Virtual Screening of DPP-4 Inhibitors Using QSAR-Based Artificial Intelligence and Molecular Docking of Hit Compounds to DPP-8 and DPP-9 Enzymes

Hermansyah, Oky; Bustamam, Alhadi; Yanuar, Arry

doi:10.21203/rs.2.22282/v2

Cited by 3 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A particularly appealing yet somewhat less common approach to virtual screening is presented by QSAR equations derived from easy to calculate 1D, 2D and sometimes global 3D descriptors. Several such studies were reported in the literature, and in most cases, the descriptors were calculated for the ligands in their unbound states [ 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 ]. Some of these efforts were summarized in several review articles [ 29 , 30 ].…”

Section: Introductionmentioning

confidence: 99%

A Comparison between Enrichment Optimization Algorithm (EOA)-Based and Docking-Based Virtual Screening

Spiegel

Senderowitz

2021

IJMS

View full text Add to dashboard Cite

Virtual screening (VS) is a well-established method in the initial stages of many drug and material design projects. VS is typically performed using structure-based approaches such as molecular docking, or various ligand-based approaches. Most docking tools were designed to be as global as possible, and consequently only require knowledge on the 3D structure of the biotarget. In contrast, many ligand-based approaches (e.g., 3D-QSAR and pharmacophore) require prior development of project-specific predictive models. Depending on the type of model (e.g., classification or regression), predictive ability is typically evaluated using metrics of performance on either the training set (e.g.,QCV2) or the test set (e.g., specificity, selectivity or QF1/F2/F32). However, none of these metrics were developed with VS in mind, and consequently, their ability to reliably assess the performances of a model in the context of VS is at best limited. With this in mind we have recently reported the development of the enrichment optimization algorithm (EOA). EOA derives QSAR models in the form of multiple linear regression (MLR) equations for VS by optimizing an enrichment-based metric in the space of the descriptors. Here we present an improved version of the algorithm which better handles active compounds and which also takes into account information on inactive (either known inactive or decoy) compounds. We compared the improved EOA in small-scale VS experiments with three common docking tools, namely, Glide-SP, GOLD and AutoDock Vina, employing five molecular targets (acetylcholinesterase, human immunodeficiency virus type 1 protease, MAP kinase p38 alpha, urokinase-type plasminogen activator, and trypsin I). We found that EOA consistently outperformed all docking tools in terms of the area under the ROC curve (AUC) and EF1% metrics that measured the overall and initial success of the VS process, respectively. This was the case when the docking metrics were calculated based on a consensus approach and when they were calculated based on two different sets of single crystal structures. Finally, we propose that EOA could be combined with molecular docking to derive target-specific scoring functions.

show abstract

Section: Introductionmentioning

confidence: 99%

A Comparison between Enrichment Optimization Algorithm (EOA)-Based and Docking-Based Virtual Screening

Spiegel

Senderowitz

2021

IJMS

View full text Add to dashboard Cite

show abstract

“…Task type Compounds Split Metric ChEMBL(C) [23] Pre-train 1,941,410 -Accuracy ChEMBL and PubChem(CP) [24] Pre-train 103,395,400 -Accuracy ChEMBL, PubChem, and ZINC(CPZ) [25] Pre-train 775,007,514 -Accuracy Ames mutagenicity (Ames) [31] Classification 6512 Random, 8:1:1 ROC-AUC β-Secretase 1 inhibition (bace) [32] Classification 1513 Random, 8:1:1 ROC-AUC Blood-brain barrier penetration (bbbp) [33] Classification 2039 Random, 8:1:1 ROC-AUC Toxicity in honeybees (beet) [34] Classification 254 Random, 8:1:1 ROC-AUC ClinTox (Clinical trial results) [35] Classification 1478 Random, 8:1:1 ROC-AUC Aqueous Solubility (ESOL) [36] Regression 1128 Random, 8:1:1 R 2 Lipophilicity (Lipop) [23] Regression 4200 Random, 8:1:1 R 2 Free Solvation Database (FreeSolv) [37] Regression 642 Random, 8:1:1 R 2 LogS [38] Regression 4801 Random, 8:1:1 R 2 DPP-4 inhibitors (DPP4) [39] Regression 3933 Random, 8:1:1 R 2…”

Section: Datasetsmentioning

confidence: 99%

Extracting Predictive Representations from Hundreds of Millions of Molecules

Chen

Wei

Pan

2021

Preprint

View full text Add to dashboard Cite

Although deep learning can automatically extract features in relatively simple tasks such as image analysis, the construction of appropriate representations remains essential for molecular predictions due to intricate molecular complexity. Additionally, it is often expensive, time-consuming, and ethically constrained to generate labeled data for supervised learning in molecular sciences, leading to challenging small and diverse datasets. In this work, we develop a self-supervised learning approach via a masking strategy to pre-train transformer models from over 700 million unlabeled molecules in multiple databases. The intrinsic chemical logic learned from this approach enables the extraction of predictive representations from task-specific molecular sequences in a fine-tuned process. To understand the importance of self-supervised learning from unlabeled molecules, we assemble three models with different combinations of databases. Moreover, we propose a new protocol based on data traits to automatically select the optimal model for a specific predictive task. To validate the proposed representation and protocol, we consider 10 benchmark datasets in addition to 38 ligand-based virtual screening datasets. Extensive validation indicates that the proposed representation and protocol show superb performance.

show abstract

“…According to [6], a random selection of molecules can lead to a mismatch because all members of the validation data may be members of the same group, thereby resulting in a molecular set that is not representative of the real data. Thus, a method is needed that can produce a representative data set in the data partition stage [2], [6], [7].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence Paradigm for Ligand-Based Virtual Screening on the Drug Discovery of Type 2 Diabetes Mellitus

Bustamam

Hamzah

Husna

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background: New dipeptidyl peptidase-4 (DPP-4) inhibitors need to be developed to be used as agents with low adverse effects for the treatment of type 2 diabetes mellitus. This study aims to build quantitative structure-activity relationship (QSAR) models using the artificial intelligence paradigm. Random Forest and Deep Neural Network are used to predict QSAR models. We compared principal component analysis (PCA) with sparse PCA as methods for transforming Rotation Forest. K-modes clustering with Levenshtein distance was used for the selection method of molecules, and CatBoost was used for the feature selection method. Results: The amount of the DPP-4 inhibitor molecules resulting from the selection process of molecules using K-Modes clustering algorithm is 1020 with logP range value of -1.6693 to 4.99044. Several fingerprint methods such as extended connectivity fingerprint and functional class fingerprint with diameters of 4 and 6 were used to construct four fingerprint datasets, ECFP_4, ECFP_6, FCFP_4, and FCFP_6. There are 1024 features from the four fingerprint datasets that are then selected using the CatBoost method. CatBoost can represent QSAR models with good performance for machine learning and deep learning methods respectively with evaluation metrics, such as Sensitivity, Specificity, Accuracy, and Matthew's correlation coefficient, all valued above 70% with a feature importance level of 60%, 70%, 80%, and 90%.Conclusions: The K-Modes clustering algorithm can produce a representative subset of DPP-4 inhibitor molecules. Feature selection in the fingerprint dataset using CatBoost is best used before making QSAR Classification and QSAR Regression models. QSAR Classification using Machine Learning and QSAR Classification using Deep Learning, each of which has an accuracy of above 70%. The Rotation Forest (PCA) model performed better than the Rotation Forest (Sparse PCA) model, both in the QSAR Classification and QSAR Regression model because the Rotation Forest (PCA) has a more effective time than the Rotation Forest (Sparse PCA).

show abstract

Virtual Screening of DPP-4 Inhibitors Using QSAR-Based Artificial Intelligence and Molecular Docking of Hit Compounds to DPP-8 and DPP-9 Enzymes

Cited by 3 publications

References 53 publications

A Comparison between Enrichment Optimization Algorithm (EOA)-Based and Docking-Based Virtual Screening

A Comparison between Enrichment Optimization Algorithm (EOA)-Based and Docking-Based Virtual Screening

Extracting Predictive Representations from Hundreds of Millions of Molecules

Artificial Intelligence Paradigm for Ligand-Based Virtual Screening on the Drug Discovery of Type 2 Diabetes Mellitus

Contact Info

Product

Resources

About