Investigating pharmacokinetic profiles of Centella asiatica using machine learning and PBPK modelling.

Physiologically based pharmacokinetic (PBPK) modeling serves as a valuable tool for determining the distribution and disposition of substances in the body of an organism. It involves a mathematical representation of the interrelationships among crucial physiological, biochemical, and physicochemical parameters. A lack of the values of pharmacokinetic parameters can be challenging in constructing a PBPK model. Herein, we propose an artificial intelligence framework to evaluate a key pharmacokinetic parameter, the intestinal effective permeability (Peff). The publicly available Peff dataset was utilized to develop regression machine learning models. The XGBoost model demonstrates the best test accuracy of R-squared (R2, coefficient of determination) of 0.68. The model is then applied to compute the Peff of asiaticoside and madecassoside, the parent compounds found in Centella asiatica. Subsequently, PBPK modeling was conducted to evaluate the biodistribution of the herbal substances following oral administration in a rat model. The simulation results were evaluated and validated, which agreed with the existing in vivo studies in rats. This in silico pipeline presents a potential approach for investigating the pharmacokinetic parameters and profiles of drugs or herbal substances, which can be used independently or integrated into other modeling systems.

Combining Deep Learning and Structural Modeling to Identify Potential Acetylcholinesterase Inhibitors from Hericium erinaceus.

Alzheimer's disease (AD) is the most common type of dementia, affecting over 50 million people worldwide. Currently, most approved medications for AD inhibit the activity of acetylcholinesterase (AChE), but these treatments often come with harmful side effects. There is growing interest in the use of natural compounds for disease prevention, alleviation, and treatment. This trend is driven by the anticipation that these substances may incur fewer side effects than existing medications. This research presents a computational approach combining machine learning with structural modeling to discover compounds from medicinal mushrooms with a high potential to inhibit the activity of AChE. First, we developed a deep neural network capable of rapidly screening a vast number of compounds to indicate their potential to inhibit AChE activity. Subsequently, we applied deep learning models to screen the compounds in the BACMUSHBASE database, which catalogs the bioactive compounds from cultivated and wild mushroom varieties local to Thailand, resulting in the identification of five promising compounds. Next, the five identified compounds underwent molecular docking techniques to calculate the binding energy between the compounds and AChE. This allowed us to refine the selection to two compounds, erinacerin A and hericenone B. Further analysis of the binding energy patterns between these compounds and the target protein revealed that both compounds displayed binding energy profiles similar to the combined characteristics of donepezil and galanthamine, the prescription drugs for AD. We propose that these two compounds, derived from Hericium erinaceus (also known as lion's mane mushroom), are suitable candidates for further research and development into symptom-alleviating AD medications.

Light-Exposed Metabolic Responses of Cordyceps militaris through Transcriptome-Integrated Genome-Scale Modeling.

The genome-scale metabolic model (GSMM) of Cordyceps militaris provides a comprehensive basis of carbon assimilation for cell growth and metabolite production. However, the model with a simple mass balance concept shows limited capability to probe the metabolic responses of C. militaris under light exposure. This study, therefore, employed the transcriptome-integrated GSMM approach to extend the investigation of C. militaris's metabolism under light conditions. Through the gene inactivity moderated by metabolism and expression (GIMME) framework, the iPS1474-tiGSMM model was furnished with the transcriptome data, thus providing a simulation that described reasonably well the metabolic responses underlying the phenotypic observation of C. militaris under the particular light conditions. The iPS1474-tiGSMM obviously showed an improved prediction of metabolic fluxes in correlation with the expressed genes involved in the cordycepin and carotenoid biosynthetic pathways under the sucrose culturing conditions. Further analysis of reporter metabolites suggested that the central carbon, purine, and fatty acid metabolisms towards carotenoid biosynthesis were the predominant metabolic processes responsible in light conditions. This finding highlights the key responsive processes enabling the acclimatization of C. militaris metabolism in varying light conditions. This study provides a valuable perspective on manipulating metabolic genes and fluxes towards the target metabolite production of C. militaris.

Interpreting drug synergy in breast cancer with deep learning using target-protein inhibition profiles.

BACKGROUND: Breast cancer is the most common malignancy among women worldwide. Despite advances in treating breast cancer over the past decades, drug resistance and adverse effects remain challenging. Recent therapeutic progress has shifted toward using drug combinations for better treatment efficiency. However, with a growing number of potential small-molecule cancer inhibitors, in silico strategies to predict pharmacological synergy before experimental trials are required to compensate for time and cost restrictions. Many deep learning models have been previously proposed to predict the synergistic effects of drug combinations with high performance. However, these models heavily relied on a large number of drug chemical structural fingerprints as their main features, which made model interpretation a challenge. RESULTS: This study developed a deep neural network model that predicts synergy between small-molecule pairs based on their inhibitory activities against 13 selected key proteins. The synergy prediction model achieved a Pearson correlation coefficient between model predictions and experimental data of 0.63 across five breast cancer cell lines. BT-549 and MCF-7 achieved the highest correlation of 0.67 when considering individual cell lines. Despite achieving a moderate correlation compared to previous deep learning models, our model offers a distinctive advantage in terms of interpretability. Using the inhibitory activities against key protein targets as the main features allowed a straightforward interpretation of the model since the individual features had direct biological meaning. By tracing the synergistic interactions of compounds through their target proteins, we gained insights into the patterns our model recognized as indicative of synergistic effects. CONCLUSIONS: The framework employed in the present study lays the groundwork for future advancements, especially in model interpretation. By combining deep learning techniques and target-specific models, this study shed light on potential patterns of target-protein inhibition profiles that could be exploited in breast cancer treatment.

Boolean modeling of breast cancer signaling pathways uncovers mechanisms of drug synergy.

Breast cancer is one of the most common types of cancer in females. While drug combinations have shown potential in breast cancer treatments, identifying new effective drug pairs is challenging due to the vast number of possible combinations among available compounds. Efforts have been made to accelerate the process with in silico predictions. Here, we developed a Boolean model of signaling pathways in breast cancer. The model was tailored to represent five breast cancer cell lines by integrating information about cell-line specific mutations, gene expression, and drug treatments. The models reproduced cell-line specific protein activities and drug-response behaviors in agreement with experimental data. Next, we proposed a calculation of protein synergy scores (PSSs), determining the effect of drug combinations on individual proteins' activities. The PSSs of selected proteins were used to investigate the synergistic effects of 150 drug combinations across five cancer cell lines. The comparison of the highest single agent (HSA) synergy scores between experiments and model predictions from the MDA-MB-231 cell line achieved the highest Pearson's correlation coefficient of 0.58 with a great balance among the classification metrics (AUC = 0.74, sensitivity = 0.63, and specificity = 0.64). Finally, we clustered drug pairs into groups based on the selected PSSs to gain further insights into the mechanisms underlying the observed synergistic effects of drug pairs. Clustering analysis allowed us to identify distinct patterns in the protein activities that correspond to five different modes of synergy: 1) synergistic activation of FADD and BID (extrinsic apoptosis pathway), 2) synergistic inhibition of BCL2 (intrinsic apoptosis pathway), 3) synergistic inhibition of MTORC1, 4) synergistic inhibition of ESR1, and 5) synergistic inhibition of CYCLIN D. Our approach offers a mechanistic understanding of the efficacy of drug combinations and provides direction for selecting potential drug pairs worthy of further laboratory investigation.

Combined Deep Learning and Molecular Modeling Techniques on the Virtual Screening of New mTOR Inhibitors from the Thai Mushroom Database.

The mammalian target of rapamycin (mTOR) is a protein kinase of the PI3K/Akt signaling pathway that regulates cell growth and division and is an attractive target for cancer therapy. Many reports on finding alternative mTOR inhibitors available in a database contain a mixture of active compound data with different mechanisms, which results in an increased complexity for training the machine learning models based on the chemical features of active compounds. In this study, a deep learning model supported by principal component analysis (PCA) and structural methods was used to search for an alternative mTOR inhibitor from mushrooms. The mTORC1 active compound data set from the PubChem database was first filtered for only the compounds resided near the first-generation inhibitors (rapalogs) within the first two PCA coordinates of chemical features. A deep learning model trained by the filtered data set captured the main characteristics of rapalogs and displayed the importance of steroid cores. After that, another layer of virtual screening by molecular docking calculations was performed on ternary complexes of FKBP12-FRB domains and six compound candidates with high "active" probability scores predicted by the deep learning models. Finally, all-atom molecular dynamics simulations and MMPBSA binding energy analysis were performed on two selected candidates in comparison to rapamycin, which confirmed the importance of ring groups and steroid cores for interaction networks. Trihydroxysterol from Lentinus polychrous Lev. was predicted as an interesting candidate due to the small but effective interaction network that facilitated FKBP12-FRB interactions and further stabilized the ternary complex.

A continuous-time stochastic Boolean model provides a quantitative description of the budding yeast cell cycle.

The cell division cycle is regulated by a complex network of interacting genes and proteins. The control system has been modeled in many ways, from qualitative Boolean switching-networks to quantitative differential equations and highly detailed stochastic simulations. Here we develop a continuous-time stochastic model using seven Boolean variables to represent the activities of major regulators of the budding yeast cell cycle plus one continuous variable representing cell growth. The Boolean variables are updated asynchronously by logical rules based on known biochemistry of the cell-cycle control system using Gillespie's stochastic simulation algorithm. Time and cell size are updated continuously. By simulating a population of yeast cells, we calculate statistical properties of cell cycle progression that can be compared directly to experimental measurements. Perturbations of the normal sequence of events indicate that the cell cycle is 91% robust to random 'flips' of the Boolean variables, but 9% of the perturbations induce lethal mistakes in cell cycle progression. This simple, hybrid Boolean model gives a good account of the growth and division of budding yeast cells, suggesting that this modeling approach may be as accurate as detailed reaction-kinetic modeling with considerably less demands on estimating rate constants.

mSRFR: a machine learning model using microalgal signature features for ncRNA classification.

This work presents mSRFR (microalgae SMOTE Random Forest Relief model), a classification tool for noncoding RNAs (ncRNAs) in microalgae, including green algae, diatoms, golden algae, and cyanobacteria. First, the SMOTE technique was applied to address the challenge of imbalanced data due to the different numbers of microalgae ncRNAs from different species in the EBI RNA-central database. Then the top 20 significant features from a total of 106 features, including sequence-based, secondary structure, base-pair, and triplet sequence-structure features, were selected using the Relief feature selection method. Next, ten-fold cross-validation was applied to choose a classifier algorithm with the highest performance among Support Vector Machine, Random Forest, Decision Tree, Naïve Bayes, K-nearest Neighbor, and Neural Network, based on the receiver operating characteristic (ROC) area. The results showed that the Random Forest classifier achieved the highest ROC area of 0.992. Then, the Random Forest algorithm was selected and compared with other tools, including RNAcon, CPC, CPC2, CNCI, and CPPred. Our model achieved a high accuracy of about 97% and a low false-positive rate of about 2% in predicting the test dataset of microalgae. Furthermore, the top features from Relief revealed that the %GA dinucleotide is a signature feature of microalgal ncRNAs when compared to Escherichia coli, Saccharomyces cerevisiae, Arabidopsis thaliana, and Homo sapiens.

Construction of Light-Responsive Gene Regulatory Network for Growth, Development and Secondary Metabolite Production in Cordyceps militaris.

Cordyceps militaris is an edible fungus that produces many beneficial compounds, including cordycepin and carotenoid. In many fungi, growth, development and secondary metabolite production are controlled by crosstalk between light-signaling pathways and other regulatory cascades. However, little is known about the gene regulation upon light exposure in C. militaris. This study aims to construct a gene regulatory network (GRN) that responds to light in C. militaris. First, a genome-scale GRN was built based on transcription factor (TF)-target gene interactions predicted from the Regulatory Sequence Analysis Tools (RSAT). Then, a light-responsive GRN was extracted by integrating the transcriptomic data onto the genome-scale GRN. The light-responsive network contains 2689 genes and 6837 interactions. From the network, five TFs, Snf21 (CCM_04586), an AT-hook DNA-binding motif TF (CCM_08536), a homeobox TF (CCM_07504), a forkhead box protein L2 (CCM_02646) and a heat shock factor Hsf1 (CCM_05142), were identified as key regulators that co-regulate a large group of growth and developmental genes. The identified regulatory network and expression profiles from our analysis suggested how light may induce the growth and development of C. militaris into a sexual cycle. The light-mediated regulation also couples fungal development with cordycepin and carotenoid production. This study leads to an enhanced understanding of the light-responsive regulation of growth, development and secondary metabolite production in the fungi.

PhotoModPlus: A web server for photosynthetic protein prediction from genome neighborhood features.

A new web server called PhotoModPlus is presented as a platform for predicting photosynthetic proteins via genome neighborhood networks (GNN) and genome neighborhood-based machine learning. GNN enables users to visualize the overview of the conserved neighboring genes from multiple photosynthetic prokaryotic genomes and provides functional guidance on the query input. In the platform, we also present a new machine learning model utilizing genome neighborhood features for predicting photosynthesis-specific functions based on 24 prokaryotic photosynthesis-related GO terms, namely PhotoModGO. The new model performed better than the sequence-based approaches with an F1 measure of 0.872, based on nested five-fold cross-validation. Finally, we demonstrated the applications of the webserver and the new model in the identification of novel photosynthetic proteins. The server is user-friendly, compatible with all devices, and available at bicep.kmutt.ac.th/photomod.

A model of infection in honeybee colonies with social immunity.

Honeybees (Apis mellifera) play a significant role in the pollination of various food crops and plants. In the past decades, honeybee management has been challenged with increased pathogen and environmental pressure associating with increased beekeeping costs, having a marked economic impact on the beekeeping industry. Pathogens have been identified as a contributing cause of colony losses. Evidence suggested a possible route of pathogen transmission among bees via oral-oral contacts through trophallaxis. Here we propose a model that describes the transmission of an infection within a colony when bee members engage in the trophallactic activity to distribute nectar. In addition, we examine two important features of social immunity, defined as collective disease defenses organized by honeybee society. First, our model considers the social segregation of worker bees. The segregation limits foragers, which are highly exposed to pathogens during foraging outside the nest, from interacting with bees residing in the inner parts of the nest. Second, our model includes a hygienic response, by which healthy nurse bees exterminate infected bees to mitigate horizontal transmission of the infection to other bee members. We propose that the social segregation forms the first line of defense in reducing the uptake of pathogens into the colony. If the first line of defense fails, the hygienic behavior provides a second mechanism in preventing disease spread. Our study identifies the rate of egg-laying as a critical factor in maintaining the colony's health against an infection. We propose that winter conditions which cease or reduce the egg-laying activity combined with an infection in early spring can compromise the social immunity defenses and potentially cause colony losses.

Photosynthetic protein classification using genome neighborhood-based machine learning feature.

Identification of novel photosynthetic proteins is important for understanding and improving photosynthetic efficiency. Synergistically, genome neighborhood can provide additional useful information to identify photosynthetic proteins. We, therefore, expected that applying a computational approach, particularly machine learning (ML) with the genome neighborhood-based feature should facilitate the photosynthetic function assignment. Our results revealed a functional relationship between photosynthetic genes and their conserved neighboring genes observed by 'Phylo score', indicating their functions could be inferred from the genome neighborhood profile. Therefore, we created a new method for extracting patterns based on the genome neighborhood network (GNN) and applied them for the photosynthetic protein classification using ML algorithms. Random forest (RF) classifier using genome neighborhood-based features achieved the highest accuracy up to 87% in the classification of photosynthetic proteins and also showed better performance (Mathew's correlation coefficient = 0.718) than other available tools including the sequence similarity search (0.447) and ML-based method (0.361). Furthermore, we demonstrated the ability of our model to identify novel photosynthetic proteins compared to the other methods. Our classifier is available at http://bicep2.kmutt.ac.th/photomod_standalone, https://bit.ly/2S0I2Ox and DockerHub: https://hub.docker.com/r/asangphukieo/photomod.

Modeling the dynamic behavior of biochemical regulatory networks.

Strategies for modeling the complex dynamical behavior of gene/protein regulatory networks have evolved over the last 50 years as both the knowledge of these molecular control systems and the power of computing resources have increased. Here, we review a number of common modeling approaches, including Boolean (logical) models, systems of piecewise-linear or fully non-linear ordinary differential equations, and stochastic models (including hybrid deterministic/stochastic approaches). We discuss the pro's and con's of each approach, to help novice modelers choose a modeling strategy suitable to their problem, based on the type and bounty of available experimental information. We illustrate different modeling strategies in terms of some abstract network motifs, and in the specific context of cell cycle regulation.

A Model of Yeast Cell-Cycle Regulation Based on a Standard Component Modeling Strategy for Protein Regulatory Networks.

To understand the molecular mechanisms that regulate cell cycle progression in eukaryotes, a variety of mathematical modeling approaches have been employed, ranging from Boolean networks and differential equations to stochastic simulations. Each approach has its own characteristic strengths and weaknesses. In this paper, we propose a "standard component" modeling strategy that combines advantageous features of Boolean networks, differential equations and stochastic simulations in a framework that acknowledges the typical sorts of reactions found in protein regulatory networks. Applying this strategy to a comprehensive mechanism of the budding yeast cell cycle, we illustrate the potential value of standard component modeling. The deterministic version of our model reproduces the phenotypic properties of wild-type cells and of 125 mutant strains. The stochastic version of our model reproduces the cell-to-cell variability of wild-type cells and the partial viability of the CLB2-dbΔ clb5Δ mutant strain. Our simulations show that mathematical modeling with "standard components" can capture in quantitative detail many essential properties of cell cycle control in budding yeast.

Computational Design of Hypothetical New Peptides Based on a Cyclotide Scaffold as HIV gp120 Inhibitor.

Cyclotides are a family of triple disulfide cyclic peptides with exceptional resistance to thermal/chemical denaturation and enzymatic degradation. Several cyclotides have been shown to possess anti-HIV activity, including kalata B1 (KB1). However, the use of cyclotides as anti-HIV therapies remains limited due to the high toxicity in normal cells. Therefore, grafting anti-HIV epitopes onto a cyclotide might be a promising approach for reducing toxicity and simultaneously improving anti-HIV activity. Viral envelope glycoprotein gp120 is required for entry of HIV into CD4+ T cells. However, due to a high degree of variability and physical shielding, the design of drugs targeting gp120 remains challenging. We created a computational protocol in which molecular modeling techniques were combined with a genetic algorithm (GA) to automate the design of new cyclotides with improved binding to HIV gp120. We found that the group of modified cyclotides has better binding scores (23.1%) compared to the KB1. By using molecular dynamic (MD) simulation as a post filter for the final candidates, we identified two novel cyclotides, GA763 and GA190, which exhibited better interaction energies (36.6% and 22.8%, respectively) when binding to gp120 compared to KB1. This computational design represents an alternative tool for modifying peptides, including cyclotides and other stable peptides, as therapeutic agents before the synthesis process.

From START to FINISH: computational analysis of cell cycle control in budding yeast.

In the cell division cycle of budding yeast, START refers to a set of tightly linked events that prepare a cell for budding and DNA replication, and FINISH denotes the interrelated events by which the cell exits from mitosis and divides into mother and daughter cells. On the basis of recent progress made by molecular biologists in characterizing the genes and proteins that control START and FINISH, we crafted a new mathematical model of cell cycle progression in yeast. Our model exploits a natural separation of time scales in the cell cycle control network to construct a system of differential-algebraic equations for protein synthesis and degradation, post-translational modifications, and rapid formation and dissociation of multimeric complexes. The model provides a unified account of the observed phenotypes of 257 mutant yeast strains (98% of the 263 strains in the data set used to constrain the model). We then use the model to predict the phenotypes of 30 novel combinations of mutant alleles. Our comprehensive model of the molecular events controlling cell cycle progression in budding yeast has both explanatory and predictive power. Future experimental tests of the model's predictions will be useful to refine the underlying molecular mechanism, to constrain the adjustable parameters of the model, and to provide new insights into how the cell division cycle is regulated in budding yeast.

Decision-making in honeybee swarms based on quality and distance information of candidate nest sites.

In the nest-site selection process of honeybee swarms, an individual bee performs a waggle dance to communicate information about direction, quality, and distance of a discovered site to other bees at the swarm. Initially, different groups of bees dance to represent different potential sites, but eventually the swarm usually reaches an agreement for only one site. Here, we model the nest-site selection process in honeybee swarms of Apis mellifera and show how the swarms make adaptive decisions based on a trade-off between the quality and distance to candidate nest sites. We use bifurcation analysis and stochastic simulations to reveal that the swarm's site distance preference is moderate>near>far when the swarms choose between low quality sites. However, the distance preference becomes near>moderate>far when the swarms choose between high quality sites. Our simulations also indicate that swarms with large population size prefer nearer sites and, in addition, are more adaptive at making decisions based on available information compared to swarms with smaller population size.

A stochastic model correctly predicts changes in budding yeast cell cycle dynamics upon periodic expression of CLN2.

In this study, we focus on a recent stochastic budding yeast cell cycle model. First, we estimate the model parameters using extensive data sets: phenotypes of 110 genetic strains, single cell statistics of wild type and cln3 strains. Optimization of stochastic model parameters is achieved by an automated algorithm we recently used for a deterministic cell cycle model. Next, in order to test the predictive ability of the stochastic model, we focus on a recent experimental study in which forced periodic expression of CLN2 cyclin (driven by MET3 promoter in cln3 background) has been used to synchronize budding yeast cell colonies. We demonstrate that the model correctly predicts the experimentally observed synchronization levels and cell cycle statistics of mother and daughter cells under various experimental conditions (numerical data that is not enforced in parameter optimization), in addition to correctly predicting the qualitative changes in size control due to forced CLN2 expression. Our model also generates a novel prediction: under frequent CLN2 expression pulses, G1 phase duration is bimodal among small-born cells. These cells originate from daughters with extended budded periods due to size control during the budded period. This novel prediction and the experimental trends captured by the model illustrate the interplay between cell cycle dynamics, synchronization of cell colonies, and size control in budding yeast.

Optimization and model reduction in the high dimensional parameter space of a budding yeast cell cycle model.

BACKGROUND: Parameter estimation from experimental data is critical for mathematical modeling of protein regulatory networks. For realistic networks with dozens of species and reactions, parameter estimation is an especially challenging task. In this study, we present an approach for parameter estimation that is effective in fitting a model of the budding yeast cell cycle (comprising 26 nonlinear ordinary differential equations containing 126 rate constants) to the experimentally observed phenotypes (viable or inviable) of 119 genetic strains carrying mutations of cell cycle genes. RESULTS: Starting from an initial guess of the parameter values, which correctly captures the phenotypes of only 72 genetic strains, our parameter estimation algorithm quickly improves the success rate of the model to 105-111 of the 119 strains. This success rate is comparable to the best values achieved by a skilled modeler manually choosing parameters over many weeks. The algorithm combines two search and optimization strategies. First, we use Latin hypercube sampling to explore a region surrounding the initial guess. From these samples, we choose ∼20 different sets of parameter values that correctly capture wild type viability. These sets form the starting generation of differential evolution that selects new parameter values that perform better in terms of their success rate in capturing phenotypes. In addition to producing highly successful combinations of parameter values, we analyze the results to determine the parameters that are most critical for matching experimental outcomes and the most competitive strains whose correct outcome with a given parameter vector forces numerous other strains to have incorrect outcomes. These "most critical parameters" and "most competitive strains" provide biological insights into the model. Conversely, the "least critical parameters" and "least competitive strains" suggest ways to reduce the computational complexity of the optimization. CONCLUSIONS: Our approach proves to be a useful tool to help systems biologists fit complex dynamical models to large experimental datasets. In the process of fitting the model to the data, the tool identifies suggestive correlations among aspects of the model and the data.