Neural computational prediction of oral drug absorption based on CODES 2D descriptors

Integrating (deep) machine learning and cheminformatics for predicting human intestinal absorption of small molecules

The oral route is the most preferred route for drug delivery, due to which the largest share of the pharmaceutical market is represented by oral drugs. Human intestinal absorption (HIA) is closely related to oral bioavailability making it an important factor in predicting drug absorption. In this study, we focus on predicting drug permeability at HIA as a marker for oral bioavailability. A set of 2648 compounds were collected from some early as well as recent works and curated to build a robust dataset. Five machine learning (ML) algorithms have been trained with a set of molecular descriptors of these compounds which have been selected after rigorous feature engineering. Additionally, two deep learning models - graph convolution neural network (GCNN) and graph attention network (GAT) based model were developed using the same set of compounds to exploit the predictability with automated extracted features. The numerical analyses show that out the five ML models, Random forest and LightGBM could predict with an accuracy of 87.71 % and 86.04 % on the test set and 81.43 % and 77.30 % with the external validation set respectively. Whereas with the GCNN and GAT based models, the final accuracy achieved was 77.69 % and 78.58 % on test set and 79.29 % and 79.42 % on the external validation set respectively. We believe deployment of these models for screening oral drugs can provide promising results and therefore deposited the dataset and models on the GitHub platform (https://github.com/hridoy69/HIA).

Transcriptome comparisons of in vitro intestinal epithelia grown under static and microfluidic gut-on-chip conditions with in vivo human epithelia

Gut-on-chip devices enable exposure of cells to a continuous flow of culture medium, inducing shear stresses and could thus better recapitulate the in vivo human intestinal environment in an in vitro epithelial model compared to static culture methods. We aimed to study if dynamic culture conditions affect the gene expression of Caco-2 cells cultured statically or dynamically in a gut-on-chip device and how these gene expression patterns compared to that of intestinal segments in vivo. For this we applied whole genome transcriptomics. Dynamic culture conditions led to a total of 5927 differentially expressed genes (3280 upregulated and 2647 downregulated genes) compared to static culture conditions. Gene set enrichment analysis revealed upregulated pathways associated with the immune system, signal transduction and cell growth and death, and downregulated pathways associated with drug metabolism, compound digestion and absorption under dynamic culture conditions. Comparison of the in vitro gene expression data with transcriptome profiles of human in vivo duodenum, jejunum, ileum and colon tissue samples showed similarities in gene expression profiles with intestinal segments. It is concluded that both the static and the dynamic gut-on-chip model are suitable to study human intestinal epithelial responses as an alternative for animal models.

PTML Model of ChEMBL Compounds Assays for Vitamin Derivatives

Determining the biological activity of vitamin derivatives is needed given that organic synthesis of analogs of vitamins is an active field of interest for medicinal chemistry, pharmaceuticals, and food additives. Accordingly, scientists from different disciplines perform preclinical assays (n_ij) with a considerable combination of assay conditions (c_j). Indeed, the ChEMBL platform contains a database that includes results from 36 220 different biological activity bioassays of 21 240 different vitamins and vitamin derivatives. These assays present are heterogeneous in terms of assay combinations of c_j. They are focused on >500 different biological activity parameters (c₀), >340 different targets (c₁), >6200 types of cell (c₂), >120 organisms of assay (c₃), and >60 assay strains (c₄). It includes a total of >1850 niacin assays, >1580 tretinoin assays, >1580 retinol assays, 857 ascorbic acid assays, etc. Given the complexity of this combinatorial data in terms of being assimilated by researchers, we propose to build a model by combining perturbation theory (PT) and machine learning (ML). Through this study, we propose a PTML (PT + ML) combinatorial model for ChEMBL results on biological activity of vitamins and vitamins derivatives. The linear discriminant analysis (LDA) model presented the following results for training subset a: specificity (%) = 90.38, sensitivity (%) = 87.51, and accuracy (%) = 89.89. The model showed the following results for the external validation subset: specificity (%) = 90.58, sensitivity (%) = 87.72, and accuracy (%) = 90.09. Different types of linear and nonlinear PTML models, such as logistic regression (LR), classification tree (CT), näive Bayes (NB), and random Forest (RF), were applied to contrast the capacity of prediction. The PTML-LDA model predicts with more accuracy by applying combinatorial descriptors. In addition, a PCA experiment with chemical structure descriptors allowed us to characterize the high structural diversity of the chemical space studied. In any case, PTML models using chemical structure descriptors do not improve the performance of the PTML-LDA model based on ALOGP and PSA. We can conclude that the three variable PTML-LDA model is a simplified and adaptable tool for the prediction, for different experiment combinations, the biological activity of derivative vitamins.

Synthesis, biological evaluation and computational study of novel isoniazid containing 4H-Pyrimido[2,1-b]benzothiazoles derivatives

Synthesis of novel and potent hit molecules has an eternal demand. It is our continuous study to search novel bioactive hit molecules and as a part of this, a series of novel N'-isonicotinoyl-2-methyl-4-(pyridin-2-yl)-4H-benzo[4,5]thiazolo[3,2-a]pyrimidine-3-carbohydrazide analogs (5a-5n) were synthesized with good yields by the conventional method. The various novel compounds have been characterized and identified by many analytical technique such as IR, ¹H NMR, ¹³C NMR, mass spectral analysis, and elemental analysis. All the synthetic analogs (5a-5n) are evaluated for their in vitro antibacterial and anti-mycobacterial activities against different bacterial strains. Molecular docking and Molecular dynamics studies were helped in revealing the mode of action of these compounds through their interactions with the active site of the Mycobacterium tuberculosis enoyl reductase (InhA) enzyme. The calculated ADMET descriptors for the synthesized compounds validated good pharmacokinetic properties, confirming that these compounds could be used as templates for the development of new Anti-mycobacterial agents.

A novel adaptive ensemble classification framework for ADME prediction

AECF is a GA based ensemble method. It includes four components which are (1) data balancing, (2) generating individual models, (3) combining individual models, and (4) optimizing the ensemble.

Hybridizing Feature Selection and Feature Learning Approaches in QSAR Modeling for Drug Discovery

Quantitative structure-activity relationship modeling using machine learning techniques constitutes a complex computational problem, where the identification of the most informative molecular descriptors for predicting a specific target property plays a critical role. Two main general approaches can be used for this modeling procedure: feature selection and feature learning. In this paper, a performance comparative study of two state-of-art methods related to these two approaches is carried out. In particular, regression and classification models for three different issues are inferred using both methods under different experimental scenarios: two drug-like properties, such as blood-brain-barrier and human intestinal absorption, and enantiomeric excess, as a measurement of purity used for chiral substances. Beyond the contrastive analysis of feature selection and feature learning methods as competitive approaches, the hybridization of these strategies is also evaluated based on previous results obtained in material sciences. From the experimental results, it can be concluded that there is not a clear winner between both approaches because the performance depends on the characteristics of the compound databases used for modeling. Nevertheless, in several cases, it was observed that the accuracy of the models can be improved by combining both approaches when the molecular descriptor sets provided by feature selection and feature learning contain complementary information.

Novel Imidazo[4,5-c][1,2,6]thiadiazine 2,2-dioxides as antiproliferative trypanosoma cruzi drugs: Computational screening from neural network, synthesis and in vivo biological properties

A new family of imidazo[4,5-c][1,2,6]thiadiazine 2,2-dioxide with antiproliferative Trypanosoma cruzi properties was identified from a neural network model published by our group. The synthesis and evaluation of this new class of trypanocidal agents are described. These compounds inhibit the growth of Trypanosoma cruzi, comparable with benznidazole or nifurtimox. In vitro assays were performed to study their effects on the growth of the epimastigote form of the Tulahuen 2 strain, as well as the epimastigote and amastigote forms of CL clone B5 of Trypanosoma cruzi. To verify selectivity towards parasite cells, the non-specific cytotoxicity of the most relevant compounds was studied in mammalian cells, i.e. J774 murine macrophages and NCTC clone 929 fibroblasts. Furthermore, these compounds were assayed regarding the inhibition of cruzipain. In vivo studies revealed that one of the compounds, 19, showed interesting trypanocidal activity, and could be a very promising candidate for the treatment of Chagas disease.

Predicting human intestinal absorption with modified random forest approach: a comprehensive evaluation of molecular representation, unbalanced data, and applicability domain issues

A relatively larger dataset consisting of 970 compounds was collected. Classification RF models were established based on different training sets and different descriptors. model validation and evaluation.

Predicting human intestinal absorption of diverse chemicals using ensemble learning based QSAR modeling approaches

Human intestinal absorption (HIA) of the drugs administered through the oral route constitutes an important criterion for the candidate molecules. The computational approach for predicting the HIA of molecules may potentiate the screening of new drugs. In this study, ensemble learning (EL) based qualitative and quantitative structure-activity relationship (SAR) models (gradient boosted tree, GBT and bagged decision tree, BDT) have been established for the binary classification and HIA prediction of the chemicals, using the selected molecular descriptors. The structural diversity of the chemicals and the nonlinear structure in the considered data were tested by the similarity index and Brock-Dechert-Scheinkman statistics. The external predictive power of the developed SAR models was evaluated through the internal and external validation procedures recommended in the literature. All the statistical criteria parameters derived for the performance of the constructed SAR models were above their respective thresholds suggesting for their robustness for future applications. In complete data, the qualitative SAR models rendered classification accuracy of >99%, while the quantitative SAR models yielded correlation (R(2)) of >0.91 between the measured and predicted HIA values. The performances of the EL-based SAR models were also compared with the linear models (linear discriminant analysis, LDA and multiple linear regression, MLR). The GBT and BDT SAR models performed better than the LDA and MLR methods. A comparison of our models with the previously reported QSARs for HIA prediction suggested for their better performance. The results suggest for the appropriateness of the developed SAR models to reliably predict the HIA of structurally diverse chemicals and can serve as useful tools for the initial screening of the molecules in the drug development process.

Systems Pharmacology Dissecting Holistic Medicine for Treatment of Complex Diseases: An Example Using Cardiocerebrovascular Diseases Treated by TCM

Holistic medicine is an interdisciplinary field of study that integrates all types of biological information (protein, small molecules, tissues, organs, external environmental signals, etc.) to lead to predictive and actionable models for health care and disease treatment. Despite the global and integrative character of this discipline, a comprehensive picture of holistic medicine for the treatment of complex diseases is still lacking. In this study, we develop a novel systems pharmacology approach to dissect holistic medicine in treating cardiocerebrovascular diseases (CCDs) by TCM (traditional Chinese medicine). Firstly, by applying the TCM active ingredients screened out by a systems-ADME process, we explored and experimentalized the signed drug-target interactions for revealing the pharmacological actions of drugs at a molecule level. Then, at a/an tissue/organ level, the drug therapeutic mechanisms were further investigated by a target-organ location method. Finally, a translational integrating pathway approach was applied to extract the diseases-therapeutic modules for understanding the complex disease and its therapy at systems level. For the first time, the feature of the drug-target-pathway-organ-cooperations for treatment of multiple organ diseases in holistic medicine was revealed, facilitating the development of novel treatment paradigm for complex diseases in the future.

Identification in silico and experimental validation of novel phosphodiesterase 7 inhibitors with efficacy in experimental autoimmune encephalomyelitis mice

A neural network model has been developed to predict the inhibitory capacity of any chemical structure to be a phosphodiesterase 7 (PDE7) inhibitor, a new promising kind of drugs for the treatment of neurological disorders. The numerical definition of the structures was achieved using CODES program. Through the validation of this neural network model, a novel family of 5-imino-1,2,4-thiadiazoles (ITDZs) has been identified as inhibitors of PDE7. Experimental extensive biological studies have demonstrated the ability of ITDZs to inhibit PDE7 and to increase intracellular levels of cAMP. Among them, the derivative 15 showed a high in vitro potency with desirable pharmacokinetic profile (safe genotoxicity and blood brain barrier penetration). Administration of ITDZ 15 in an experimental autoimmune encephalomyelitis (EAE) mouse model results in a significant attenuation of clinical symptoms, showing the potential of ITDZs, especially compound 15, for the effective treatment of multiple sclerosis.

QSPR studies on soot-water partition coefficients of persistent organic pollutants by using artificial neural network

Two quantitative structure property relationship (QSPR) models for predicting soot-water partition coefficients (K(sc)) of 25 persistent organic pollutants (POPs) were developed. One model was established with linear artificial neural network (L-ANN), the other model was developed by using back propagation artificial neural network (BP-ANN). Leave one out cross validation was adopted to assess the predictive ability of the developed models. For the L-ANN model, the square of correlation coefficient (R(2)) between the predicted and experimental log K(SC) is 0.8358 and the RMS%RE is 6.32 for all the compounds. For the BP-ANN model, R(2) is 0.9628 and the RMS%RE is 4.12 for all the compounds. The result of leave one out cross validation demonstrates that both L-ANN and BP-ANN are practicable for developing the QSPR model for K(SC) of the investigated POPs. However, the model established with BP-ANN is better than the model established with L-ANN in prediction accuracy. It is shown that BP-ANN is a promising method for developing QSPR models for K(SC) of POPs.