSSM (Position-Specific Scoring Matrix), and disorder. The SMOTE (Synthetic Minority Oversampling Technique) is applied to solve the imbalanced data problem. To reduce feature redundancy and computation complexity, we propose a two-step feature selection process to select informative features. A 5-fold cross-validation technique is used for the evaluation of various prediction strategies. The proposed method achieves a sensitivity of 0.779, a specificity of 0.717, an accuracy of 0.748, and an MCC (Matthew's Correlation Coefficient) of 0.497. The prediction results are also compared with other existing methods on the same dataset using 5-fold cross-validation. The comparison results demonstrate the high effectiveness of our method for predicting cancerlectins.

RAFP-Pred: Robust Prediction of Antifreeze Proteins Using Localized Analysis of n-Peptide Compositions

In extreme cold weather, living organisms produce Antifreeze Proteins (AFPs) to counter the otherwise lethal intracellular formation of ice. Structures and sequences of various AFPs exhibit a high degree of heterogeneity, consequently the prediction of the AFPs is considered to be a challenging task. In this research, we propose to handle this arduous manifold learning task using the notion of localized processing. In particular, an AFP sequence is segmented into two sub-segments each of which is analyzed for amino acid and di-peptide compositions. We propose to use only the most significant features using the concept of information gain (IG) followed by a random forest classification approach. The proposed RAFP-Pred achieved an excellent performance on a number of standard datasets. We report a high Youden's index (sensitivity+specificity-1) value of 0.75 on the standard independent test data set outperforming the AFP-PseAAC, AFP_PSSM, AFP-Pred, and iAFP by a margin of 0.05, 0.06, 0.14, and 0.68, respectively. The verification rate on the UniProKB dataset is found to be 83.19 percent which is substantially superior to the 57.18 percent reported for the iAFP method.

A Novel Feature Extraction Method with Feature Selection to Identify Golgi-Resident Protein Types from Imbalanced Data

The Golgi Apparatus (GA) is a major collection and dispatch station for numerous proteins destined for secretion, plasma membranes and lysosomes. The dysfunction of GA proteins can result in neurodegenerative diseases. Therefore, accurate identification of protein subGolgi localizations may assist in drug development and understanding the mechanisms of the GA involved in various cellular processes. In this paper, a new computational method is proposed for identifying cis-Golgi proteins from trans-Golgi proteins. Based on the concept of Common Spatial Patterns (CSP), a novel feature extraction technique is developed to extract evolutionary information from protein sequences. To deal with the imbalanced benchmark dataset, the Synthetic Minority Over-sampling Technique (SMOTE) is adopted. A feature selection method called Random Forest-Recursive Feature Elimination (RF-RFE) is employed to search the optimal features from the CSP based features and g-gap dipeptide composition. Based on the optimal features, a Random Forest (RF) module is used to distinguish cis-Golgi proteins from trans-Golgi proteins. Through the jackknife cross-validation, the proposed method achieves a promising performance with a sensitivity of 0.889, a specificity of 0.880, an accuracy of 0.885, and a Matthew's Correlation Coefficient (MCC) of 0.765, which remarkably outperforms previous methods. Moreover, when tested on a common independent dataset, our method also achieves a significantly improved performance. These results highlight the promising performance of the proposed method to identify Golgi-resident protein types. Furthermore, the CSP based feature extraction method may provide guidelines for protein function predictions.

Better Than Nothing? Limitations of the Prediction Tool SecretomeP in the Search for Leaderless Secretory Proteins (LSPs) in Plants

In proteomic analyses of the plant secretome, the presence of putative leaderless secretory proteins (LSPs) is difficult to confirm due to the possibility of contamination from other sub-cellular compartments. In the absence of a plant-specific tool for predicting LSPs, the mammalian-trained SecretomeP has been applied to plant proteins in multiple studies to identify the most likely LSPs. This study investigates the effectiveness of using SecretomeP on plant proteins, identifies its limitations and provides a benchmark for its use. In the absence of experimentally verified LSPs we exploit the common-feature hypothesis behind SecretomeP and use known classically secreted proteins (CSPs) of plants as a proxy to evaluate its accuracy. We show that, contrary to the common-feature hypothesis, plant CSPs are a poor proxy for evaluating LSP detection due to variation in the SecretomeP prediction scores when the signal peptide (SP) is modified. Removing the SP region from CSPs and comparing the predictive performance against non-secretory proteins indicates that commonly used threshold scores of 0.5 and 0.6 result in false-positive rates in excess of 0.3 when applied to plants proteins. Setting the false-positive rate to 0.05, consistent with the original mammalian performance of SecretomeP, yields only a marginally higher true positive rate compared to false positives. Therefore the use of SecretomeP on plant proteins is not recommended. This study investigates the trade-offs of using SecretomeP on plant proteins and provides insights into predictive features for future development of plant-specific common-feature tools.

An Effective Antifreeze Protein Predictor with Ensemble Classifiers and Comprehensive Sequence Descriptors

Antifreeze proteins (AFPs) play a pivotal role in the antifreeze effect of overwintering organisms. They have a wide range of applications in numerous fields, such as improving the production of crops and the quality of frozen foods. Accurate identification of AFPs may provide important clues to decipher the underlying mechanisms of AFPs in ice-binding and to facilitate the selection of the most appropriate AFPs for several applications. Based on an ensemble learning technique, this study proposes an AFP identification system called AFP-Ensemble. In this system, random forest classifiers are trained by different training subsets and then aggregated into a consensus classifier by majority voting. The resulting predictor yields a sensitivity of 0.892, a specificity of 0.940, an accuracy of 0.938 and a balanced accuracy of 0.916 on an independent dataset, which are far better than the results obtained by previous methods. These results reveal that AFP-Ensemble is an effective and promising predictor for large-scale determination of AFPs. The detailed feature analysis in this study may give useful insights into the molecular mechanisms of AFP-ice interactions and provide guidance for the related experimental validation. A web server has been designed to implement the proposed method.

An ensemble method with hybrid features to identify extracellular matrix proteins

The extracellular matrix (ECM) is a dynamic composite of secreted proteins that play important roles in numerous biological processes such as tissue morphogenesis, differentiation and homeostasis. Furthermore, various diseases are caused by the dysfunction of ECM proteins. Therefore, identifying these important ECM proteins may assist in understanding related biological processes and drug development. In view of the serious imbalance in the training dataset, a Random Forest-based ensemble method with hybrid features is developed in this paper to identify ECM proteins. Hybrid features are employed by incorporating sequence composition, physicochemical properties, evolutionary and structural information. The Information Gain Ratio and Incremental Feature Selection (IGR-IFS) methods are adopted to select the optimal features. Finally, the resulting predictor termed IECMP (Identify ECM Proteins) achieves an balanced accuracy of 86.4% using the 10-fold cross-validation on the training dataset, which is much higher than results obtained by other methods (ECMPRED: 71.0%, ECMPP: 77.8%). Moreover, when tested on a common independent dataset, our method also achieves significantly improved performance over ECMPP and ECMPRED. These results indicate that IECMP is an effective method for ECM protein prediction, which has a more balanced prediction capability for positive and negative samples. It is anticipated that the proposed method will provide significant information to fully decipher the molecular mechanisms of ECM-related biological processes and discover candidate drug targets. For public access, we develop a user-friendly web server for ECM protein identification that is freely accessible at http://iecmp.weka.cc.

EcmPred: prediction of extracellular matrix proteins based on random forest with maximum relevance minimum redundancy feature selection

The extracellular matrix (ECM) is a major component of tissues of multicellular organisms. It consists of secreted macromolecules, mainly polysaccharides and glycoproteins. Malfunctions of ECM proteins lead to severe disorders such as marfan syndrome, osteogenesis imperfecta, numerous chondrodysplasias, and skin diseases. In this work, we report a random forest approach, EcmPred, for the prediction of ECM proteins from protein sequences. EcmPred was trained on a dataset containing 300 ECM and 300 non-ECM and tested on a dataset containing 145 ECM and 4187 non-ECM proteins. EcmPred achieved 83% accuracy on the training and 77% on the test dataset. EcmPred predicted 15 out of 20 experimentally verified ECM proteins. By scanning the entire human proteome, we predicted novel ECM proteins validated with gene ontology and InterPro. The dataset and standalone version of the EcmPred software is available at http://www.inb.uni-luebeck.de/tools-demos/Extracellular_matrix_proteins/EcmPred.

Ranking Gene Ontology terms for predicting non-classical secretory proteins in eukaryotes and prokaryotes

Protein secretion is an important biological process for both eukaryotes and prokaryotes. Several sequence-based methods mainly rely on utilizing various types of complementary features to design accurate classifiers for predicting non-classical secretory proteins. Gene Ontology (GO) terms are increasing informative in predicting protein functions. However, the number of used GO terms is often very large. For example, there are 60,020 GO terms used in the prediction method Euk-mPLoc 2.0 for subcellular localization. This study proposes a novel approach to identify a small set of m top-ranked GO terms served as the only type of input features to design a support vector machine (SVM) based method Sec-GO to predict non-classical secretory proteins in both eukaryotes and prokaryotes. To evaluate the Sec-GO method, two existing methods and their used datasets are adopted for performance comparisons. The Sec-GO method using m=436 GO terms yields an independent test accuracy of 96.7% on mammalian proteins, much better than the existing method SPRED (82.2%) which uses frequencies of tri-peptides and short peptides, secondary structure, and physicochemical properties as input features of a random forest classifier. Furthermore, when applying to Gram-positive bacterial proteins, the Sec-GO with m=158 GO terms has a test accuracy of 94.5%, superior to NClassG+ (90.0%) which uses SVM with several feature types, comprising amino acid composition, di-peptides, physicochemical properties and the position specific weighting matrix. Analysis of the distribution of secretory proteins in a GO database indicates the percentage of the non-classical secretory proteins annotated by GO is larger than that of classical secretory proteins in both eukaryotes and prokaryotes. Of the m top-ranked GO features, the top-four GO terms are all annotated by such subcellular locations as GO:0005576 (Extracellular region). Additionally, the method Sec-GO is easily implemented and its web tool of prediction is available at iclab.life.nctu.edu.tw/secgo.

The cardiokine story unfolds: ischemic stress-induced protein secretion in the heart

Intercellular communication depends on many factors, including proteins released via the classical or non-classical secretory pathways, many of which must be properly folded to be functional. Owing to their adverse effects on the secretion machinery, stresses such as ischemia can impair the folding of secreted proteins. Paradoxically, cells rely on secreted proteins to mount a response designed to resist stress-induced damage. This review examines this paradox using proteins secreted from the heart, cardiokines, as examples, and focuses on how the ischemic heart maintains or even increases the release of select cardiokines that regulate important cellular processes in the heart, including excitation-contraction coupling, hypertrophic growth, myocardial remodeling and stem cell function, in ways that moderate ischemic damage and enhance cardiac repair.

AFP-Pred: A random forest approach for predicting antifreeze proteins from sequence-derived properties

Some creatures living in extremely low temperatures can produce some special materials called "antifreeze proteins" (AFPs), which can prevent the cell and body fluids from freezing. AFPs are present in vertebrates, invertebrates, plants, bacteria, fungi, etc. Although AFPs have a common function, they show a high degree of diversity in sequences and structures. Therefore, sequence similarity based search methods often fails to predict AFPs from sequence databases. In this work, we report a random forest approach "AFP-Pred" for the prediction of antifreeze proteins from protein sequence. AFP-Pred was trained on the dataset containing 300 AFPs and 300 non-AFPs and tested on the dataset containing 181 AFPs and 9193 non-AFPs. AFP-Pred achieved 81.33% accuracy from training and 83.38% from testing. The performance of AFP-Pred was compared with BLAST and HMM. High prediction accuracy and successful of prediction of hypothetical proteins suggests that AFP-Pred can be a useful approach to identify antifreeze proteins from sequence information, irrespective of their sequence similarity.