Artificial neural network models for prediction of intestinal permeability of oligopeptides

Predicting Peptide Permeability Across Diverse Barriers: A Systematic Investigation

Peptide-based therapeutics hold immense promise for the treatment of various diseases. However, their effectiveness is often hampered by poor cell membrane permeability, hindering targeted intracellular delivery and oral drug development. This study addressed this challenge by introducing a novel graph neural network (GNN) framework and advanced machine learning algorithms to build predictive models for peptide permeability. Our models offer systematic evaluation across diverse peptides (natural, modified, linear and cyclic) and cell lines [Caco-2, Ralph Russ canine kidney (RRCK) and parallel artificial membrane permeability assay (PAMPA)]. The predictive models for linear and cyclic peptides in Caco-2 and RRCK cell lines were constructed for the first time, with an impressive coefficient of determination (R2) of 0.708, 0.484, 0.553, and 0.528 in the test set, respectively. Notably, the GNN framework behaved better in permeability prediction with larger data sets and improved the accuracy of cyclic peptide prediction in the PAMPA cell line. The R2 increased by about 0.32 compared with the reported models. Furthermore, the important molecular structural features that contribute to good permeability were interpreted; the influence of cell lines, peptide modification, and cyclization on permeability were successfully revealed. To facilitate broader use, we deployed these models on the user-friendly KNIME platform (https://github.com/ifyoungnet/PharmPapp). This work provides a rapid and reliable strategy for systematically assessing peptide permeability, aiding researchers in drug delivery optimization, peptide preselection during drug discovery, and potentially the design of targeted peptide-based materials.

ANN multi-layer perceptron for prediction of blood-brain barrier permeable compounds for central nervous system therapeutics

Endothelial cells produce a semipermeable barrier known as the blood-brain barrier (BBB) to keep undesired chemicals out of the central nervous system (CNS). However, this barrier also restricts the exploration of potential new medications due to insufficient exposure. To address this challenge, machine learning (ML) algorithms can be useful to predict the BBB permeability of chemical compounds. Support vector machines, continuous neural networks, and deep learning approaches have been used to identify compounds that can penetrate the BBB. However, predicting BBB permeability based solely on chemical structure can be difficult. In the current research, we developed an ML model using a large dataset to predict BBB permeability, which could be used for early-stage drug screening of potential CNS medications. Our artificial neural network ANN algorithm exhibited an accuracy of 0.94, specificity of 0.83, sensitivity of 0.97, AUC of 0.96, and MCC of 0.83. These metrics suggest that our model has a high accuracy rate in predicting BBB permeability and therefore has the potential to advance drug discovery efforts in the CNS. This study's outcomes demonstrate the potential for ML models to predict BBB permeability accurately, aiding in the identification of new CNS therapeutic options.Communicated by Ramaswamy H. Sarma.

A machine learning-based quantitative model (LogBB_Pred) to predict the blood-brain barrier permeability (logBB value) of drug compounds

MOTIVATION

Efficient assessment of the blood-brain barrier (BBB) penetration ability of a drug compound is one of the major hurdles in central nervous system drug discovery since experimental methods are costly and time-consuming. To advance and elevate the success rate of neurotherapeutic drug discovery, it is essential to develop an accurate computational quantitative model to determine the absolute logBB value (a logarithmic ratio of the concentration of a drug in the brain to its concentration in the blood) of a drug candidate.

RESULTS

Here, we developed a quantitative model (LogBB_Pred) capable of predicting a logBB value of a query compound. The model achieved an R2 of 0.61 on an independent test dataset and outperformed other publicly available quantitative models. When compared with the available qualitative (classification) models that only classified whether a compound is BBB-permeable or not, our model achieved the same accuracy (0.85) with the best qualitative model and far-outperformed other qualitative models (accuracies between 0.64 and 0.70). For further evaluation, our model, quantitative models, and the qualitative models were evaluated on a real-world central nervous system drug screening library. Our model showed an accuracy of 0.97 while the other models showed an accuracy in the range of 0.29-0.83. Consequently, our model can accurately classify BBB-permeable compounds as well as predict the absolute logBB values of drug candidates.

AVAILABILITY AND IMPLEMENTATION

Web server is freely available on the web at http://ssbio.cau.ac.kr/software/logbb_pred/. The data used in this study are available to download at http://ssbio.cau.ac.kr/software/logbb_pred/dataset.zip.

Stock Portfolio Optimization Using a Combined Approach of Multi Objective Grey Wolf Optimizer and Machine Learning Preselection Methods

The present paper deals with optimizing the stock portfolio of active companies listed on the Tehran Stock Exchange based on the forecast price. This paper is based on a combination of different filtering methods such as optimization of trading rules based on technical analysis (ROC, SMA, EMA, WMA, and MACD at six levels—Very Very Weak (VVW), Very Weak (VW), Weak (W), Strong (S), Very Strong (VS), and Very Very Strong (VVS)), Markov Chains, and Machine Learning (Random Forest and Support Vector Machine) Filter stock exchanges and provide buy signals between 2011 and 2020. In proportion to each combination of filtering methods, a buy signal is issued and based on the mean-variance (M-V) model, the stock portfolio is optimized based on increasing the portfolio return and minimizing the stock portfolio risk. Based on this, out of 480 companies listed on the Tehran Stock Exchange, 85 active companies have been selected and stock portfolio optimization is based on two algorithms, MOGWO and NSGA II. The analysis results show that the use of SVM learning machine leads to minor correlation error than the random forest method. Therefore, this method was used to predict stock prices. Based on the results, it was observed that if the shares of companies are filtered, the risk of transactions decreases, and the return on the stock portfolio increases. Also, if two filtering methods are applied simultaneously, the stock portfolio returns slightly and the risk increases. In the analysis, MOGWO algorithm has obtained 133.13% stock return rate with a risk of 3.346%, while the stock portfolio returns in NSGA II algorithm 107.73, with a risk of 1.459%. Comparison of solution methods shows that the MOGWO algorithm has high efficiency in stock portfolio optimization.

Machine Learning in Drug Discovery: A Review

This review provides the feasible literature on drug discovery through ML tools and techniques that are enforced in every phase of drug development to accelerate the research process and deduce the risk and expenditure in clinical trials. Machine learning techniques improve the decision-making in pharmaceutical data across various applications like QSAR analysis, hit discoveries, de novo drug architectures to retrieve accurate outcomes. Target validation, prognostic biomarkers, digital pathology are considered under problem statements in this review. ML challenges must be applicable for the main cause of inadequacy in interpretability outcomes that may restrict the applications in drug discovery. In clinical trials, absolute and methodological data must be generated to tackle many puzzles in validating ML techniques, improving decision-making, promoting awareness in ML approaches, and deducing risk failures in drug discovery.

LightBBB: computational prediction model of blood-brain-barrier penetration based on LightGBM

MOTIVATION

Identification of blood-brain barrier (BBB) permeability of a compound is a major challenge in neurotherapeutic drug discovery. Conventional approaches for BBB permeability measurement are expensive, time-consuming and labor-intensive. BBB permeability is associated with diverse chemical properties of compounds. However, BBB permeability prediction models have been developed using small datasets and limited features, which are usually not practical due to their low coverage of chemical diversity of compounds. Aim of this study is to develop a BBB permeability prediction model using a large dataset for practical applications. This model can be used for facilitated compound screening in the early stage of brain drug discovery.

RESULTS

A dataset of 7162 compounds with BBB permeability (5453 BBB+ and 1709 BBB-) was compiled from the literature, where BBB+ and BBB- denote BBB-permeable and non-permeable compounds, respectively. We trained a machine learning model based on Light Gradient Boosting Machine (LightGBM) algorithm and achieved an overall accuracy of 89%, an area under the curve (AUC) of 0.93, specificity of 0.77 and sensitivity of 0.93, when 10-fold cross-validation was performed. The model was further evaluated using 74 central nerve system compounds (39 BBB+ and 35 BBB-) obtained from the literature and showed an accuracy of 90%, sensitivity of 0.85 and specificity of 0.94. Our model outperforms over existing BBB permeability prediction models.

AVAILABILITYAND IMPLEMENTATION

The prediction server is available at http://ssbio.cau.ac.kr/software/bbb.

Thermostable Recombinant Polypeptides as the Source of L-Amino Acids for Culture Media

Mutant homologues of small chemotactic and DNA-binding proteins from thermophilic bacteria Thermotoga petrophila RKU-1 and Thermotoga naphthophila were obtained. These proteins can be expressed in the recombinant form in E. coli cells. A wide range of properties and parameters that are important for isolation of these proteins were revealed: stability in a wide temperature and pH range, high level of expression, solubility, and the possibility of using simple purification schemes with low number of successive steps. The positive effect of proteins on in vitro fibroblasts growth was demonstrated. The described properties of the target proteins indicate the possibility of their use in different biotechnology industries as an inexpensive source of L-amino acids.

Improved Prediction of Blood-Brain Barrier Permeability Through Machine Learning with Combined Use of Molecular Property-Based Descriptors and Fingerprints

Blood-brain barrier (BBB) permeability of a compound determines whether the compound can effectively enter the brain. It is an essential property which must be accounted for in drug discovery with a target in the brain. Several computational methods have been used to predict the BBB permeability. In particular, support vector machine (SVM), which is a kernel-based machine learning method, has been used popularly in this field. For SVM training and prediction, the compounds are characterized by molecular descriptors. Some SVM models were based on the use of molecular property-based descriptors (including 1D, 2D, and 3D descriptors) or fragment-based descriptors (known as the fingerprints of a molecule). The selection of descriptors is critical for the performance of a SVM model. In this study, we aimed to develop a generally applicable new SVM model by combining all of the features of the molecular property-based descriptors and fingerprints to improve the accuracy for the BBB permeability prediction. The results indicate that our SVM model has improved accuracy compared to the currently available models of the BBB permeability prediction.

In silico ADME/T modelling for rational drug design

In recent decades, in silico absorption, distribution, metabolism, excretion (ADME), and toxicity (T) modelling as a tool for rational drug design has received considerable attention from pharmaceutical scientists, and various ADME/T-related prediction models have been reported. The high-throughput and low-cost nature of these models permits a more streamlined drug development process in which the identification of hits or their structural optimization can be guided based on a parallel investigation of bioavailability and safety, along with activity. However, the effectiveness of these tools is highly dependent on their capacity to cope with needs at different stages, e.g. their use in candidate selection has been limited due to their lack of the required predictability. For some events or endpoints involving more complex mechanisms, the current in silico approaches still need further improvement. In this review, we will briefly introduce the development of in silico models for some physicochemical parameters, ADME properties and toxicity evaluation, with an emphasis on the modelling approaches thereof, their application in drug discovery, and the potential merits or deficiencies of these models. Finally, the outlook for future ADME/T modelling based on big data analysis and systems sciences will be discussed.

Presep: predicting the propensity of a protein being secreted into the supernatant when expressed in Pichia pastoris

Pichia pastoris is commonly used for the production of recombinant proteins due to its preferential secretion of recombinant proteins, resulting in lower production costs and increased yields of target proteins. However, not all recombinant proteins can be successfully secreted in P. pastoris. A computational method that predicts the likelihood of a protein being secreted into the supernatant would be of considerable value; however, to the best of our knowledge, no such tool has yet been developed. We present a machine-learning approach called Presep to assess the likelihood of a recombinant protein being secreted by P. pastoris based on its pseudo amino acid composition (PseAA). Using a 20-fold cross validation, Presep demonstrated a high degree of accuracy, with Matthews correlation coefficient (MCC) and overall accuracy (Q2) scores of 0.78 and 95%, respectively. Computational results were validated experimentally, with six β-galactosidase genes expressed in P. pastoris strain GS115 to verify Presep model predictions. A strong correlation (R(2) = 0.967) was observed between Presep prediction secretion propensity and the experimental secretion percentage. Together, these results demonstrate the ability of the Presep model for predicting the secretion propensity of P. pastoris for a given protein. This model may serve as a valuable tool for determining the utility of P. pastoris as a host organism prior to initiating biological experiments. The Presep prediction tool can be freely downloaded at http://www.mobioinfor.cn/Presep.

Dexamethasone-releasing cochlear implant coatings: application of artificial neural networks for modelling of formulation parameters and drug release profile

Objectives

Over the past few decades, mathematical modelling and simulation of drug delivery systems has been steadily gained interest as a focus for academic and industrial attention. Here, simulation of dexamethasone (DEX, a corticosteroid anti-inflammatory agent) release profile from drug-eluting cochlear implant coatings is reported using artificial neural networks.

Methods

The devices were fabricated as monolithic dispersions of the pharmaceutically active ingredient in a silicone rubber matrix. A two-phase exponential model was fitted on the experimentally obtained DEX release profiles. An artificial neural network (ANN) was trained to determine formulation parameters (i.e. DEX loading percentage, the devices surface area and their geometry) for a specific experimentally obtained drug release profile. In a reverse strategy, an ANN was trained for determining expected drug release profiles for the same set of formulation parameters.

Key findings

An algorithm was developed by combining the two previously developed ANNs in a serial manner, and this was successfully used for simulating the developed drug-eluting cochlear implant coatings. The models were validated by a leave-one-out method and performing new experiments.

Conclusions

The developed ANN algorithms were capable to bilaterally predict drug release profile for a known set of formulation parameters or find out the levels for input formulation parameters to obtain a desired DEX release profile.

Role of computational methods in pharmaceutical sciences

Over the past two decades computational methods have eased up the financial and experimental burden of early drug discovery process. The in silico methods have provided support in terms of databases, data mining of large genomes, network analysis, systems biology on the bioinformatics front and structure-activity relationship, similarity analysis, docking, and pharmacophore methods for lead design and optimization. This review highlights some of the applications of bioinformatics and chemoinformatics methods that have enriched the field of drug discovery. In addition, the review also provided insights into the use of free energy perturbation methods for efficiently computing binding energy. These in silico methods are complementary and can be easily integrated into the traditional in vitro and in vivo methods to test pharmacological hypothesis.

Machine learning study for the prediction of transdermal peptide

In order to develop a computational method to rapidly evaluate transdermal peptides, we report approaches for predicting the transdermal activity of peptides on the basis of peptide sequence information using Artificial Neural Network (ANN), Partial Least Squares (PLS) and Support Vector Machine (SVM). We identified 269 transdermal peptides by the phage display technique and use them as the positive controls to develop and test machine learning models. Combinations of three descriptors with neural network architectures, the number of latent variables and the kernel functions are tried in training to make appropriate predictions. The capacity of models is evaluated by means of statistical indicators including sensitivity, specificity, and the area under the receiver operating characteristic curve (ROC score). In the ROC score-based comparison, three methods proved capable of providing a reasonable prediction of transdermal peptide. The best result is obtained by SVM model with a radial basis function and VHSE descriptors. The results indicate that it is possible to discriminate between transdermal peptides and random sequences using our models. We anticipate that our models will be applicable to prediction of transdermal peptide for large peptide database for facilitating efficient transdermal drug delivery through intact skin.

Estimation of ADME properties with substructure pattern recognition

Over the past decade, absorption, distribution, metabolism, and excretion (ADME) property evaluation has become one of the most important issues in the process of drug discovery and development. Since in vivo and in vitro evaluations are costly and laborious, in silico techniques had been widely used to estimate ADME properties of chemical compounds. Traditional prediction methods usually try to build a functional relationship between a set of molecular descriptors and a given ADME property. Although traditional methods have been successfully used in many cases, the accuracy and efficiency of molecular descriptors must be concerned. Herein, we report a new classification method based on substructure pattern recognition, in which each molecule is represented as a substructure pattern fingerprint based on a predefined substructure dictionary, and then a support vector machine (SVM) algorithm is applied to build the prediction model. Therefore, a direct connection between substructures and molecular properties is built. The most important substructure patterns can be identified via the information gain analysis, which could help to interpret the models from a medicinal chemistry perspective. Afterward, this method was verified with two data sets, one for blood-brain barrier (BBB) penetration and the other for human intestinal absorption (HIA). The results demonstrated that the overall predictive accuracies of the best HIA model for the training and test sets were 98.5 and 98.8%, and the overall predictive accuracies of the best BBB model for the training and test sets were 98.8 and 98.4%, which confirmed the reliability of our method. In the additional validations, the predictive accuracies were 94 and 69.5% for the HIA and the BBB models, respectively. Moreover, some of the representative key substructure patterns which significantly correlated with the HIA and BBB penetration properties were also presented.

The use of machine learning and nonlinear statistical tools for ADME prediction

Absorption, distribution, metabolism and excretion (ADME)-related failure of drug candidates is a major issue for the pharmaceutical industry today. Prediction of ADME by in silico tools has now become an inevitable paradigm to reduce cost and enhance efficiency in pharmaceutical research. Recently, machine learning as well as nonlinear statistical tools has been widely applied to predict routine ADME end points. To achieve accurate and reliable predictions, it would be a prerequisite to understand the concepts, mechanisms and limitations of these tools. Here, we have devised a small synthetic nonlinear data set to help understand the mechanism of machine learning by 2D-visualisation. We applied six new machine learning methods to four different data sets. The methods include Naive Bayes classifier, classification and regression tree, random forest, Gaussian process, support vector machine and k nearest neighbour. The results demonstrated that ensemble learning and kernel machine displayed greater accuracy of prediction than classical methods irrespective of the data set size. The importance of interaction with the engineering field is also addressed. The results described here provide insights into the mechanism of machine learning, which will enable appropriate usage in the future.

Troubleshooting computational methods in drug discovery

Computational approaches for drug discovery such as ligand-based and structure-based methods, are increasingly seen as an efficient approach for lead discovery as well as providing insights on absorption, distribution, metabolism, excretion and toxicity (ADME/Tox). What is perhaps less well known and widely described are the limitations of the different technologies. We have therefore presented a troubleshooting approach to QSAR, homology modeling, docking as well as hybrid methods. If such computational or cheminformatics methods are to become more widely used by non-experts it is critical that such limitations are brought to the user's attention and addressed during their workflows. This could improve the quality of the models and results that are obtained.

Prediction of amyloid fibril-forming segments based on a support vector machine

BACKGROUND

Amyloid fibrillar aggregates of proteins or polypeptides are known to be associated with many human diseases. Recent studies suggest that short protein regions trigger this aggregation. Thus, identifying these short peptides is critical for understanding diseases and finding potential therapeutic targets.

RESULTS

We propose a method, named Pafig (Prediction of amyloid fibril-forming segments) based on support vector machines, to identify the hexpeptides associated with amyloid fibrillar aggregates. The features of Pafig were obtained by a two-round selection from AAindex. Using a 10-fold cross validation test on Hexpepset dataset, Pafig performed well with regards to overall accuracy of 81% and Matthews correlation coefficient of 0.63. Pafig was used to predict the potential fibril-forming hexpeptides in all of the 64,000,000 hexpeptides. As a result, approximately 5.08% of hexpeptides showed a high aggregation propensity. In the predicted fibril-forming hexpeptides, the amino acids--alanine, phenylalanine, isoleucine, leucine and valine occurred at the higher frequencies and the amino acids--aspartic acid, glutamic acid, histidine, lysine, arginine and praline, appeared with lower frequencies.

CONCLUSION

The performance of Pafig indicates that it is a powerful tool for identifying the hexpeptides associated with fibrillar aggregates and will be useful for large-scale analysis of proteomic data.