Protein Descriptors Research Articles

1D and 2D Feature Extraction Based on AAC and DC Protein Descriptors for Classification of Acetylation in Lysine Proteins using Convolutional Neural Network

Post-Translational Modification (PTM) denotes a biochemical alteration observed in an amino acid, playing crucial roles in protein activity, functionality, and the regulation of protein structure. The recognition of associated PTMs serves as a fundamental basis for understanding biological processes, therapeutic interventions for diseases, and the development of pharmaceutical agents. Using computational approaches (in silico) offers an efficient and cost-effective means to identify PTM sites swiftly. The exploration of protein classification commences with extracting protein sequence features that are subsequently transformed into numerical features for utilization in classification algorithms. Feature extraction methodologies involve using protein descriptors like Amino Acid Composition (AAC) and Dipeptide Composition (DC). Yet, these approaches exhibit a limitation by neglecting crucial amino acid sequence details. Moreover, both descriptor techniques generate a limited number of 1-dimensional (1D) features, which may not be ideal for processing through the Convolutional Neural Network (CNN) classification method. This investigation presents a novel approach to enhance feature diversity through protein sequence segmentation techniques, employing adjacent and overlapping segment strategies. Furthermore, the study illustrates the organization of features into 1D and 2D formats to facilitate processing through 1D CNN and 2D CNN classification methodologies. The findings of this research endeavour highlight the potential for enhancing the accuracy of acetylation classification in lysine proteins through the multiplication of protein sequence segments in a 2D configuration. The highest accuracy achieved for AAC and DC-based feature extraction methods is 77.39% and 76.75%, respectively.

Descriptor-augmented machine learning for enzyme-chemical interaction predictions

Descriptors play a pivotal role in enzyme design for the greener synthesis of biochemicals, as they could characterize enzymes and chemicals from the physicochemical and evolutionary perspective. This study examined the effects of various descriptors on the performance of Random Forest model used for enzyme-chemical relationships prediction. We curated activity data of seven specific enzyme families from the literature and developed the pipeline for evaluation the machine learning model performance using 10-fold cross-validation. The influence of protein and chemical descriptors was assessed in three scenarios, which were predicting the activity of unknown relations between known enzymes and known chemicals (new relationship evaluation), predicting the activity of novel enzymes on known chemicals (new enzyme evaluation), and predicting the activity of new chemicals on known enzymes (new chemical evaluation). The results showed that protein descriptors significantly enhanced the classification performance of model on new enzyme evaluation in three out of the seven datasets with the greatest number of enzymes, whereas chemical descriptors appear no effect. A variety of sequence-based and structure-based protein descriptors were constructed, among which the esm-2 descriptor achieved the best results. Using enzyme families as labels showed that descriptors could cluster proteins well, which could explain the contributions of descriptors to the machine learning model. As a counterpart, in the new chemical evaluation, chemical descriptors made significant improvement in four out of the seven datasets, while protein descriptors appear no effect. We attempted to evaluate the generalization ability of the model by correlating the statistics of the datasets with the performance of the models. The results showed that datasets with higher sequence similarity were more likely to get better results in the new enzyme evaluation and datasets with more enzymes were more likely beneficial from the protein descriptor strategy. This work provides guidance for the development of machine learning models for specific enzyme families.

DescribePROT in 2023: more, higher-quality and experimental annotations and improved data download options.

The DescribePROT database of amino acid-level descriptors of protein structures and functions was substantially expanded since its release in 2020. This expansion includes substantial increase in the size, scope, and quality of the underlying data, the addition of experimental structural information, the inclusion of new data download options, and an upgraded graphical interface. DescribePROT currently covers 19 structural and functional descriptors for proteins in 273 reference proteomes generated by 11 accurate and complementary predictive tools. Users can search our resource in multiple ways, interact with the data using the graphical interface, and download data at various scales including individual proteins, entire proteomes, and whole database. The annotations in DescribePROT are useful for a broad spectrum of studies that include investigations of protein structure and function, development and validation of predictive tools, and to support efforts in understanding molecular underpinnings of diseases and development of therapeutics. DescribePROT can be freely accessed at http://biomine.cs.vcu.edu/servers/DESCRIBEPROT/.

Fuse feeds as one: cross-modal framework for general identification of AMPs.

Antimicrobial peptides (AMPs) are promising candidates for the development of new antibiotics due to their broad-spectrum activity against a range of pathogens. However, identifying AMPs through a huge bunch of candidates is challenging due to their complex structures and diverse sequences. In this study, we propose SenseXAMP, a cross-modal framework that leverages semantic embeddings of and protein descriptors (PDs) of input sequences to improve the identification performance of AMPs. SenseXAMP includes a multi-input alignment module and cross-representation fusion module to explore the hidden information between the two input features and better leverage the fusion feature. To better address the AMPs identification task, we accumulate the latest annotated AMPs data to form more generous benchmark datasets. Additionally, we expand the existing AMPs identification task settings by adding an AMPs regression task to meet more specific requirements like antimicrobial activity prediction. The experimental results indicated that SenseXAMP outperformed existing state-of-the-art models on multiple AMP-related datasets including commonly used AMPs classification datasets and our proposed benchmark datasets. Furthermore, we conducted a series of experiments to demonstrate the complementary nature of traditional PDs and protein pre-training models in AMPs tasks. Our experiments reveal that SenseXAMP can effectively combine the advantages of PDs to improve the performance of protein pre-training models in AMPs tasks.

3DDPDs: describing protein dynamics for proteochemometric bioactivity prediction. A case for (mutant) G protein-coupled receptors

Proteochemometric (PCM) modelling is a powerful computational drug discovery tool used in bioactivity prediction of potential drug candidates relying on both chemical and protein information. In PCM features are computed to describe small molecules and proteins, which directly impact the quality of the predictive models. State-of-the-art protein descriptors, however, are calculated from the protein sequence and neglect the dynamic nature of proteins. This dynamic nature can be computationally simulated with molecular dynamics (MD). Here, novel 3D dynamic protein descriptors (3DDPDs) were designed to be applied in bioactivity prediction tasks with PCM models. As a test case, publicly available G protein-coupled receptor (GPCR) MD data from GPCRmd was used. GPCRs are membrane-bound proteins, which are activated by hormones and neurotransmitters, and constitute an important target family for drug discovery. GPCRs exist in different conformational states that allow the transmission of diverse signals and that can be modified by ligand interactions, among other factors. To translate the MD-encoded protein dynamics two types of 3DDPDs were considered: one-hot encoded residue-specific (rs) and embedding-like protein-specific (ps) 3DDPDs. The descriptors were developed by calculating distributions of trajectory coordinates and partial charges, applying dimensionality reduction, and subsequently condensing them into vectors per residue or protein, respectively. 3DDPDs were benchmarked on several PCM tasks against state-of-the-art non-dynamic protein descriptors. Our rs- and ps3DDPDs outperformed non-dynamic descriptors in regression tasks using a temporal split and showed comparable performance with a random split and in all classification tasks. Combinations of non-dynamic descriptors with 3DDPDs did not result in increased performance. Finally, the power of 3DDPDs to capture dynamic fluctuations in mutant GPCRs was explored. The results presented here show the potential of including protein dynamic information on machine learning tasks, specifically bioactivity prediction, and open opportunities for applications in drug discovery, including oncology.

Protein-Ligand Binding Affinity Prediction Exploiting Sequence Constituent Homology.

Molecular docking is a commonly used approach for estimating binding conformations and their resultant binding affinities. Machine learning has been successfully deployed to enhance such affinity estimations. Many methods of varying complexity have been developed making use of some or all the spatial and categorical information available in these structures. The evaluation of such methods has mainly been carried out using datasets from PDBbind. Particularly the CASF 2007, 2013 and 2016 datasets with dedicated test sets. This work demonstrates that only a small number of simple descriptors is necessary to efficiently estimate binding affinity for these complexes without the need to know the exact binding conformation of a ligand. The developed approach of using a small number of ligand and protein descriptors in conjunction with gradient boosting trees demonstrates high performance on the CASF datasets. This includes the commonly used benchmark CASF2016 where it appears to perform better than any other approach. This methodology is also useful for datasets where the spatial relationship between the ligand and protein is unknown as demonstrated using a large ChEMBL derived dataset. Code and data uploaded to https://github.com/abbiAR/PLBAffinity. Supplementary data are available at Bioinformatics online.

A study of the interaction space of two lactate dehydrogenase isoforms (LDHA and LDHB) and some of their inhibitors using proteochemometrics modeling

Lactate dehydrogenase (LDH) is a tetramer enzyme that converts pyruvate to lactate reversibly. This enzyme becomes important because it is associated with diseases such as cancers, heart disease, liver problems, and most importantly, corona disease. As a system-based method, proteochemometrics does not require knowledge of the protein's three-dimensional structure, but rather depends on the amino acid sequence and protein descriptors. Here, we applied this methodology to model a set of LDHA and LDHB isoenzyme inhibitors. To implement the proteochemetrics method, the camb package in the R Studio Server programming environment was used. The activity of 312 compounds of LDHA and LDHB isoenzyme inhibitors from the valid Binding DB database was retrieved. The proteochemometrics method was applied to three machine learning algorithms gradient amplification model, random forest, and support vector machine as regression methods to find the best model. Through the combination of different models into an ensemble (greedy and stacking optimization), we explored the possibility of improving the performance of models. For the RF best ensemble model of inhibitors of LDHA and LDHB isoenzymes, and were 0.66 and 0.62, respectively. LDH inhibitory activation is influenced by Morgan fingerprints and topological structure descriptors.

A Hybrid Docking and Machine Learning Approach to Enhance the Performance of Virtual Screening Carried out on Protein-Protein Interfaces.

The modulation of protein-protein interactions (PPIs) by small chemical compounds is challenging. PPIs play a critical role in most cellular processes and are involved in numerous disease pathways. As such, novel strategies that assist the design of PPI inhibitors are of major importance. We previously reported that the knowledge-based DLIGAND2 scoring tool was the best-rescoring function for improving receptor-based virtual screening (VS) performed with the Surflex docking engine applied to several PPI targets with experimentally known active and inactive compounds. Here, we extend our investigation by assessing the vs. potential of other types of scoring functions with an emphasis on docking-pose derived solvent accessible surface area (SASA) descriptors, with or without the use of machine learning (ML) classifiers. First, we explored rescoring strategies of Surflex-generated docking poses with five GOLD scoring functions (GoldScore, ChemScore, ASP, ChemPLP, ChemScore with Receptor Depth Scaling) and with consensus scoring. The top-ranked poses were post-processed to derive a set of protein and ligand SASA descriptors in the bound and unbound states, which were combined to derive descriptors of the docked protein-ligand complexes. Further, eight ML models (tree, bagged forest, random forest, Bayesian, support vector machine, logistic regression, neural network, and neural network with bagging) were trained using the derivatized SASA descriptors and validated on test sets. The results show that many SASA descriptors are better than Surflex and GOLD scoring functions in terms of overall performance and early recovery success on the used dataset. The ML models were superior to all scoring functions and rescoring approaches for most targets yielding up to a seven-fold increase in enrichment factors at 1% of the screened collections. In particular, the neural networks and random forest-based ML emerged as the best techniques for this PPI dataset, making them robust and attractive vs. tools for hit-finding efforts. The presented results suggest that exploring further docking-pose derived SASA descriptors could be valuable for structure-based virtual screening projects, and in the present case, to assist the rational design of small-molecule PPI inhibitors.

Predicting unseen antibodies’ neutralizability via adaptive graph neural networks

Most natural and synthetic antibodies are ‘unseen’. That is, the demonstration of their neutralization effects with any antigen requires laborious and costly wet-lab experiments. The existing methods that learn antibody representations from known antibody–antigen interactions are unsuitable for unseen antibodies owing to the absence of interaction instances. The DeepAAI method proposed herein learns unseen antibody representations by constructing two adaptive relation graphs among antibodies and antigens and applying Laplacian smoothing between unseen and seen antibodies’ representations. Rather than using static protein descriptors, DeepAAI learns representations and relation graphs ‘dynamically’, optimized towards the downstream tasks of neutralization prediction and 50% inhibition concentration estimation. The performance of DeepAAI is demonstrated on human immunodeficiency virus, severe acute respiratory syndrome coronavirus 2, influenza and dengue. Moreover, the relation graphs have rich interpretability. The antibody relation graph implies similarity in antibody neutralization reactions, and the antigen relation graph indicates the relation among a virus’s different variants. We accordingly recommend probable broad-spectrum antibodies against new variants of these viruses.

ICAN: Interpretable cross-attention network for identifying drug and target protein interactions.

Drug–target protein interaction (DTI) identification is fundamental for drug discovery and drug repositioning, because therapeutic drugs act on disease-causing proteins. However, the DTI identification process often requires expensive and time-consuming tasks, including biological experiments involving large numbers of candidate compounds. Thus, a variety of computation approaches have been developed. Of the many approaches available, chemo-genomics feature-based methods have attracted considerable attention. These methods compute the feature descriptors of drugs and proteins as the input data to train machine and deep learning models to enable accurate prediction of unknown DTIs. In addition, attention-based learning methods have been proposed to identify and interpret DTI mechanisms. However, improvements are needed for enhancing prediction performance and DTI mechanism elucidation. To address these problems, we developed an attention-based method designated the interpretable cross-attention network (ICAN), which predicts DTIs using the Simplified Molecular Input Line Entry System of drugs and amino acid sequences of target proteins. We optimized the attention mechanism architecture by exploring the cross-attention or self-attention, attention layer depth, and selection of the context matrixes from the attention mechanism. We found that a plain attention mechanism that decodes drug-related protein context features without any protein-related drug context features effectively achieved high performance. The ICAN outperformed state-of-the-art methods in several metrics on the DAVIS dataset and first revealed with statistical significance that some weighted sites in the cross-attention weight matrix represent experimental binding sites, thus demonstrating the high interpretability of the results. The program is freely available at https://github.com/kuratahiroyuki/ICAN.

A multiscale modeling methodfor therapeutic antibodies in ion exchange chromatography.

The development of biopharmaceutical downstream processes relies on exhaustive experimental studies. The root cause is the poorly understood relationship between the protein structure of monoclonal antibodies (mAbs) and their macroscopic process behavior. Especially the development of preparative chromatography processes is challenged by the increasing structural complexity of novel antibody formats and accelerated development timelines. This study introduces a multiscale in silico model consisting of homology modeling, quantitative structure-property relationships (QSPR), and mechanistic chromatography modeling leading from the amino acid sequence of a mAb to the digital representation of its cation exchange chromatography (CEX) process. The model leverages the mAbs' structural characteristics and experimental data of a diverse set of 21 therapeutic antibodies to predict elution profiles of two mAbs that were removed from the training data set. QSPR modeling identified mAb-specific protein descriptors relevant for the prediction of the thermodynamic equilibrium and the stoichiometric coefficient of the adsorption reaction. The consideration of two discrete conformational states of IgG4 mAbs enabled prediction of split-peak elution profiles. Starting from the sequence, the presented multiscale model allows in silico development of chromatography processes before protein material is available for experimental studies.

Statistical proofs of the interdependence between nearest neighbor effects on polypeptide backbone conformations

Backbone dihedral angles ϕ and ψ are the main structural descriptors of proteins and peptides. The distribution of these angles has been investigated over decades as they are essential for the validation and refinement of experimental measurements, as well as for structure prediction and design methods. The dependence of these distributions, not only on the nature of each amino acid but also on that of the closest neighbors, has been the subject of numerous studies. Although neighbor-dependent distributions are nowadays generally accepted as a good model, there is still some controversy about the combined effects of left and right neighbors. We have investigated this question using rigorous methods based on recently-developed statistical techniques. Our results unambiguously demonstrate that the influence of left and right neighbors cannot be considered independently. Consequently, three-residue fragments should be considered as the minimal building blocks to investigate polypeptide sequence-structure relationships.

Handcrafted versus non-handcrafted (self-supervised) features for the classification of antimicrobial peptides: complementary or redundant?

Antimicrobial peptides (AMPs) have received a great deal of attention given their potential to become a plausible option to fight multi-drug resistant bacteria as well as other pathogens. Quantitative sequence-activity models (QSAMs) have been helpful to discover new AMPs because they allow to explore a large universe of peptide sequences and help reduce the number of wet lab experiments. A main aspect in the building of QSAMs based on shallow learning is to determine an optimal set of protein descriptors (features) required to discriminate between sequences with different antimicrobial activities. These features are generally handcrafted from peptide sequence datasets that are labeled with specific antimicrobial activities. However, recent developments have shown that unsupervised approaches can be used to determine features that outperform human-engineered (handcrafted) features. Thus, knowing which of these two approaches contribute to a better classification of AMPs, it is a fundamental question in order to design more accurate models. Here, we present a systematic and rigorous study to compare both types of features. Experimental outcomes show that non-handcrafted features lead to achieve better performances than handcrafted features. However, the experiments also prove that an improvement in performance is achieved when both types of features are merged. A relevance analysis reveals that non-handcrafted features have higher information content than handcrafted features, while an interaction-based importance analysis reveals that handcrafted features are more important. These findings suggest that there is complementarity between both types of features. Comparisons regarding state-of-the-art deep models show that shallow models yield better performances both when fed with non-handcrafted features alone and when fed with non-handcrafted and handcrafted features together.

Fuzzy spherical truncation-based multi-linear protein descriptors: From their definition to application in structural-related predictions.

This study introduces a set of fuzzy spherically truncated three-dimensional (3D) multi-linear descriptors for proteins. These indices codify geometric structural information from kth spherically truncated spatial-(dis)similarity two-tuple and three-tuple tensors. The coefficients of these truncated tensors are calculated by applying a smoothing value to the 3D structural encoding based on the relationships between two and three amino acids of a protein embedded into a sphere. At considering, the geometrical center of the protein matches with center of the sphere, the distance between each amino acid involved in any specific interaction and the geometrical center of the protein can be computed. Then, the fuzzy membership degree of each amino acid from an spherical region of interest is computed by fuzzy membership functions (FMFs). The truncation value is finally a combination of the membership degrees from interacting amino acids, by applying the arithmetic mean as fusion rule. Several fuzzy membership functions with diverse biases on the calculation of amino acids memberships (e.g., Z-shaped (close to the center), PI-shaped (middle region), and A-Gaussian (far from the center)) were considered as well as traditional truncation functions (e.g., Switching). Such truncation functions were comparatively evaluated by exploring: 1) the frequency of membership degrees, 2) the variability and orthogonality analyses among them based on the Shannon Entropy’s and Principal Component’s methods, respectively, and 3) the prediction performance of alignment-free prediction of protein folding rates and structural classes. These analyses unraveled the singularity of the proposed fuzzy spherically truncated MDs with respect to the classical (non-truncated) ones and respect to the MDs truncated with traditional functions. They also showed an improved prediction power by attaining an external correlation coefficient of 95.82% in the folding rate modelling and an accuracy of 100% in distinguishing structural protein classes. These outcomes are better than the ones attained by existing approaches, justifying the theoretical contribution of this report. Thus, the fuzzy spherically truncated-based protein descriptors from MuLiMs-MCoMPAs (http://tomocomd.com/mulims-mcompas) are promising alignment-free predictors for modeling protein functions and properties.

DRDB: A Machine Learning Platform to Predict Chemical-Protein Interactions towards Diabetic Retinopathy.

Diabetic retinopathy (DR), a diabetic microangiopathy caused by diabetes, affects approximately 93 million people, worldwide. However, the drugs used to treat DR have limited efficacy and the variety of side effects. This is possibly because the complicated pathogenesis of DR is associated with multiple proteins. In this work, we attempted to identify potential drugs against DR-associated proteins and predict potential targets for drugs using in silico prediction of chemical-protein interactions (CPI) based on multitarget quantitative structure-activity relationship (mt-QSAR) method. Therefore, we developed 128 binary classifiers to predict the CPI for 15 DR targets using random forest (RF), k-nearest neighbours (KNN), support vector machine (SVM), and neural network (NN) algorithms with MACCS, extended connectivity fingerprints (ECFP6) fingerprints, and protein descriptors. In order to facilitate discovery of the novel drugs and target identification using the 128 binary classifiers, a free web server (DRDB) was developed. Compound Danshen Dripping Pills (CDDP), composed of Salvia miltiorrhiza, Panax notoginseng, and borneol, is commonly used in the treatment of cardiovascular diseases. To explore the applicability of DRDB, the potential CPIs of CDDP in treatment of DR were investigated based on DRDB. In vitro experimental validation demonstrated that cryptotanshinone and protocatechuic acid, two key components of CDDP, are capable of targeting ICAM-1 which is one of the key target of DR. We hope that this work can facilitate development of more effective clinical strategies for the treatment of DR.

On the Frustration to Predict Binding Affinities from Protein-Ligand Structures with Deep Neural Networks.

Accurate prediction of binding affinities from protein-ligand atomic coordinates remains a major challenge in early stages of drug discovery. Using modular message passing graph neural networks describing both the ligand and the protein in their free and bound states, we unambiguously evidence that an explicit description of protein-ligand noncovalent interactions does not provide any advantage with respect to ligand or protein descriptors. Simple models, inferring binding affinities of test samples from that of the closest ligands or proteins in the training set, already exhibit good performances, suggesting that memorization largely dominates true learning in the deep neural networks. The current study suggests considering only noncovalent interactions while omitting their protein and ligand atomic environments. Removing all hidden biases probably requires much denser protein-ligand training matrices and a coordinated effort of the drug design community to solve the necessary protein-ligand structures.

Proteochemometrics modeling for prediction of the interactions between caspase isoforms and their inhibitors.

Caspases (cysteine-aspartic proteases) play critical roles in inflammation and the programming of cell death in the form of necroptosis, apoptosis, and pyroptosis. The name of these enzymes has been chosen in accordance with their cysteine protease activity. They act as cysteines in nucleophilically active sites to attack and cleave target proteins in the aspartic acid and amino acid C-terminal. Based on the substrate's structure and the specificity, the physiological activity of caspases is divided. However, in apoptosis, the division of caspases into initiating caspases (caspase 2, 8, 9, and 10) and executive caspases (caspase 3, 6, and 7) is essential. The present study aimed to perform Proteochemometrics Modeling to generalize the data on caspases, which could predict ligand and protein interactions. In this study, we employed protein and ligand descriptors. Moreover, protein descriptors were computed using the Protr R package, while PADEL-Descriptor was employed for the computation of ligand descriptors. In addition, NCA (Neighborhood Component Analyses) was used for descriptor selection, and SVR, decision tree, and ensemble methods were utilized for the proteochemometrics modeling. This study shows that the ensemble model demonstrates superior performance compared with other models in terms of R2, Q2, and RMSE criteria.

Machine learning based predictive model for the analysis of sequence activity relationships using protein spectra and protein descriptors.

Accurately establishing the connection between a protein sequence and its function remains a focal point within the field of protein engineering, especially in the context of predicting the effects of mutations. From this, there has been a continued drive to build accurate and reliable predictive models via machine learning that allow for the virtual screening of many protein mutant sequences, measuring the relationship between sequence and 'fitness' or 'activity', commonly known as a Sequence-Activity-Relationship (SAR). An important preliminary stage in the building of these predictive models is the encoding of the chosen sequences. Evaluated in this work is a plethora of encoding strategies using the Amino Acid Index database, where the indices are transformed into their spectral form via Digital Signal Processing (DSP) techniques, as well as numerous protein structural and physiochemical descriptors. The encoding strategies are explored on a dataset curated to measure the thermostability of various mutants from a recombination library, designed from parental cytochrome P450s. In this work it was concluded that the implementation of protein spectra in concatenation with protein descriptors, together with the Partial Least Squares Regression (PLS) algorithm, gave the most noteworthy increase in the quality of the predictive models (as described in Encoding Strategy C), highlighting their utility in identifying an SAR. The accompanying software produced for this paper is termed pySAR (Python Sequence-Activity-Relationship), which allows for a user to find the optimal arrangement of structural and or physiochemical properties to encode their specific mutant library dataset; the source code is available at: https://github.com/amckenna41/pySAR.

In-silico screening of potential target transporters for glycyrrhetinic acid (GA) via deep learning prediction of drug-target interactions

Glycyrrhetinic acid (GA) is one of the major bioactive components of the leguminous plant Glycyrrhiza spp. (Chinese licorice). The mechanism by which GA is transported within or out of cells remains completely unknown. Given the fact that living organisms harbor thousands of membrane transporters, experimental verification of membrane transporters for specific GA transporters is both laborious and time consuming. In this study, we carried out virtual screening of membrane transporters to predict their probability of binding with GA. Our mining strategy relied on deep learning prediction of drug-target interactions (DTI) combined with molecular docking. We used combinations of drug and protein descriptors to create 12 deep learning models to compare the performance of each descriptor followed by the evaluation of predictions via molecular docking scores. The ABC transporter BPT1p was predicted as a target that achieved the highest docking score among all tested proteins (−10.9 kcal/mol). Additionally, the models predictions of ABC transporters such as NPC1, MRP1, MRP3, NPC1L1, ABCA3 and PDR11, which have similar substrates reflect the ability of the models to learn the sequence features associated with similar compound molecules. We conclude that, our mining method was an effective approach for predicting membrane transporter substrates.

Deep Learning Model for Protein Disease Classification

Background: Protein sequence analysis helps in the prediction of protein functions. As the number of proteins increases, it gives the bioinformaticians a challenge to analyze and study the similarity between them. Most of the existing protein analysis methods use Support Vector Machine. Deep learning did not receive much attention regarding protein analysis as it is noted that little work focused on studying the protein diseases classification. Objective: The contribution of this paper is to present a deep learning approach that classifies protein diseases based on protein descriptors. Methods: Different protein descriptors are used and decomposed into modified feature descriptors. Uniquely, we introduce using the Convolutional Neural Network model to learn and classify protein diseases. The modified feature descriptors are fed to the Convolutional Neural Network model on a dataset of 1563 protein sequences classified into 3 different disease classes: AIDS, Tumor suppressor, and Proto-oncogene. Results: The usage of the modified feature descriptors shows a significant increase in the performance of the Convolutional Neural Network model over Support Vector Machine using different kernel functions. One modified feature descriptor improved by 19.8%, 27.9%, 17.6%, 21.5%, 17.3%, and 22% for evaluation metrics: Area Under the Curve, Matthews Correlation Coefficient, Accuracy, F1-score, Recall, and Precision, respectively. Conclusion: Results show that the prediction of the proposed CNN model trained by modified feature descriptors significantly surpasses that of Support Vector Machine model.