MDL Drug Data Report Research Articles

Convolutional Neural Network Model Based on 2D Fingerprint for Bioactivity Prediction.

Determining and modeling the possible behaviour and actions of molecules requires investigating the basic structural features and physicochemical properties that determine their behaviour during chemical, physical, biological, and environmental processes. Computational approaches such as machine learning methods are alternatives to predicting the physiochemical properties of molecules based on their structures. However, the limited accuracy and high error rates of such predictions restrict their use. In this paper, a novel technique based on a deep learning convolutional neural network (CNN) for the prediction of chemical compounds' bioactivity is proposed and developed. The molecules are represented in the new matrix format Mol2mat, a molecular matrix representation adapted from the well-known 2D-fingerprint descriptors. To evaluate the performance of the proposed methods, a series of experiments were conducted using two standard datasets, namely the MDL Drug Data Report (MDDR) and Sutherland, datasets comprising 10 homogeneous and 14 heterogeneous activity classes. After analysing the eight fingerprints, all the probable combinations were investigated using the five best descriptors. The results showed that a combination of three fingerprints, ECFP4, EPFP4, and ECFC4, along with a CNN activity prediction process, achieved the highest performance of 98% AUC when compared to the state-of-the-art ML algorithms NaiveB, LSVM, and RBFN.

Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron.

Traditional drug development is a slow and costly process that leads to the production of new drugs. Virtual screening (VS) is a computational procedure that measures the similarity of molecules as one of its primary tasks. Many techniques for capturing the biological similarity between a test compound and a known target ligand have been established in ligand-based virtual screens (LBVSs). However, despite the good performances of the above methods compared to their predecessors, especially when dealing with molecules that have structurally homogenous active elements, they are not satisfied when dealing with molecules that are structurally heterogeneous. The main aim of this study is to improve the performance of similarity searching, especially with molecules that are structurally heterogeneous. The Siamese network will be used due to its capability to deal with complicated data samples in many fields. The Siamese multi-layer perceptron architecture will be enhanced by using two similarity distance layers with one fused layer, then multiple layers will be added after the fusion layer, and then the nodes of the model that contribute less or nothing during inference according to their signal-to-noise ratio values will be pruned. Several benchmark datasets will be used, which are: the MDL Drug Data Report (MDDR-DS1, MDDR-DS2, and MDDR-DS3), the Maximum Unbiased Validation (MUV), and the Directory of Useful Decoys (DUD). The results show the outperformance of the proposed method on standard Tanimoto coefficient (TAN) and other methods. Additionally, it is possible to reduce the number of nodes in the Siamese multilayer perceptron model while still keeping the effectiveness of recall on the same level.

Improved Deep Learning Based Method for Molecular Similarity Searching Using Stack of Deep Belief Networks.

Virtual screening (VS) is a computational practice applied in drug discovery research. VS is popularly applied in a computer-based search for new lead molecules based on molecular similarity searching. In chemical databases similarity searching is used to identify molecules that have similarities to a user-defined reference structure and is evaluated by quantitative measures of intermolecular structural similarity. Among existing approaches, 2D fingerprints are widely used. The similarity of a reference structure and a database structure is measured by the computation of association coefficients. In most classical similarity approaches, it is assumed that the molecular features in both biological and non-biologically-related activity carry the same weight. However, based on the chemical structure, it has been found that some distinguishable features are more important than others. Hence, this difference should be taken consideration by placing more weight on each important fragment. The main aim of this research is to enhance the performance of similarity searching by using multiple descriptors. In this paper, a deep learning method known as deep belief networks (DBN) has been used to reweight the molecule features. Several descriptors have been used for the MDL Drug Data Report (MDDR) dataset each of which represents different important features. The proposed method has been implemented with each descriptor individually to select the important features based on a new weight, with a lower error rate, and merging together all new features from all descriptors to produce a new descriptor for similarity searching. Based on the extensive experiments conducted, the results show that the proposed method outperformed several existing benchmark similarity methods, including Bayesian inference networks (BIN), the Tanimoto similarity method (TAN), adapted similarity measure of text processing (ASMTP) and the quantum-based similarity method (SQB). The results of this proposed multi-descriptor-based on Stack of deep belief networks method (SDBN) demonstrated a higher accuracy compared to existing methods on structurally heterogeneous datasets.

Stacked Ensemble for Bioactive Molecule Prediction

Bioactive molecular compounds are essential for drug discovery. The biological activity of these compounds needs to be predicted as this is used to determine the drug-target ability. As ineffective drugs are discarded after production, leading to resource and time wastage, it is important to predict bioactive molecules with models having high predictive performance. This study utilizes the stacked ensemble which uses the prediction of multiple base classifiers as features, used to train a meta classifier which makes the final prediction. Using three datasets DS1, DS2, and DS3 gotten from MDL Drug Data Report (MDDR) database, the performance of stacked ensemble was compared to three other ensembles: adaboost, bagging, and vote ensemble, based on different evaluation criteria and also a statistical method, Kendall's W test. The accuracy of Stacked ensemble ranged from 96.7002%, 98.2260% and 94.9007% for the three datasets respectively, although Vote had the best accuracy using dataset DS2 which consist of structurally homogeneous bioactive molecules. Also, using Kendall's W test to rank the ensembles, Stacked ensemble was ranked best with datasets DS1 and DS3, with both having a mean average of 4.00 and an overall level of agreement, W, of 0.986 and 1.000 respectively. Using dataset DS2, it was ranked after Vote and Adaboost with mean average of 2.33 and an overall level of agreement, W of 0.857. Stacked ensemble is recommended for the prediction of heterogeneous bioactive molecules during drug discovery and can also be implemented in other research areas.

Ensemble learning method for the prediction of new bioactive molecules.

Pharmacologically active molecules can provide remedies for a range of different illnesses and infections. Therefore, the search for such bioactive molecules has been an enduring mission. As such, there is a need to employ a more suitable, reliable, and robust classification method for enhancing the prediction of the existence of new bioactive molecules. In this paper, we adopt a recently developed combination of different boosting methods (Adaboost) for the prediction of new bioactive molecules. We conducted the research experiments utilizing the widely used MDL Drug Data Report (MDDR) database. The proposed boosting method generated better results than other machine learning methods. This finding suggests that the method is suitable for inclusion among the in silico tools for use in cheminformatics, computational chemistry and molecular biology.

Quantum probability ranking principle for ligand-based virtual screening.

Chemical libraries contain thousands of compounds that need screening, which increases the need for computational methods that can rank or prioritize compounds. The tools of virtual screening are widely exploited to enhance the cost effectiveness of lead drug discovery programs by ranking chemical compounds databases in decreasing probability of biological activity based upon probability ranking principle (PRP). In this paper, we developed a novel ranking approach for molecular compounds inspired by quantum mechanics, called quantum probability ranking principle (QPRP). The QPRP ranking criteria would make an attempt to draw an analogy between the physical experiment and molecular structure ranking process for 2D fingerprints in ligand based virtual screening (LBVS). The development of QPRP criteria in LBVS has employed the concepts of quantum at three different levels, firstly at representation level, this model makes an effort to develop a new framework of molecular representation by connecting the molecular compounds with mathematical quantum space. Secondly, estimate the similarity between chemical libraries and references based on quantum-based similarity searching method. Finally, rank the molecules using QPRP approach. Simulated virtual screening experiments with MDL drug data report (MDDR) data sets showed that QPRP outperformed the classical ranking principle (PRP) for molecular chemical compounds.

Structure-based virtual screening and characterization of a novel IL-6 antagonistic compound from synthetic compound database

According to the three-dimensional (3D) complex structure of (hIL-6⋅hIL-6R⋅gp 130)2 and the binding orientation of hIL-6, three compounds with high affinity to hIL-6R and bioactivity to block hIL-6 in vitro were screened theoretically from the chemical databases, including 3D-Available Chemicals Directory (ACD) and MDL Drug Data Report (MDDR), by means of the computer-guided virtual screening method. Using distance geometry, molecular modeling and molecular dynamics trajectory analysis methods, the binding mode and binding energy of the three compounds were evaluated theoretically. Enzyme-linked immunosorbent assay analysis demonstrated that all the three compounds could block IL-6 binding to IL-6R specifically. However, only compound 1 could effectively antagonize the function of hIL-6 and inhibit the proliferation of XG-7 cells in a dose-dependent manner, whereas it showed no cytotoxicity to SP2/0 or L929 cells. These data demonstrated that the compound 1 could be a promising candidate of hIL-6 antagonist.

Adapting Document Similarity Measures for Ligand-Based Virtual Screening.

Quantifying the similarity of molecules is considered one of the major tasks in virtual screening. There are many similarity measures that have been proposed for this purpose, some of which have been derived from document and text retrieving areas as most often these similarity methods give good results in document retrieval and can achieve good results in virtual screening. In this work, we propose a similarity measure for ligand-based virtual screening, which has been derived from a text processing similarity measure. It has been adopted to be suitable for virtual screening; we called this proposed measure the Adapted Similarity Measure of Text Processing (ASMTP). For evaluating and testing the proposed ASMTP we conducted several experiments on two different benchmark datasets: the Maximum Unbiased Validation (MUV) and the MDL Drug Data Report (MDDR). The experiments have been conducted by choosing 10 reference structures from each class randomly as queries and evaluate them in the recall of cut-offs at 1% and 5%. The overall obtained results are compared with some similarity methods including the Tanimoto coefficient, which are considered to be the conventional and standard similarity coefficients for fingerprint-based similarity calculations. The achieved results show that the performance of ligand-based virtual screening is better and outperforms the Tanimoto coefficients and other methods.

A Quantum-Based Similarity Method in Virtual Screening.

One of the most widely-used techniques for ligand-based virtual screening is similarity searching. This study adopted the concepts of quantum mechanics to present as state-of-the-art similarity method of molecules inspired from quantum theory. The representation of molecular compounds in mathematical quantum space plays a vital role in the development of quantum-based similarity approach. One of the key concepts of quantum theory is the use of complex numbers. Hence, this study proposed three various techniques to embed and to re-represent the molecular compounds to correspond with complex numbers format. The quantum-based similarity method that developed in this study depending on complex pure Hilbert space of molecules called Standard Quantum-Based (SQB). The recall of retrieved active molecules were at top 1% and top 5%, and significant test is used to evaluate our proposed methods. The MDL drug data report (MDDR), maximum unbiased validation (MUV) and Directory of Useful Decoys (DUD) data sets were used for experiments and were represented by 2D fingerprints. Simulated virtual screening experiment show that the effectiveness of SQB method was significantly increased due to the role of representational power of molecular compounds in complex numbers forms compared to Tanimoto benchmark similarity measure.

Weighted voting-based consensus clustering for chemical structure databases.

The cluster-based compound selection is used in the lead identification process of drug discovery and design. Many clustering methods have been used for chemical databases, but there is no clustering method that can obtain the best results under all circumstances. However, little attention has been focused on the use of combination methods for chemical structure clustering, which is known as consensus clustering. Recently, consensus clustering has been used in many areas including bioinformatics, machine learning and information theory. This process can improve the robustness, stability, consistency and novelty of clustering. For chemical databases, different consensus clustering methods have been used including the co-association matrix-based, graph-based, hypergraph-based and voting-based methods. In this paper, a weighted cumulative voting-based aggregation algorithm (W-CVAA) was developed. The MDL Drug Data Report (MDDR) benchmark chemical dataset was used in the experiments and represented by the AlogP and ECPF_4 descriptors. The results from the clustering methods were evaluated by the ability of the clustering to separate biologically active molecules in each cluster from inactive ones using different criteria, and the effectiveness of the consensus clustering was compared to that of Ward's method, which is the current standard clustering method in chemoinformatics. This study indicated that weighted voting-based consensus clustering can overcome the limitations of the existing voting-based methods and improve the effectiveness of combining multiple clusterings of chemical structures.

Condorcet and borda count fusion method for ligand-based virtual screening.

BackgroundIt is known that any individual similarity measure will not always give the best recall of active molecule structure for all types of activity classes. Recently, the effectiveness of ligand-based virtual screening approaches can be enhanced by using data fusion. Data fusion can be implemented using two different approaches: group fusion and similarity fusion. Similarity fusion involves searching using multiple similarity measures. The similarity scores, or ranking, for each similarity measure are combined to obtain the final ranking of the compounds in the database.ResultsThe Condorcet fusion method was examined. This approach combines the outputs of similarity searches from eleven association and distance similarity coefficients, and then the winner measure for each class of molecules, based on Condorcet fusion, was chosen to be the best method of searching. The recall of retrieved active molecules at top 5% and significant test are used to evaluate our proposed method. The MDL drug data report (MDDR), maximum unbiased validation (MUV) and Directory of Useful Decoys (DUD) data sets were used for experiments and were represented by 2D fingerprints.ConclusionsSimulated virtual screening experiments with the standard two data sets show that the use of Condorcet fusion provides a very simple way of improving the ligand-based virtual screening, especially when the active molecules being sought have a lowest degree of structural heterogeneity. However, the effectiveness of the Condorcet fusion was increased slightly when structural sets of high diversity activities were being sought.

Combining multiple clusterings of chemical structures using cluster-based similarity partitioning algorithm

Many types of clustering techniques for chemical structures have been used in the literature, but it is known that any single method will not always give the best results for all types of applications. Recent work on consensus clustering methods is motivated because of the successes of combining multiple classifiers in many areas and the ability of consensus clustering to improve the robustness, novelty, consistency and stability of individual clusterings. In this paper, the Cluster-based Similarity Partitioning Algorithm (CSPA) was examined for improving the quality of chemical structures clustering. The effectiveness of clustering was evaluated based on the ability to separate active from inactive molecules in each cluster and the results were compared with the Ward's clustering method. The chemical dataset MDL Drug Data Report (MDDR) database was used for experiments. The results, obtained by combining multiple clusterings, showed that the consensus clustering method can improve the robustness, novelty and stability of chemical structures clustering.

Information Theory and Voting Based Consensus Clustering for Combining Multiple Clusterings of Chemical Structures.

Many consensus clustering methods have been applied in different areas such as pattern recognition, machine learning, information theory and bioinformatics. However, few methods have been used for chemical compounds clustering. In this paper, an information theory and voting based algorithm (Adaptive Cumulative Voting-based Aggregation Algorithm A-CVAA) was examined for combining multiple clusterings of chemical structures. The effectiveness of clusterings was evaluated based on the ability of the clustering method to separate active from inactive molecules in each cluster, and the results were compared with Ward's method. The chemical dataset MDL Drug Data Report (MDDR) and the Maximum Unbiased Validation (MUV) dataset were used. Experiments suggest that the adaptive cumulative voting-based consensus method can improve the effectiveness of combining multiple clusterings of chemical structures.

Mining basic active structures from a large-scale database

BackgroundThe Pubchem Database is a large-scale resource for chemical information, containing millions of chemical compound activities derived by high-throughput screening (HTS). The ability to extract characteristic substructures from such enormous amounts of data is steadily growing in importance. Compounds with shared basic active structures (BASs) exhibiting G-protein coupled receptor (GPCR) activity and repeated dose toxicity have been mined from small datasets. However, the mining process employed was not applicable to large datasets owing to a large imbalance between the numbers of active and inactive compounds. In most datasets, one active compound will appear for every 1000 inactive compounds. Most mining techniques work well only when these numbers are similar.ResultsThis difficulty was overcome by sampling an equal number of active and inactive compounds. The sampling process was repeated to maintain the structural diversity of the inactive compounds. An interactive KNIME workflow that enabled effective sampling and data cleaning processes was created. The application of the cascade model and subsequent structural refinement yielded the BAS candidates. Repeated sampling increased the ratio of active compounds containing these substructures. Three samplings were deemed adequate to identify all of the meaningful BASs. BASs expressing similar structures were grouped to give the final set of BASs. This method was applied to HIV integrase and protease inhibitor activities in the MDL Drug Data Report (MDDR) database and to procaspase-3 activators in the PubChem BioAssay database, yielding 14, 12, and 18 BASs, respectively.ConclusionsThe proposed mining scheme successfully extracted meaningful substructures from large datasets of chemical structures. The resulting BASs were deemed reasonable by an experienced medicinal chemist. The mining itself requires about 3 days to extract BASs with a given physiological activity. Thus, the method described herein is an effective way to analyze large HTS databases.

Using graph-based consensus clustering for combining K-means clustering of heterogeneous chemical structures

Consensus clustering methods are motivated by the success of combining multiple classifiers in many areas. In this paper, graph-based consensus clustering is used to improve the quality of chemical compound clustering by enhancing the robustness, novelty, consistency and stability of individual clusterings. For this purpose, Hyper-Graph Partitioning Algorithm (HGPA) [1], was applied. The clustering is evaluated based on the ability to separate actives from inactives molecules in each cluster and the results were compared with the Ward's clustering method. The chemical dataset MDL Drug Data Report (MDDR) database has been used for experiments. The MDL Drug Data Report (MDDR) database consists of 102516 molecules. For the experiments, the dataset DS1 was chosen from the MDDR database. This dataset has been used for many virtual screening experiments [2-4]. The dataset DS1contains 10 heterogeneous activity classes (8568 molecules). For the clustering experiments, two 2D fingerprint descriptors will be used which are developed by Scitegic's Pipeline Pilot [5]. These are 120-bit ALOGP and 1024-bit extended connectivity fingerprints (ECFP_4). The results were evaluated based on the effectiveness of the methods to separate actives from non-actives molecules using QPI- (for quality partition index) measure, which was devised by Varin et al. [6]. As defined by [7], an active cluster as a non-singleton cluster for which the percentage of active molecules in the cluster is greater than the percentage of active molecules in the dataset as a whole. Let p be the number of actives in active clusters, q the number of inactives in active clusters, r the number of actives in inactive clusters (i.e., clusters that are not active clusters) and s the number of singleton actives. The high value occurs when the actives are clustered tightly together and separated from the inactive molecules. Then the quality partition index, QPI, is defined to be: QPI=pp+q+r+s (1) Then, the results will be compared with Ward's individual clustering method, the standard clustering method for chemoinformatics applications. The generation process has been done by multiple run of K-means algorithms, each with random initialization of cluster centroids. The number of partitions generated in this step is ranged between n = 5 to n = 50, with 5-times step. Then, all the generated partitions were combined using HGPA to obtain the consensus partition. This process is done for each fingerprint (ALOGP and ECFP_4). The mean of QPI values are averaged over the ten activity classes of the datasets. Tables ​Tables1,1, ​,22 show the effectiveness of MDDR dataset clustering using ALOGP and ECFP_4 fingerprints. The best PQI value of consensus clustering methods for each column has been bold-faced for ease of reference. Table 1 Effectivenss of clustering of high diverse MDDR dataset: ALOGP Fingerprint. Table 2 Effectivenss of clustering of high diverse MDDR dataset: ECFP_4 Fingerprint. Visual inspection of the results enables comparisons to be made between the effectiveness of clustering of MDDR datasets and Ward's method, the best of choice clustering method for chemoinformatics applications. In addition, ten times of consensus clustering, for each fingerprint were observed in order to study the effectiveness of consensus clustering with different ensemble sizes. The results show that HGPA consensus clustering gives robust and novel result when K-means algorithm is run 20-50 times using ALOGP. The performance of consensus clustering outperforms the Wards' method. For consensus of dataset which represented by ECFP_4 fingerprint, the best QPI values of consensus clustering are obtained from ensembles of size n = 20-50. The performance of consensus clustering gives robust results which are better than overall performance of individual clusterings. The values of QPI in both datasets for consensus clustering are close to the Wards method. The consensus clustering, HGPA, provide stable clusters by decreasing the sensitivity to noise and outliers. The average percentages of singleton clusters of individual clusterings compared with consensus clustering for both fingerprints. The results show that consensus clustering partition the datasets with average percentage of singleton equal to zero, which is much better than individual clusterings and Wards' method. For example, 16.72% of molecules of DS1 are clustered as singletons when Wards method is applied on ALOGP fingerprint with number of clusters equal to 1000 clusters. Finally we conclude that graph-based consensus clustering can improve the effectiveness of chemical compounds clustering. The performance of consensus clustering is more robust, novel, stable, consistent, and out-perform Wards' method in case of using ALOGP fingerprint. By using ECFP_4 fingerprint, consensus clustering methods provide more robust, stable, and consistent clustering and close to the Wards clustering results. The experiments reported here suggest that graph-based consensus clustering can improve the quality of individual clustering by using the efficient algorithm, K-means algorithm, to generate the ensemble with size (20-50) for both structurally diverse chemical datasets.

3D Molecular Descriptors Important for Clinical Success

The pharmacokinetic and safety profiles of clinical drug candidates are greatly influenced by their requisite physicochemical properties. In particular, it has been shown that 2D molecular descriptors such as fraction of Sp3 carbon atoms (Fsp3) and number of stereo centers correlate with clinical success. Using the proteomic off-target hit rate of nicotinic ligands, we found that shape-based 3D descriptors such as the radius of gyration and shadow indices discriminate off-target promiscuity better than do Fsp3 and the number of stereo centers. We have deduced the relevant descriptor values required for a ligand to be nonpromiscuous. Investigating the MDL Drug Data Report (MDDR) database as compounds move from the preclinical stage toward the market, we have found that these shape-based 3D descriptors predict clinical success of compounds at preclinical and phase1 stages vs compounds withdrawn from the market better than do Fsp3 and LogD. Further, these computed 3D molecular descriptors correlate well with experimentally observed solubility, which is among well-known physicochemical properties that drive clinical success. We also found that about 84% of launched drugs satisfy either Shadow index or Fsp3 criteria, whereas withdrawn and discontinued compounds fail to meet the same criteria. Our studies suggest that spherical compounds (rather than their elongated counterparts) with a minimal number of aromatic rings may exhibit a high propensity to advance from clinical trials to market.

Voting-based consensus clustering for combining multiple clusterings of chemical structures.

BackgroundAlthough many consensus clustering methods have been successfully used for combining multiple classifiers in many areas such as machine learning, applied statistics, pattern recognition and bioinformatics, few consensus clustering methods have been applied for combining multiple clusterings of chemical structures. It is known that any individual clustering method will not always give the best results for all types of applications. So, in this paper, three voting and graph-based consensus clusterings were used for combining multiple clusterings of chemical structures to enhance the ability of separating biologically active molecules from inactive ones in each cluster.ResultsThe cumulative voting-based aggregation algorithm (CVAA), cluster-based similarity partitioning algorithm (CSPA) and hyper-graph partitioning algorithm (HGPA) were examined. The F-measure and Quality Partition Index method (QPI) were used to evaluate the clusterings and the results were compared to the Ward’s clustering method. The MDL Drug Data Report (MDDR) dataset was used for experiments and was represented by two 2D fingerprints, ALOGP and ECFP_4. The performance of voting-based consensus clustering method outperformed the Ward’s method using F-measure and QPI method for both ALOGP and ECFP_4 fingerprints, while the graph-based consensus clustering methods outperformed the Ward’s method only for ALOGP using QPI. The Jaccard and Euclidean distance measures were the methods of choice to generate the ensembles, which give the highest values for both criteria.ConclusionsThe results of the experiments show that consensus clustering methods can improve the effectiveness of chemical structures clusterings. The cumulative voting-based aggregation algorithm (CVAA) was the method of choice among consensus clustering methods.

Drug-likeness analysis of traditional Chinese medicines: 1. property distributions of drug-like compounds, non-drug-like compounds and natural compounds from traditional Chinese medicines

BackgroundIn this work, we analyzed and compared the distribution profiles of a wide variety of molecular properties for three compound classes: drug-like compounds in MDL Drug Data Report (MDDR), non-drug-like compounds in Available Chemical Directory (ACD), and natural compounds in Traditional Chinese Medicine Compound Database (TCMCD).ResultsThe comparison of the property distributions suggests that, when all compounds in MDDR, ACD and TCMCD with molecular weight lower than 600 were used, MDDR and ACD are substantially different while TCMCD is much more similar to MDDR than ACD. However, when the three subsets of ACD, MDDR and TCMCD with similar molecular weight distributions were examined, the distribution profiles of the representative physicochemical properties for MDDR and ACD do not differ significantly anymore, suggesting that after the dependence of molecular weight is removed drug-like and non-drug-like molecules cannot be effectively distinguished by simple property-based filters; however, the distribution profiles of several physicochemical properties for TCMCD are obviously different from those for MDDR and ACD. Then, the performance of each molecular property on predicting drug-likeness was evaluated. No single molecular property shows good performance to discriminate between drug-like and non-drug-like molecules. Compared with the other descriptors, fractional negative accessible surface area (FASA-) performs the best. Finally, a PCA-based scheme was used to visually characterize the spatial distributions of the three classes of compounds with similar molecular weight distributions.ConclusionIf FASA- was used as a drug-likeness filter, more than 80% molecules in TCMCD were predicted to be drug-like. Moreover, the principal component plots show that natural compounds in TCMCD have different and even more diverse distributions than either drug-like compounds in MDDR or non-drug-like compounds in ACD.

Drug-likeness Analysis of Traditional Chinese Medicines: Prediction of Drug-likeness Using Machine Learning Approaches

Quantitative or qualitative characterization of the drug-like features of known drugs may help medicinal and computational chemists to select higher quality drug leads from a huge pool of compounds and to improve the efficiency of drug design pipelines. For this purpose, the theoretical models for drug-likeness to discriminate between drug-like and non-drug-like based on molecular physicochemical properties and structural fingerprints were developed by using the naive Bayesian classification (NBC) and recursive partitioning (RP) techniques, and then the drug-likeness of the compounds from the Traditional Chinese Medicine Compound Database (TCMCD) was evaluated. First, the impact of molecular physicochemical properties and structural fingerprints on the prediction accuracy of drug-likeness was examined. We found that, compared with simple molecular properties, structural fingerprints were more essential for the accurate prediction of drug-likeness. Then, a variety of Bayesian classifiers were constructed by changing the ratio of drug-like to non-drug-like molecules and the size of the training set. The results indicate that the prediction accuracy of the Bayesian classifiers was closely related to the size and the degree of the balance of the training set. When a balanced training set was used, the best Bayesian classifier based on 21 physicochemical properties and the LCFP_6 fingerprint set yielded an overall leave-one-out (LOO) cross-validated accuracy of 91.4% for the 140,000 molecules in the training set and 90.9% for the 40,000 molecules in the test set. In addition, the RP classifiers with different maximum depth were constructed and compared with the Bayesian classifiers, and we found that the best Bayesian classifier outperformed the best RP model with respect to overall prediction accuracy. Moreover, the Bayesian classifier employing structural fingerprints highlights the important substructures favorable or unfavorable for drug-likeness, offering extra valuable information for getting high quality lead compounds in the early stage of the drug design/discovery process. Finally, the best Bayesian classifier was used to predict the drug-likeness of 33,961 compounds in TCMCD. Our calculations show that 59.37% of the molecules in TCMCD were identified as drug-like molecules, indicating that traditional Chinese medicines (TCMs) are therefore an excellent source of drug-like molecules. Furthermore, the important structural fingerprints in TCMCD were detected and analyzed. Considering that the pharmacology of TCMCD and MDDR (MDL Drug Data Report) was linked by the important common structural features, the potential pharmacology of the compounds in TCMCD may therefore be annotated by these important structural signatures identified from Bayesian analysis, which may be valuable to promote the development of TCMs.

Detecting Drug Promiscuity Using Gaussian Ensemble Screening

Polypharmacology describes the binding of a ligand to multiple protein targets (a promiscuous ligand) or multiple diverse ligands binding to a given target (a promiscuous target). Pharmaceutical companies are discovering increasing numbers of both promiscuous drugs and drug targets. Hence, polypharmacology is now recognized as an important aspect of drug design. Here, we describe a new and fast way to predict polypharmacological relationships between drug classes quantitatively, which we call Gaussian Ensemble Screening (GES). This approach represents a cluster of molecules with similar spherical harmonic surface shapes as a Gaussian distribution with respect to a selected center molecule. Calculating the Gaussian overlap between pairs of such clusters allows the similarity between drug classes to be calculated analytically without requiring thousands of bootstrap comparisons, as in current promiscuity prediction approaches. We find that such cluster similarity scores also follow a Gaussian distribution. Hence, a cluster similarity score may be transformed into a probability value, or "p-value", in order to quantify the relationships between drug classes. We present results obtained when using the GES approach to predict relationships between drug classes in a subset of the MDL Drug Data Report (MDDR) database. Our results indicate that GES is a useful way to study polypharmacology relationships, and it could provide a novel way to propose new targets for drug repositioning.