Advances in computational methods to predict the biological activity of compounds

Stack-HDAC3i: A high-precision identification of HDAC3 inhibitors by exploiting a stacked ensemble-learning framework

Epigenetics involves reversible modifications in gene expression without altering the genetic code itself. Among these modifications, histone deacetylases (HDACs) play a key role by removing acetyl groups from lysine residues on histones. Overexpression of HDACs is linked to the proliferation and survival of tumor cells. To combat this, HDAC inhibitors (HDACi) are commonly used in cancer treatments. However, pan-HDAC inhibition can lead to numerous side effects. Therefore, isoform-selective HDAC inhibitors, such as HDAC3i, could be advantageous for treating various medical conditions while minimizing off-target effects. To date, computational approaches that use only the SMILES notation without any experimental evidence have become increasingly popular and necessary for the initial discovery of novel potential therapeutic drugs. In this study, we develop an innovative and high-precision stacked-ensemble framework, called Stack-HDAC3i, which can directly identify HDAC3i using only the SMILES notation. Using an up-to-date benchmark dataset, we first employed both molecular descriptors and Mol2Vec embeddings to generate feature representations that cover multi-view information embedded in HDAC3i, such as structural and contextual information. Subsequently, these feature representations were used to train baseline models using nine popular ML algorithms. Finally, the probabilistic features derived from the selected baseline models were fused to construct the final stacked model. Both cross-validation and independent tests showed that Stack-HDAC3i is a high-accuracy prediction model with great generalization ability for identifying HDAC3i. Furthermore, in the independent test, Stack-HDAC3i achieved an accuracy of 0.926 and Matthew's correlation coefficient of 0.850, which are 0.44-6.11% and 0.83-11.90% higher than its constituent baseline models, respectively.

An extensive review on lung cancer therapeutics using machine learning techniques: state-of-the-art and perspectives

There are over 100 types of human cancer, accounting for millions of deaths every year. Lung cancer alone claims over 1.8 million lives per year and is expected to surpass 3.2 million by 2050, which underscores the urgent need for rapid drug development and repurposing initiatives. The application of AI emerges as a pivotal solution to developing anti-cancer therapeutics. This state-of-the-art review aims to explore the various applications of AI in lung cancer therapeutics. Predictive models can analyse large datasets, including clinical data, genetic information, and treatment outcomes, for novel drug design and to generate personalised treatment recommendations, potentially optimising therapeutic strategies, enhancing treatment efficacy, and minimising adverse effects. A thorough literature review study was conducted based on articles indexed in PubMed and Scopus. We compiled the use of various machine learning approaches, including CNN, RNN, GAN, VAEs, and other AI techniques, enhancing efficiency with accuracy exceeding 95%, which is validated through a computer-aided drug design process. AI can revolutionise lung cancer therapeutics, streamlining processes and saving biological scientists' time and effort-however, further research is needed to overcome challenges and fully unlock AI's potential in Lung Cancer Therapeutics.

An In Vitro Human Skin Test for Predicting Skin Sensitization and Adverse Immune Reactions to Biologics

Biologics, including monoclonal antibodies (mAb), have proved to be effective and successful therapeutic agents, particularly in the treatment of cancer and immune-inflammatory conditions, as well as allergies and infections. However, their use carries an inherent risk of an immune-mediated adverse drug reaction. In this study, we describe the use of a novel pre-clinical human in vitro skin explant test for predicting skin sensitization and adverse immune reactions. The skin explant test was used to investigate the effects of therapeutic antibodies, which are known to cause a limited reaction in a small number of patients or more severe reactions.

MATERIAL AND METHODS

Immune responses were determined by T cell proliferation and multiplex cytokine analysis, as well as histopathological analysis of skin damage (grades I-IV in increasing severity), predicting a negative (grade I) or positive (grade ≥ II) response for an adverse skin sensitization effect.

RESULTS

T cell proliferation responses were significantly increased in the positive group (p < 0.004). Multiplex cytokine analysis showed significantly increased levels of IFNγ, TNFα, IL-10, IL-12, IL-13, IL-1β, and IL-4 in the positive response group compared with the negative response group (p < 0.0001, p < 0.0001, p < 0.002, p < 0.01, p < 0.04, p < 0.006, and p < 0.004, respectively).

CONCLUSIONS

Overall, the skin explant test correctly predicted the clinical outcome of 13 out of 16 therapeutic monoclonal antibodies with a correlation coefficient of 0.770 (p = 0.0001). This assay therefore provides a valuable pre-clinical test for predicting adverse immune reactions, including T cell proliferation and cytokine release, both associated with skin sensitization to monoclonal antibodies.

Ligand based-design of potential schistosomiasis inhibitors through QSAR, homology modeling, molecular dynamics, pharmacokinetics, and DFT studies

Objectives

Schistosomiasis, a neglected tropical disease, is a leading cause of mortality in affected geographic areas. Currently, because no vaccine for schistosomiasis is available, control measures rely on widespread administration of the drug praziquantel (PZQ). The mass administration of PZQ has prompted concerns regarding the emergence of drug resistance. Therefore, new therapeutic targets and potential compounds are necessary to combat schistosomiasis.

Methods

Twenty-four potent derivatives of PZQ were optimized via density functional theory (DFT) at the B3LYP/6-31G∗ level. Quantitative structureactivity relationship (QSAR) models were generated and statistically validated, and a lead candidate was selected to develop therapeutic options with improved efficacy against schistosomiasis. The biological and binding energies of the designed compounds were evaluated. In addition, molecular dynamics; drug-likeness; absorption, distribution, metabolism, excretion, and toxicity (ADMET); and DFT studies were performed on the newly designed compounds.

Results

Five QSAR models were generated, among which model 1 had favorable validation parameters (R2train: 0.957, R2adj: 0.941, LOF: 0.101, Q2cv: 0.906, and R2test: 0.783) and was chosen to identify a lead candidate. Other statistical parameters for the chosen model included variance inflation factor values ranging from 1.242 to 1.678, and a Y-scrambling coefficient (cRp2) of 0.747. Five new compounds were designed with improved predicted activity (ranging from 5.081 to 7.022) surpassing those of both the lead compound and PZQ (predicted pEC50 of 5.545). Molecular dynamics simulation revealed high binding affinity of the proposed compounds toward the target receptor. ADMET and drug-likeness assessments indicated adherence to Lipinski's rule of five criteria, thereby suggesting pharmacological and oral safety. In addition, DFT analysis indicated resistance to electronic alteration during chemical reactions.

Conclusion

The proposed compounds exhibited potential drug characteristics, thus indicating their suitability for further investigation to enhance schistosomiasis treatment options.

Molecular structural modeling and physical characteristics of anti-breast cancer drugs via some novel topological descriptors and regression models

Research is continuously being pursued to treat cancer patients and prevent the disease by developing new medicines. However, experimental drug design and development is a costly, time-consuming, and challenging process. Alternatively, computational and mathematical techniques play an important role in optimally achieving this goal. Among these mathematical techniques, topological indices (TIs) have many applications in the drugs used for the treatment of breast cancer. TIs can be utilized to forecast the effectiveness of drugs by providing molecular structure information and related properties of the drugs. In addition, these can assist in the design and discovery of new drugs by providing insights into the structure-property/structure-activity relationships. In this article, a Quantitative Structure Property Relationship (QSPR) analysis is carried out using some novel degree-based molecular descriptors and regression models to predict various properties (such as boiling point, melting point, enthalpy, flashpoint, molar refraction, molar volume, and polarizability) of 14 drugs used for the breast cancer treatment. The molecular structures of these drugs are topologically modeled through vertex and edge partitioning techniques of graph theory, and then linear regression models are developed to correlate the computed values with the experimental properties of the drugs to investigate the performance of TIs in predicting these properties. The results confirmed the potential of the considered topological indices as a tool for drug discovery and design in the field of breast cancer treatment.

Modern technologies and solutions to enhance surveillance and response systems for emerging zoonotic diseases

Background

Zoonotic diseases originating in animals pose a significant threat to global public health. Recent outbreaks, such as coronavirus disease 2019 (COVID-19), have caused widespread illness, death, and socioeconomic disruptions worldwide. To cope with these diseases effectively, it is crucial to strengthen surveillance capabilities and establish rapid response systems.

Aim

The aim of this review to examine the modern technologies and solutions that have the potential to enhance zoonotic disease surveillance and outbreak responses and provide valuable insights into how cutting-edge innovations could be leveraged to prevent, detect, and control emerging zoonotic disease outbreaks. Herein, we discuss advanced tools including big data analytics, artificial intelligence, the Internet of Things, geographic information systems, remote sensing, molecular diagnostics, point-of-care testing, telemedicine, digital contact tracing, and early warning systems.

Results

These technologies enable real-time monitoring, the prediction of outbreak risks, early anomaly detection, rapid diagnosis, and targeted interventions during outbreaks. When integrated through collaborative partnerships, these strategies can significantly improve the speed and effectiveness of zoonotic disease control. However, several challenges persist, particularly in resource-limited settings, such as infrastructure limitations, costs, data integration and training requirements, and ethical implementation.

Conclusion

With strategic planning and coordinated efforts, modern technologies and solutions offer immense potential to bolster surveillance and outbreak responses, and serve as a critical resource against emerging zoonotic disease threats worldwide.

BioAct-Het: A Heterogeneous Siamese Neural Network for Bioactivity Prediction Using Novel Bioactivity Representation

Drug failure during experimental procedures due to low bioactivity presents a significant challenge. To mitigate this risk and enhance compound bioactivities, predicting bioactivity classes during lead optimization is essential. The existing studies on structure-activity relationships have highlighted the connection between the chemical structures of compounds and their bioactivity. However, these studies often overlook the intricate relationship between drugs and bioactivity, which encompasses multiple factors beyond the chemical structure alone. To address this issue, we propose the BioAct-Het model, employing a heterogeneous siamese neural network to model the complex relationship between drugs and bioactivity classes, bringing them into a unified latent space. In particular, we introduce a novel representation for the bioactivity classes, called Bio-Prof, and enhance the original bioactivity data sets to tackle data scarcity. These innovative approaches resulted in our model outperforming the previous ones. The evaluation of BioAct-Het is conducted through three distinct strategies: association-based, bioactivity class-based, and compound-based. The association-based strategy utilizes supervised learning classification, while the bioactivity class-based strategy adopts a retrospective study evaluation approach. On the other hand, the compound-based strategy demonstrates similarities to the concept of meta-learning. Furthermore, the model's effectiveness in addressing real-world problems is analyzed through a case study on the application of vancomycin and oseltamivir for COVID-19 treatment as well as molnupiravir's potential efficacy in treating COVID-19 patients. The data and code underlying this article are available on https://github.com/CBRC-lab/BioAct-Het. However, data sets were derived from sources in the public domain.

Mpropred: A machine learning (ML) driven Web-App for bioactivity prediction of SARS-CoV-2 main protease (Mpro) antagonists

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic emerged in 2019 and still requiring treatments with fast clinical translatability. Frequent occurrence of mutations in spike glycoprotein of SARS-CoV-2 led the consideration of an alternative therapeutic target to combat the ongoing pandemic. The main protease (Mpro) is such an attractive drug target due to its importance in maturating several polyproteins during the replication process. In the present study, we used a classification structure-activity relationship (CSAR) model to find substructures that leads to to anti-Mpro activities among 758 non-redundant compounds. A set of 12 fingerprints were used to describe Mpro inhibitors, and the random forest approach was used to build prediction models from 100 distinct data splits. The data set's modelability (MODI index) was found to be robust, with a value of 0.79 above the 0.65 threshold. The accuracy (89%), sensitivity (89%), specificity (73%), and Matthews correlation coefficient (79%) used to calculate the prediction performance, was also found to be statistically robust. An extensive analysis of the top significant descriptors unveiled the significance of methyl side chains, aromatic ring and halogen groups for Mpro inhibition. Finally, the predictive model is made publicly accessible as a web-app named Mpropred in order to allow users to predict the bioactivity of compounds against SARS-CoV-2 Mpro. Later, CMNPD, a marine compound database was screened by our app to predict bioactivity of all the compounds and results revealed significant correlation with their binding affinity to Mpro. Molecular dynamics (MD) simulation and molecular mechanics/Poisson Boltzmann surface area (MM/PBSA) analysis showed improved properties of the complexes. Thus, the knowledge and web-app shown herein can be used to develop more effective and specific inhibitors against the SARS-CoV-2 Mpro. The web-app can be accessed from https://share.streamlit.io/nadimfrds/mpropred/Mpropred_app.py.

DrugRep-KG: Toward Learning a Unified Latent Space for Drug Repurposing Using Knowledge Graphs

Drug repurposing or repositioning (DR) refers to finding new therapeutic applications for existing drugs. Current computational DR methods face data representation and negative data sampling challenges. Although retrospective studies attempt to operate various representations, it is a crucial step for an accurate prediction to aggregate these features and bring the associations between drugs and diseases into a unified latent space. In addition, the number of unknown associations between drugs and diseases, which is considered negative data, is much higher than the number of known associations, or positive data, leading to an imbalanced dataset. In this regard, we propose the DrugRep-KG method, which applies a knowledge graph embedding approach for representing drugs and diseases, to address these challenges. Despite the typical DR methods that consider all unknown drug-disease associations as negative data, we select a subset of unknown associations, provided the disease occurs because of an adverse reaction to a drug. DrugRep-KG has been evaluated based on different settings and achieves an AUC-ROC (area under the receiver operating characteristic curve) of 90.83% and an AUC-PR (area under the precision-recall curve) of 90.10%, which are higher than in previous works. Besides, we checked the performance of our framework in finding potential drugs for coronavirus infection and skin-related diseases: contact dermatitis and atopic eczema. DrugRep-KG predicted beclomethasone for contact dermatitis, and fluorometholone, clocortolone, fluocinonide, and beclomethasone for atopic eczema, all of which have previously been proven to be effective in other studies. Fluorometholone for contact dermatitis is a novel suggestion by DrugRep-KG that should be validated experimentally. DrugRep-KG also predicted the associations between COVID-19 and potential treatments suggested by DrugBank, in addition to new drug candidates provided with experimental evidence. The data and code underlying this article are available at https://github.com/CBRC-lab/DrugRep-KG.

Reverse tracking from drug-induced transcriptomes through multilayer molecular networks reveals hidden drug targets

Identifying molecular targets of a drug is an essential process for drug discovery and development. The recent in-silico approaches are usually based on the structure information of chemicals and proteins. However, 3D structure information is hard to obtain and machine-learning methods using 2D structure suffer from data imbalance problem. Here, we present a reverse tracking method from genes to target proteins using drug-perturbed gene transcriptional profiles and multilayer molecular networks. We scored how well the protein explains gene expression changes perturbed by a drug. We validated the protein scores of our method in predicting known targets of drugs. Our method performs better than other methods using the gene transcriptional profiles and shows the ability to suggest the molecular mechanism of drugs. Furthermore, our method has the potential to predict targets for objects that do not have rigid structural information, such as coronavirus.

Machine learning facilitated structural activity relationship approach for the discovery of novel inhibitors targeting EGFR

This research manuscript aims to find the most effective epidermal growth factor receptor (EGFR) inhibitors from millions of in house compounds through Machine Learning (ML) techniques. ML-based structure activity relationship (SAR) models were validated to predict biological activity of untested novel molecules. Six ML algorithms, including k nearest neighbour (KNN), decision tree (DT), Logistic Regression, support vector machine (SVM), multilinear regression (MLR), and random forest (RF), were used to build for activity prediction. Among these, RF classifier (accuracy for train and test set is 90% and 81%) and RF regressor (R2 and MSE for trainset is 0.83 and 0.29 and for test set, 0.69 and 0.46) showed good predictive performance. Also, the six most essential features that affect the biological activity parameter and highly contribute to model development were successfully selected by the variable importance technique. RF regression model was used to predict the biological activity expressed as pIC50 of nearly ten million molecules while RF classification model classifies those molecules into active, moderately active, and least active according to their predicted pIC50. Based on two models, thousand molecules from million molecules with higher predicted pIC50 values and classified as active were selected for molecular docking. Based on the docking scores, predicted pIC50, and binding interactions with MET769 residue, compounds, i.e., Zinc257233137, Zinc257232249, and Zinc101379788, were identified as potential EGFR inhibitors with predicted pIC50 7.72, 7.85, and 7.70. Dynamics studies were also performed on Zinc257233137 to illustrate that it has good binding free energy and stable hydrogen bonding interactions with EGFR. These molecules can be used for further research and proved to be the novel drugs for EGFR in cancer treatment.Communicated by Ramaswamy H. Sarma.

Insight into potent TLR2 inhibitors for the treatment of disease caused by Mycoplasma pneumoniae based on machine learning approaches

Mycoplasma pneumoniae (MP) is one of the most common pathogens that causes acute respiratory tract infections. Children experiencing MP infection often suffer severe complications, lung injury, and even death. Previous studies have demonstrated that Toll-like receptor 2 (TLR2) is a potential therapeutic target for treating the MP-induced inflammatory response. However, the screening of natural compounds has received more attention for the treatment of bacterial infections to reduce the likelihood of bacterial resistance. Herein, we screened compounds by combining molecular docking and machine learning approaches to find potential lead compounds for treating MP infection. First, all compounds were docked with the TLR2 receptor protein to screen for potential candidates. To predict drug bioactivity, a machine learning model (random forest) was trained for TLR2 inhibitors to obtain the predictive model. The model achieved significant squared correlation coefficient (R²) values for the training set (0.85) and validation set (0.84) of compounds. The developed machine learning model was then used to predict the pIC50 values of the top 50 candidates from the Traditional Chinese compounds and Discovery Diversity sets of compounds. As a result, these compounds are capable of inhibiting the inflammatory response induced by MP. However, prior to bringing these compounds to market, it is necessary to verify these results with additional biological testing, including preclinical and clinical studies. Moreover, the present study provides a theoretical basis for the use of natural compounds as potential candidates to treat pneumonia caused by MP.

Insight into TLR4 receptor inhibitory activity via QSAR for the treatment of Mycoplasma pneumonia disease

Mycoplasma pneumoniae (MP) is one of the most common pathogenic organisms causing upper and lower respiratory tract infections, lung injury, and even death in young children. Toll-like receptors (TLRs) play an important role in innate immunity by allowing the host to recognize pathogens invading the body. Previous studies demonstrated that TLR4 is a potential therapeutic target for the treatment of MP pneumonia. Therefore, the present study aimed to screen biologically active ingredients that target the TLR4 receptor pathway. We first used molecular docking to screen out the active compounds inhibiting the TLR4 pathway, and then used regression and classification machine learning algorithms to establish a quantitative structure-activity relationship (QSAR) model to predict the biological activity of the screened compounds. A total of 78 molecules were used in QSAR modelling, which were retrieved from the ChEMBL database. The QSAR models had acceptable correlation coefficients of R ² on the training and testing dataset in the range of 0.96 to 0.91 and 0.93 to 0.76, respectively. The multiclass classification models showed accuracy on training and testing data within ranges of 1.0 to 0.70, 0.96 to 0.63, and log loss ranges from 0.27 to 8.63, respectively. In addition, molecular descriptors and fingerprints have been studied as structural elements involved in increased and decreased inhibitory activities. These results provide a quantitative analysis of QSAR and classification models applicable for high-throughput screening, as well as insights into the mechanisms of inhibition of TLR4 antagonists.

Machine-Learning-Based Predictions of Polymer and Postconsumer Recycled Polymer Properties: A Comprehensive Review

There has been a tremendous increase in demand for virgin and postconsumer recycled (PCR) polymers due to their wide range of chemical and physical characteristics. Despite the numerous potential benefits of using a data-driven approach to polymer design, major hurdles exist in the development of polymer informatics due to the complicated hierarchical polymer structures. In this review, a brief introduction on virgin polymer structure, PCR polymers, compatibilization of polymers to be recycled, and their characterization using sensor array technologies as well as factors affecting the polymer properties are provided. Machine-learning (ML) algorithms are gaining attention as cost-effective scalable solutions to exploit the physical and chemical structures of polymers. The basic steps for applying ML in polymer science such as fingerprinting, algorithms, open-source databases, representations, and polymer design are detailed in this review. Further, a state-of-the-art review of the prediction of various polymer material properties using ML is reviewed. Finally, we discuss open-ended research questions on ML application to PCR polymers as well as potential challenges in the prediction of their properties using artificial intelligence for more efficient and targeted PCR polymer discovery and development.

Multiassay Profiling of a Focused Small Molecule Library Reveals Predictive Bidirectional Modulation of the lncRNA MALAT1 Triplex Stability In Vitro

The rapidly accelerating characterization of RNA tertiary structures has revealed their pervasiveness and active roles in human diseases. Small molecule-mediated modulation of RNA tertiary structures constitutes an attractive avenue for the development of tools for therapeutically targeting and/or uncovering the pathways associated with these RNA motifs. This potential has been highlighted by targeting of the triple helix present at the 3'-end of the noncoding RNA MALAT1, a transcript implicated in several human diseases. This triplex has been reported to decrease the susceptibility of the transcript to degradation and promote its cellular accumulation. While small molecules have been shown to bind to and impact the stability of the MALAT1 triple helix, the small molecule properties that lead to these structural modulations are not well understood. We designed a library utilizing the diminazene scaffold, which is underexplored but precedented for nucleic acid binding, to target the MALAT1 triple helix. We employed multiple assays to holistically assess what parameters, if any, could predict the small molecule affinity and effect on triplex stability. We designed and/or optimized competition, calorimetry, and thermal shift assays as well as an enzymatic degradation assay, the latter of which led to the discovery of bidirectional modulators of triple helix stability within the scaffold-centric library. Determination of quantitative structure-activity relationships afforded predictive models for both affinity- and stability-based assays. This work establishes a suite of powerful orthogonal biophysical tools for the evaluation of small molecule:RNA triplex interactions that generate predictive models and will allow small molecule interrogation of the growing body of disease-associated RNA triple helices.

A new perspective on the modeling and topological characterization of H-Naphtalenic nanosheets with applications

In the past few years, two-dimensional (2D) layered nanomaterials have greatly attracted the scientific community. Among 2D nanomaterials, the porphyrin-based Naphtalenic nanosheets have been the subject of intense research due to their utilization in photo-dynamic therapy and nanodevices. New technologies based on nanomaterials or Naphtalenic nanosheet are advantageous in overcoming the problems in conventional drug delivery like poor solubility, toxicity and poor release pattern of drugs. In chemical network theory, various molecular descriptors are used to predict the chemical properties of molecules; these molecular descriptors are found to be very useful for Quantitative Structure-Activity/ Quantitative Structure-Property (QSAR/QSPR) relationship analysis in materials engineering, chemical and pharmaceutical industries. Researchers have computed the molecular descriptors for various nanostructures; however, despite intense research, the topology of nanostructures is not yet well understood. Specially, to our knowledge, the computation of topological indices for the line graph of subdivision graph of H-Naphtalenic nanosheet has not been discussed so far, which may open new perspectives for a more accurate and reliable topological characterization of this nanosheet.In this article, we employed some important degree-based topological indices to study the chemical structure of Naphtalenic nanosheet as a chemical network for QSAR/QSPR analysis. We have computed these degree-based topological indices for the line graph of subdivision graph of H-Naphtalenic nanosheet and derived formulas for them. Based on the derived formulas, numerical results are obtained and the physical and chemical properties of the under study nanosheet are investigated.

Mechanism of action involved in the anxiolytic-like effects of Hibalactone isolated from Hydrocotyle umbellata L

Background and aim

Hibalactone (HB) is a lignan related to the anxiolytic-like effects of Hydrocotyle umbellata L. However, there is a need to understand better the mechanism of action of this lignan to support the ethnopharmacological uses of the species. This work aimed to evaluate by in vivo and in silico analysis the mechanism of action of HB involved in its anxiolytic-like effects.

Experimental procedure

The effects of HB in mice were evaluated on light-dark box (LDB) and elevated plus maze (EPM) tests. The participation of 5-HT_1A receptor and the benzodiazepine site of GABA_A receptor was evaluated to investigate the possible mechanism of action. In silico tools were used to better elucidate the anxiolytic-like effects of HB.

Results

Oral treatment with HB at a dose of 33 mg/kg showed an anxiolytic-like effect in the LDB and EPM tests. Besides that, the treatment altered the ethological parameters, frequency of head dips, and stretched-attend postures (SAP), important to better describe the anxiolytic profile of HB. Pretreatment with flumazenil (2 mg/kg) reverted the anxiolytic-like effect of HB on LDB and EPM tests. On the other hand, pretreatment with NAN-190 (0.5 mg/kg) not reverted the activity observed. In silico predictions revealed the potential of HB to increase GABAergic neurotransmission. Pharmacophore modelling and docking simulations showed that HB might interact with the α1β2γ2 GABA_A receptor.

Conclusion

Together, the results presented herein suggest that activation of the benzodiazepine site of the GABA_A receptor contributes to the anxiolytic-like effect of HB.

•

Pretreatment with flumazenil reverted the anxiolytic-like effect of hibalactone.

•

Pretreatment with NAN-190 not reverted the activity observed.

•

In silico findings showed that hibalactone may interact with α1β2γ2 GABA_A receptor.

ERpred: a web server for the prediction of subtype-specific estrogen receptor antagonists

Estrogen receptors alpha and beta (ERα and ERβ) are responsible for breast cancer metastasis through their involvement of clinical outcomes. Estradiol and hormone replacement therapy targets both ERs, but this often leads to an increased risk of breast and endometrial cancers as well as thromboembolism. A major challenge is posed for the development of compounds possessing ER subtype specificity. Herein, we present a large-scale classification structure-activity relationship (CSAR) study of inhibitors from the ChEMBL database which consisted of an initial set of 11,618 compounds for ERα and 7,810 compounds for ERβ. The IC50 was selected as the bioactivity unit for further investigation and after the data curation process, this led to a final data set of 1,593 and 1,281 compounds for ERα and ERβ, respectively. We employed the random forest (RF) algorithm for model building and of the 12 fingerprint types, models built using the PubChem fingerprint was the most robust (Ac of 94.65% and 92.25% and Matthews correlation coefficient (MCC) of 89% and 76% for ERα and ERβ, respectively) and therefore selected for feature interpretation. Results indicated the importance of features pertaining to aromatic rings, nitrogen-containing functional groups and aliphatic hydrocarbons. Finally, the model was deployed as the publicly available web server called ERpred at http://codes.bio/erpred where users can submit SMILES notation as the input query for prediction of the bioactivity against ERα and ERβ.

Siamese Recurrent Neural Network with a Self-Attention Mechanism for Bioactivity Prediction

Activity prediction plays an essential role in drug discovery by directing search of drug candidates in the relevant chemical space. Despite being applied successfully to image recognition and semantic similarity, the Siamese neural network has rarely been explored in drug discovery where modelling faces challenges such as insufficient data and class imbalance. Here, we present a Siamese recurrent neural network model (SiameseCHEM) based on bidirectional long short-term memory architecture with a self-attention mechanism, which can automatically learn discriminative features from the SMILES representations of small molecules. Subsequently, it is used to categorize bioactivity of small molecules via N-shot learning. Trained on random SMILES strings, it proves robust across five different datasets for the task of binary or categorical classification of bioactivity. Benchmarking against two baseline machine learning models which use the chemistry-rich ECFP fingerprints as the input, the deep learning model outperforms on three datasets and achieves comparable performance on the other two. The failure of both baseline methods on SMILES strings highlights that the deep learning model may learn task-specific chemistry features encoded in SMILES strings.

QSAR-Based Virtual Screening of Natural Products Database for Identification of Potent Antimalarial Hits

With about 400,000 annual deaths worldwide, malaria remains a public health burden in tropical and subtropical areas, especially in low-income countries. Selection of drug-resistant Plasmodium strains has driven the need to explore novel antimalarial compounds with diverse modes of action. In this context, biodiversity has been widely exploited as a resourceful channel of biologically active compounds, as exemplified by antimalarial drugs such as quinine and artemisinin, derived from natural products. Thus, combining a natural product library and quantitative structure-activity relationship (QSAR)-based virtual screening, we have prioritized genuine and derivative natural compounds with potential antimalarial activity prior to in vitro testing. Experimental validation against cultured chloroquine-sensitive and multi-drug-resistant P. falciparum strains confirmed the potent and selective activity of two sesquiterpene lactones (LDT-597 and LDT-598) identified in silico. Quantitative structure-property relationship (QSPR) models predicted absorption, distribution, metabolism, and excretion (ADME) and physiologically based pharmacokinetic (PBPK) parameters for the most promising compound, showing that it presents good physiologically based pharmacokinetic properties both in rats and humans. Altogether, the in vitro parasite growth inhibition results obtained from in silico screened compounds encourage the use of virtual screening campaigns for identification of promising natural compound-based antimalarial molecules.

Machine learning-driven new material discovery

New materials can bring about tremendous progress in technology and applications. However, the commonly used trial-and-error method cannot meet the current need for new materials. Now, a newly proposed idea of using machine learning to explore new materials is becoming popular. In this paper, we review this research paradigm of applying machine learning in material discovery, including data preprocessing, feature engineering, machine learning algorithms and cross-validation procedures. Furthermore, we propose to assist traditional DFT calculations with machine learning for material discovery. Many experiments and literature reports have shown the great effects and prospects of this idea. It is currently showing its potential and advantages in property prediction, material discovery, inverse design, corrosion detection and many other aspects of life.

Modeling the Physicochemical Properties of Natural Deep Eutectic Solvents

Natural deep eutectic solvents (NADES) are mixtures of naturally derived compounds with a significantly decreased melting point owing to specific interactions among the constituents. NADES have benign properties (low volatility, flammability, toxicity, cost) and tailorable physicochemical properties (by altering the type and molar ratio of constituents); hence, they are often considered to be a green alternative to common organic solvents. Modeling the relation between their composition and properties is crucial though, both for understanding and predicting their behavior. Several efforts have been made to this end. This Review aims at structuring the present knowledge as an outline for future research. First, the key properties of NADES are reviewed and related to their structure on the basis of the available experimental data. Second, available modeling methods applicable to NADES are reviewed. At the molecular level, DFT and molecular dynamics allow density differences and vibrational spectra to be interpreted, and interaction energies to be computed. Additionally, properties at the level of the bulk medium can be explained and predicted by semi-empirical methods based on ab initio methods (COSMO-RS) and equation of state models (PC-SAFT). Finally, methods based on large datasets are discussed: models based on group-contribution methods and machine learning. A combination of bulk-medium and dataset modeling allows qualitative prediction and interpretation of phase equilibria properties on the one hand, and quantitative prediction of melting point, density, viscosity, surface tension, and refractive index on the other. Multiscale modeling, combining molecular and macroscale methods, is expected to strongly enhance the predictability of NADES properties and their interaction with solutes, and thus yield truly tailorable solvents to accommodate (bio)chemical reactions.

Application of artificial neural networks to prediction of new substances with antimicrobial activity against Escherichia coli

AIMS

This article presents models of artificial neural networks (ANN) employed to predict the biological activity of chemical compounds based of their structure. Regression and classification models were designed to determine antimicrobial properties of quaternary ammonium salts against Escherichia coli strain.

METHODS AND RESULTS

The minimum inhibitory concentration microbial growth E. coli was experimentally determined by the serial dilution method for a series of 140 imidazole derivatives. Then, three-dimensional models for imidazole chlorides were constructed with computational chemistry methods which allowed to calculate molecular descriptors. The transformation of chemical information into a useful number is a main result of this operation. The designed regression and classification ANN models were characterized by a high predictive ability (classification accuracy was 95%, regression model: learning set R = 0.87, testing set R = 0.91, validation set R = 0.89).

CONCLUSIONS

Artificial neural networks can be successfully used to find potential antimicrobial preparations.

SIGNIFICANCE AND IMPACT OF THE STUDY

The neural networks are a very elaborate modelling technique, which allows not only to optimize and minimize labour costs but also to increase food safety.

HCVpred: A web server for predicting the bioactivity of hepatitis C virus NS5B inhibitors

Hepatitis C virus (HCV) is one of the major causes of liver disease affecting an estimated 170 million people culminating in 300,000 deaths from cirrhosis or liver cancer. NS5B is one of three potential therapeutic targets against HCV (i.e., the other two being NS3/4A and NS5A) that is central to viral replication. In this study, we developed a classification structure-activity relationship (CSAR) model for identifying substructures giving rise to anti-HCV activities among a set of 578 non-redundant compounds. NS5B inhibitors were described by a set of 12 fingerprint descriptors and predictive models were constructed from 100 independent data splits using the random forest algorithm. The modelability (MODI index) of the data set was determined to be robust with a value of 0.88 exceeding established threshold of 0.65. The predictive performance was deduced by the accuracy, sensitivity, specificity, and Matthews correlation coefficient, which was found to be statistically robust (i.e., the former three parameters afforded values in excess of 0.8 while the latter statistical parameter provided a value >0.7). An in-depth analysis of the top 20 important descriptors revealed that aromatic ring and alkyl side chains are important for NS5B inhibition. Finally, the predictive model is deployed as a publicly accessible HCVpred web server (available at http://codes.bio/hcvpred/) that would allow users to predict the biological activity as being active or inactive against HCV NS5B. Thus, the knowledge and web server presented herein can be used in the design of more potent and specific drugs against the HCV NS5B.

QSAR-driven rational design of novel DNA methyltransferase 1 inhibitors

DNA methylation, an epigenetic modification, is mediated by DNA methyltransferases (DNMTs), a family of enzymes. Inhibitions of these enzymes are considered a promising strategy for the treatment of several diseases. In this study, a quantitative structure-activity relationship (QSAR) modeling was employed to understand the structure-activity relationship (SAR) of currently available non-nucleoside DNMT1 inhibitors (i.e., indole and oxazoline/1,2-oxazole scaffolds). Two QSAR models were successfully constructed using multiple linear regression (MLR) and provided good predictive performance (R²_Tr = 0.850-0.988 and R²_CV = 0.672-0.869). Bond information content index (BIC1) and electronegativity (R6e+) are the most influential descriptors governing the activity of compounds. The constructed QSAR models were further applied for guiding a rational design of novel inhibitors. A novel set of 153 structurally modified compounds were designed in silico according to the important descriptors deduced from the QSAR finding, and their DNMT1 inhibitory activities were predicted. This result demonstrated that 86 newly designed inhibitors were predicted to elicit enhanced DNMT1 inhibitory activity when compared to their parent compounds. Finally, a set of promising compounds as potent DNMT1 inhibitors were highlighted to be further developed. The key SAR findings may also be beneficial for structural optimization to improve properties of the known inhibitors.

Machine Learning in Drug Discovery and Development Part 1: A Primer

Artificial intelligence, in particular machine learning (ML), has emerged as a key promising pillar to overcome the high failure rate in drug development. Here, we present a primer on the ML algorithms most commonly used in drug discovery and development. We also list possible data sources, describe good practices for ML model development and validation, and share a reproducible example. A companion article will summarize applications of ML in drug discovery, drug development, and postapproval phase.

Rational design of novel coumarins: A potential trend for antioxidants in cosmetics

Coumarins are well-known for their antioxidant effect and aromatic property, thus, they are one of ingredients commonly added in cosmetics and personal care products. Quantitative structure-activity relationships (QSAR) modeling is an in silico method widely used to facilitate rational design and structural optimization of novel drugs. Herein, QSAR modeling was used to elucidate key properties governing antioxidant activity of a series of the reported coumarin-based antioxidant agents (1-28). Several types of descriptors (calculated from 4 softwares i.e., Gaussian 09, Dragon, PaDEL and Mold2 softwares) were used to generate three multiple linear regression (MLR) models with preferable predictive performance (Q 2 LOO-CV = 0.813-0.908; RMSE LOO-CV = 0.150-0.210; Q 2 Ext = 0.875-0.952; RMSE Ext = 0.104-0.166). QSAR analysis indicated that number of secondary amines (nArNHR), polarizability (G2p), electronegativity (D467, D580, SpMin2_Bhe, and MATS8e), van der Waals volume (D491 and D461), and H-bond potential (SHBint4) are important properties governing antioxidant activity. The constructed models were also applied to guide in silico rational design of an additional set of 69 structurally modified coumarins with improved antioxidant activity. Finally, a set of 9 promising newly design compounds were highlighted for further development. Structure-activity analysis also revealed key features required for potent activity which would be useful for guiding the future rational design. In overview, our findings demonstrated that QSAR modeling could possibly be a facilitating tool to enhance successful development of bioactive compounds for health and cosmetic applications.

Towards reproducible computational drug discovery

The reproducibility of experiments has been a long standing impediment for further scientific progress. Computational methods have been instrumental in drug discovery efforts owing to its multifaceted utilization for data collection, pre-processing, analysis and inference. This article provides an in-depth coverage on the reproducibility of computational drug discovery. This review explores the following topics: (1) the current state-of-the-art on reproducible research, (2) research documentation (e.g. electronic laboratory notebook, Jupyter notebook, etc.), (3) science of reproducible research (i.e. comparison and contrast with related concepts as replicability, reusability and reliability), (4) model development in computational drug discovery, (5) computational issues on model development and deployment, (6) use case scenarios for streamlining the computational drug discovery protocol. In computational disciplines, it has become common practice to share data and programming codes used for numerical calculations as to not only facilitate reproducibility, but also to foster collaborations (i.e. to drive the project further by introducing new ideas, growing the data, augmenting the code, etc.). It is therefore inevitable that the field of computational drug design would adopt an open approach towards the collection, curation and sharing of data/code.

Toward insights on determining factors for high activity in antimicrobial peptides via machine learning

The continued and general rise of antibiotic resistance in pathogenic microbes is a well-recognized global threat. Host defense peptides (HDPs), a component of the innate immune system have demonstrated promising potential to become a next generation antibiotic effective against a plethora of pathogens. While the effectiveness of antimicrobial HDPs has been extensively demonstrated in experimental studies, theoretical insights on the mechanism by which these peptides function is comparably limited. In particular, experimental studies of AMP mechanisms are limited in the number of different peptides investigated and the type of peptide parameters considered. This study makes use of the random forest algorithm for classifying the antimicrobial activity as well for identifying molecular descriptors underpinning the antimicrobial activity of investigated peptides. Subsequent manual interpretation of the identified important descriptors revealed that polarity-solubility are necessary for the membrane lytic antimicrobial activity of HDPs.

A Bayesian machine learning approach for drug target identification using diverse data types

Drug target identification is a crucial step in development, yet is also among the most complex. To address this, we develop BANDIT, a Bayesian machine-learning approach that integrates multiple data types to predict drug binding targets. Integrating public data, BANDIT benchmarked a ~90% accuracy on 2000+ small molecules. Applied to 14,000+ compounds without known targets, BANDIT generated ~4,000 previously unknown molecule-target predictions. From this set we validate 14 novel microtubule inhibitors, including 3 with activity on resistant cancer cells. We applied BANDIT to ONC201—an anti-cancer compound in clinical development whose target had remained elusive. We identified and validated DRD2 as ONC201’s target, and this information is now being used for precise clinical trial design. Finally, BANDIT identifies connections between different drug classes, elucidating previously unexplained clinical observations and suggesting new drug repositioning opportunities. Overall, BANDIT represents an efficient and accurate platform to accelerate drug discovery and direct clinical application.

Drug target identification is a crucial step in drug development. Here, the authors introduce a Bayesian machine learning framework that integrates multiple data types to predict the targets of small molecules, enabling identification of a new set of microtubule inhibitors and the target of the anti-cancer molecule ONC201.

Anti-Inflammatory Properties of Plant Derived Natural Products - A Systematic Review

Traditionally, natural medicines have been administered as plant extracts, which are composed of a mixture of molecules. The individual molecular species in this mixture may or may not contribute to the overall medicinal effects and some may even oppose the beneficial activity of others. To better control therapeutic effects, studies that characterized specific molecules and describe their individual activity that have been performed over the past decades. These studies appear to underline that natural products are particularly effective as antioxidants and anti-inflammatory agents. In this systematic review we aimed to identify potent anti-inflammatory natural products and relate their efficacy to their chemical structure and physicochemical properties. To identify these compounds, we performed a comprehensive literature search to find those studies, in which a dose-response description and a positive control reference compound was used to benchmark the observed activity. Of the analyzed papers, 7% of initially selected studies met these requirements and were subjected to further analysis. This analysis revealed that most selected natural products indeed appeared to possess anti-inflammatory activities, in particular anti-oxidative properties. In addition, 14% of the natural products outperformed the remaining natural products in all tested assays and are attractive candidates as new anti-inflammatory agents.

Predicting binding poses and affinity ranking in D3R Grand Challenge using PL-PatchSurfer2.0

Computational prediction of protein-ligand interactions is a useful approach that aids the drug discovery process. Two major tasks of computational approaches are to predict the docking pose of a compound in a known binding pocket and to rank compounds in a library according to their predicted binding affinities. There are many computational tools developed in the past decades both in academia and industry. To objectively assess the performance of existing tools, the community has held a blind assessment of computational predictions, the Drug Design Data Resource Grand Challenge. This round, Grand Challenge 4 (GC4), focused on two targets, protein beta-secretase 1 (BACE-1) and cathepsin S (CatS). We participated in GC4 in both BACE-1 and CatS challenges using our molecular surface-based virtual screening method, PL-PatchSurfer2.0. A unique feature of PL-PatchSurfer2.0 is that it uses the three-dimensional Zernike descriptor, a mathematical moment-based shape descriptor, to quantify local shape complementarity between a ligand and a receptor, which properly incorporates molecular flexibility and provides stable affinity assessment for a bound ligand-receptor complex. Since PL-PatchSurfer2.0 does not explicitly build a bound pose of a ligand, we used an external docking program, such as AutoDock Vina, to provide an ensemble of poses, which were then evaluated by PL-PatchSurfer2.0. Here, we provide an overview of our method and report the performance in GC4.

3D-QSAR and docking studies on ursolic acid derivatives for anticancer activity based on bladder cell line T24 targeting NF-kB pathway inhibition

Bladder cancer is the common reason for mortality worldwide, and its increasing rate announces as a significant area of research in drug designing. The side effects and toxicity of existing drugs and the consequence of gradual cancer cell resistance against the available therapy make the treatment poor. Globally, there is a continuous high demand to develop new, more potent, and easily affordable drugs against cancer. The current research article illustrates the application of developed three-dimensional quantitative structure-activity relationship (3D-QSAR) based on human bladder cancer cell line T24 in vitro anticancer activity. The derived QSAR model has been used for prediction of natural compounds and analogs with 80% similarity of the most active compound of the dataset. The developed model describes the structure-activity relationship for terpenes and their derivatives at the molecular level. The developed comparative molecular field analysis (CoMFA) model shows a satisfactory cross-validation correlation coefficient (q2) of 0.54 and a regression correlation coefficient (r2) of 0.86. In order to evaluate the compliance with electronic pharmacokinetic parameters, Lipinski's rule of five filter, absorption, distribution, metabolism, and excretion (ADME) and toxicity of predicted compounds have been calculated. Furthermore, molecular-docking study has been performed to prioritize these predicted compounds based on their docking score and binding pocket similarity through the identified potential anticancer targets. Finally, two compounds T9 and B42 have been identified as the best hit because these two fall within the standard limits of all filters and show a good binding affinity. Conclusively, all satisfactory results strongly suggest that the derived 3D-QSAR model and obtained candidate's binding structures are reasonable in the prediction of a new antagonist's activity. The strategy adopted in the present research is expected to be of immense importance and a great support in the identification and optimization of lead in the early and advance drug discovery.

Rational design of novel sirtuin 1 activators via structure-activity insights from application of QSAR modeling

Sirtuin 1 (SIRT1) enzyme regulates major cell activities, and its activation offers lucrative therapeutic potentials for aging diseases including Alzheimer's disease (AD). Regarding the global aging society, continual attention has been given to various chemical scaffolds as a source for the discovery of novel SIRT1 activators since the discovery of the pioneer activator, resveratrol. Understanding structure-activity relationship (SAR) is essential for screening, designing as well as improving the properties of drugs. In this study, an in silico approach based on quantitative structure-activity relationship (QSAR) modeling, was employed for understanding the SAR of currently available SIRT1 fused-aromatic activators (i.e., imidazothiazole, oxazolopyridine, and azabenzimidazole analogs). Three QSAR models constructed using multiple linear regression (MLR) provided good predictive performance (R ² _LOOCV = 0.729 - 0.863 and RMSE _LOOCV = 0.165 - 0.325). An additional novel set of 181 structurally modified compounds were rationally designed according to key descriptors deduced from the QSAR findings and their SIRT1 activities were predicted using the constructed models. In overview, the study provides insightful SAR findings of currently available SIRT1 activators that would be useful for guiding the rational design, screening, and development of further potent SIRT1 activators for managing age-related clinical conditions. A series of promising compounds as well as important scaffolds and molecular properties for potent SIRT1 activator were highlighted. This study demonstrated the efficacious role of QSAR-driven structural modification for the rational design of novel leads.

Rational Design of Colchicine Derivatives as anti-HIV Agents via QSAR and Molecular Docking

BACKGROUND

Human immunodeficiency virus (HIV) is an infective agent that causes an acquired immunodeficiency syndrome (AIDS). Therefore, the rational design of inhibitors for preventing the progression of the disease is required.

OBJECTIVE

This study aims to construct quantitative structure-activity relationship (QSAR) models, molecular docking and newly rational design of colchicine and derivatives with anti-HIV activity.

METHODS

A data set of 24 colchicine and derivatives with anti-HIV activity were employed to develop the QSAR models using machine learning methods (e.g. multiple linear regression (MLR), artificial neural network (ANN) and support vector machine (SVM)), and to study a molecular docking.

RESULTS

The significant descriptors relating to the anti-HIV activity included JGI2, Mor24u, Gm and R8p+ descriptors. The predictive performance of the models gave acceptable statistical qualities as observed by correlation coefficient (Q2) and root mean square error (RMSE) of leave-one out cross-validation (LOO-CV) and external sets. Particularly, the ANN method outperformed MLR and SVM methods that displayed LOO-CV 2 Q and RMSELOO-CV of 0.7548 and 0.5735 for LOOCV set, and Ext 2 Q of 0.8553 and RMSEExt of 0.6999 for external validation. In addition, the molecular docking of virus-entry molecule (gp120 envelope glycoprotein) revealed the key interacting residues of the protein (cellular receptor, CD4) and the site-moiety preferences of colchicine derivatives as HIV entry inhibitors for binding to HIV structure. Furthermore, newly rational design of colchicine derivatives using informative QSAR and molecular docking was proposed.

CONCLUSION

These findings serve as a guideline for the rational drug design as well as potential development of novel anti-HIV agents.

A simple approach for assessment of toxicity of nitroaromatic compounds without using complex descriptors and computer codes

A simple approach is introduced to assess the toxicity of nitroaromatic compounds in terms of an oral LD₅₀ dose (50% lethal dose) for rats. Most of the presented Quantitative Structure-Activity Relationship (QSAR) models for prediction of in vivo toxicity of nitroaromatics are calculated by quantum computing descriptors which are more difficult to interpret and apply, while the new model requires only the molecular structure of a desirable nitroaromatic compound. The novel model is based on the constitutional descriptors, such as the number of oxygen, sulphur, phosphorous and molecular fragments. Experimental data of 90 nitroaromatics are used to derive and test the new model as the logarithm of LD₅₀ values, i.e. -log (LD₅₀). Although it is based on only simple structural parameters, the reliability of the new model is also higher than the complex QSAR model because the values of the root-mean-square deviation (RMSD) of -log (LD₅₀) for the new and the outputs of the latest QSAR method are 0.342 and 0.377, respectively.

Quantitative profile-profile relationship (QPPR) modelling: a novel machine learning approach to predict and associate chemical characteristics of unspent ammunition from gunshot residue (GSR)

Evidence association in forensic cases involving gunshot residue (GSR) remains very challenging. Herein, a new in silico approach, called quantitative profile-profile relationship (QPPR) modelling, is reported. This is based on the application of modern machine learning techniques to predict the pre-discharge chemical profiles of selected ammunition components from those of the respective post-discharge GSR. The obtained profiles can then be compared with one another and/or with other measured profiles to make evidential links during forensic investigations. In particular, the approach was optimised and successfully tested for the prediction of GC-MS profiles of smokeless powders (SLPs) from organic GSR in spent cases, for nine ammunition types. Results showed a high degree of similarity between predicted and experimentally measured profiles, after adequate combination and evaluation of fourteen machine learning techniques (median correlation of 0.982). Areas under the curve (AUCs) of 0.976 and 0.824 were observed after receiver operating characteristic (ROC) analysis of the results obtained in the comparisons between predicted-predicted and predicted-measured profiles, respectively, in the specific case that the ammunition types of interest were excluded from the training dataset (i.e., extrapolation). Furthermore, AUCs of 0.962 and 0.894 were observed in interpolation mode. These values were close to those of the comparison of the measured SLP profiles between themselves (AUC = 0.998), demonstrating excellent potential to correctly associate evidence in a number of different forensic scenarios. This work represents the first time that a quantitative approach has successfully been applied to associate a GSR to a specific ammunition.

Predicting Skin Permeability by Means of Computational Approaches: Reliability and Caveats in Pharmaceutical Studies

The skin is the main barrier between the internal body environment and the external one. The characteristics of this barrier and its properties are able to modify and affect drug delivery and chemical toxicity parameters. Therefore, it is not surprising that permeability of many different compounds has been measured through several in vitro and in vivo techniques. Moreover, many different in silico approaches have been used to identify the correlation between the structure of the permeants and their permeability, to reproduce the skin behavior, and to predict the ability of specific chemicals to permeate this barrier. A significant number of issues, like interlaboratory variability, experimental conditions, data set building rationales, and skin site of origin and hydration, still prevent us from obtaining a definitive predictive skin permeability model. This review wants to show the main advances and the principal approaches in computational methods used to predict this property, to enlighten the main issues that have arisen, and to address the challenges to develop in future research.

Accurate prediction of personalized olfactory perception from large-scale chemoinformatic features

Background

The olfactory stimulus-percept problem has been studied for more than a century, yet it is still hard to precisely predict the odor given the large-scale chemoinformatic features of an odorant molecule. A major challenge is that the perceived qualities vary greatly among individuals due to different genetic and cultural backgrounds. Moreover, the combinatorial interactions between multiple odorant receptors and diverse molecules significantly complicate the olfaction prediction. Many attempts have been made to establish structure-odor relationships for intensity and pleasantness, but no models are available to predict the personalized multi-odor attributes of molecules. In this study, we describe our winning algorithm for predicting individual and population perceptual responses to various odorants in the DREAM Olfaction Prediction Challenge.

Results

We find that random forest model consisting of multiple decision trees is well suited to this prediction problem, given the large feature spaces and high variability of perceptual ratings among individuals. Integrating both population and individual perceptions into our model effectively reduces the influence of noise and outliers. By analyzing the importance of each chemical feature, we find that a small set of low- and nondegenerative features is sufficient for accurate prediction.

Conclusions

Our random forest model successfully predicts personalized odor attributes of structurally diverse molecules. This model together with the top discriminative features has the potential to extend our understanding of olfactory perception mechanisms and provide an alternative for rational odorant design.

Bioinformatics Approaches to Predict Drug Responses from Genomic Sequencing

Fulfilling the promises of precision medicine will depend on our ability to create patient-specific treatment regimens. Therefore, being able to translate genomic sequencing into predicting how a patient will respond to a given drug is critical. In this chapter, we review common bioinformatics approaches that aim to use sequencing data to predict sample-specific drug susceptibility. First, we explain the importance of customized drug regimens to the future of medical care. Second, we discuss the different public databases and community efforts that can be leveraged to develop new methods for identifying new predictive biomarkers. Third, we cover the basic methods that are currently used to identify markers or signatures of drug response, without any prior knowledge of the drug's mechanism of action. We further discuss how one can integrate knowledge about drug targets, mechanisms, and predictive markers to better estimate drug response in a diverse set of samples. We begin this section with a primer on popular methods to identify targets and mechanism of action for new small molecules. This discussion also includes a set of computational methods that incorporate other drug features, which do not relate to drug-induced genetic changes or sequencing data such as drug structures, side-effects, and efficacy profiles. Those additional drug properties can aid in gaining higher accuracy for the identification of drug target and mechanism of action. We then progress to discuss using these targets in combination with disease-specific expression patterns, known pathways, and genetic interaction networks to aid drug choice. Finally, we conclude this chapter with a general overview of machine learning methods that can integrate multiple pieces of sequencing data along with prior drug or biological knowledge to drastically improve response prediction.

Effect of N-(2-aminoethyl) ethanolamine on hypertrophic scarring changes in vitro: Finding novel anti-fibrotic therapies

Hypertrophic scars (HS) limit movement, decrease quality of life, and remain a major impediment to rehabilitation from burns. However, no effective pharmacologic therapies for HS exist. Here we tested the in vitro anti-fibrotic effects of the novel chemical N-(2-aminoethyl) ethanolamine (AEEA) at non-toxic concentrations. Scanning electron microscopy showed that AEEA markedly altered the structure of the extracellular matrix (ECM) produced by primary dermal fibroblasts isolated from a HS of a burn patient (HTS). Compression atomic force microscopy revealed that AEEA stiffened the 3D nanostructure of ECM formed by HTS fibroblasts. Western blot analysis in three separate types of primary human dermal fibroblasts (including HTS) showed that AEEA exposure increased the extractability of type I collagen in a dose- and time-dependent fashion, while not increasing collagen synthesis. A comparison of the electrophoretic behavior of the same set of samples under native and denaturing conditions suggested that AEEA alters the 3D structure of type I collagen. The antagonization effect of AEEA to TGF-β1 on ECM formation was also observed. Furthermore, analyses of the anti-fibrotic effects of analogs of AEEA (with modified pharmacophores) suggest the existence of a chemical structure-activity relationship. Thus, AEEA and its analogs may inhibit HS development; further study and optimization of analogs may be a promising strategy for the discovery for effective HS therapies.