Predicting novel drugs for SARS-CoV-2 using machine learning from a >10 million chemical space.
Ontology highlight
ABSTRACT:
SUBMITTER: Kowalewski J
PROVIDER: S-EPMC7409807 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description: Not available
| S-EPMC10715801 | biostudies-literature
Project description:Chemical compound space refers to the vast set of all possible chemical compounds, estimated to contain 1060 molecules. While intractable as a whole, modern machine learning (ML) is increasingly capable of accurately predicting molecular properties in important subsets. Here, we therefore engage in the ML-driven study of even larger reaction space. Central to chemistry as a science of transformations, this space contains all possible chemical reactions. As an important basis for 'reactive' ML, we establish a first-principles database (Rad-6) containing closed and open-shell organic molecules, along with an associated database of chemical reaction energies (Rad-6-RE). We show that the special topology of reaction spaces, with central hub molecules involved in multiple reactions, requires a modification of existing compound space ML-concepts. Showcased by the application to methane combustion, we demonstrate that the learned reaction energies offer a non-empirical route to rationally extract reduced reaction networks for detailed microkinetic analyses.
| S-EPMC7603480 | biostudies-literature
Project description:Cell-penetrating peptides (CPPs) are naturally able to cross the lipid bilayer membrane that protects cells. These peptides share common structural and physicochemical properties and show different pharmaceutical applications, among which drug delivery is the most important. Due to their ability to cross the membranes by pulling high-molecular-weight polar molecules, they are termed Trojan horses. In this study, we proposed a machine learning (ML)-based framework named BChemRF-CPPred (beyond chemical rules-based framework for CPP prediction) that uses an artificial neural network, a support vector machine, and a Gaussian process classifier to differentiate CPPs from non-CPPs, using structure- and sequence-based descriptors extracted from PDB and FASTA formats. The performance of our algorithm was evaluated by tenfold cross-validation and compared with those of previously reported prediction tools using an independent dataset. The BChemRF-CPPred satisfactorily identified CPP-like structures using natural and synthetic modified peptide libraries and also obtained better performance than those of previously reported ML-based algorithms, reaching the independent test accuracy of 90.66% (AUC = 0.9365) for PDB, and an accuracy of 86.5% (AUC = 0.9216) for FASTA input. Moreover, our analyses of the CPP chemical space demonstrated that these peptides break some molecular rules related to the prediction of permeability of therapeutic molecules in cell membranes. This is the first comprehensive analysis to predict synthetic and natural CPP structures and to evaluate their chemical space using an ML-based framework. Our algorithm is freely available for academic use at http://comptools.linc.ufpa.br/BChemRF-CPPred .
| S-EPMC8027643 | biostudies-literature
Project description:In silico prediction of chemical ecotoxicity (HC50) represents an important complement to improve in vivo and in vitro toxicological assessment of manufactured chemicals. Recent application of machine learning models to predict chemical HC50 yields variable prediction performance that depends on effectively learning chemical representations from high-dimension data. To improve HC50 prediction performance, we developed an autoencoder model by learning latent space chemical embeddings. This novel approach achieved state-of-the-art prediction performance of HC50 with R2 of 0.668 ± 0.003 and mean absolute error (MAE) of 0.572 ± 0.001, and outperformed other dimension reduction methods including principal component analysis (PCA) (R2 = 0.601 ± 0.031 and MAE = 0.629 ± 0.005), kernel PCA (R2 = 0.631 ± 0.008 and MAE = 0.625 ± 0.006), and uniform manifold approximation and projection dimensionality reduction (R2 = 0.400 ± 0.008 and MAE = 0.801 ± 0.002). A simple linear layer with chemical embeddings learned from the autoencoder model performed better than random forest (R2 = 0.663 ± 0.007 and MAE = 0.591 ± 0.008), fully connected neural network (R2 = 0.614 ± 0.016 and MAE = 0.610 ± 0.008), least absolute shrinkage and selection operator (R2 = 0.617 ± 0.037 and MAE = 0.619 ± 0.007), and ridge regression (R2 = 0.638 ± 0.007 and MAE = 0.613 ± 0.005) using unlearned raw input features. Our results highlighted the usefulness of learning latent chemical representations, and our autoencoder model provides an alternative approach for robust HC50 prediction.
| S-EPMC9044254 | biostudies-literature
Project description:Small molecule targeting of RNA has emerged as a new frontier in medicinal chemistry, but compared to the protein targeting literature our understanding of chemical matter that binds to RNA is limited. In this study, we reported Repository Of BInders to Nucleic acids (ROBIN), a new library of nucleic acid binders identified by small molecule microarray (SMM) screening. The complete results of 36 individual nucleic acid SMM screens against a library of 24 572 small molecules were reported (including a total of 1 627 072 interactions assayed). A set of 2 003 RNA-binding small molecules was identified, representing the largest fully public, experimentally derived library of its kind to date. Machine learning was used to develop highly predictive and interpretable models to characterize RNA-binding molecules. This work demonstrates that machine learning algorithms applied to experimentally derived sets of RNA binders are a powerful method to inform RNA-targeted chemical space.
| S-EPMC9992102 | biostudies-literature
Project description:The current life-threatening and tenacious pandemic eruption of coronavirus disease in 2019 (COVID-19) has posed a significant global hazard concerning high mortality rate, economic meltdown, and everyday life distress. The rapid spread of COVID-19 demands countermeasures to combat this deadly virus. Currently, there are no drugs approved by the FDA to treat COVID-19. Therefore, discovering small molecule therapeutics for treating COVID-19 infection is essential. So far, only a few small molecule inhibitors are reported for coronaviruses. There is a need to expand the small chemical space of coronaviruses inhibitors by adding potent and selective scaffolds with anti-COVID activity. In this context, the huge antiviral chemical space already available can be analysed using cheminformatic and machine learning to unearth new scaffolds. We created three specific datasets called "antiviral dataset" (N = 38,428) "drug-like antiviral dataset" (N = 20,963) and "anticorona dataset" (N = 433) for this purpose. We analyzed the 433 molecules of "anticorona dataset" for their scaffold diversity, physicochemical distributions, principal component analysis, activity cliffs, R-group decomposition, and scaffold mapping. The scaffold diversity of the "anticorona dataset" in terms of Murcko scaffold analysis demonstrates a thorough representation of diverse chemical scaffolds. However, physicochemical descriptor analysis and principal component analysis demonstrated negligible drug-like features for the "anticorona dataset" molecules. The "antiviral dataset" and "drug-like antiviral dataset" showed low scaffold diversity as measured by the Gini coefficient. The hierarchical clustering of the "antiviral dataset" against the "anticorona dataset" demonstrated little molecular similarity. We generated a library of frequent fragments and polypharmacological ligands targeting various essential viral proteins such as main protease, helicase, papain-like protease, and replicase polyprotein 1ab. Further structural and chemical features of the "anticorona dataset" were compared with SARS-CoV-2 repurposed drugs, FDA-approved drugs, natural products, and drugs currently in clinical trials. Using machine learning tool DCA (DMax Chemistry Assistant), we converted the "anticorona dataset" into an elegant hypothesis with significant functional biological relevance. Machine learning analysis uncovered that FDA approved drugs, Tizanidine HCl, Cefazolin, Raltegravir, Azilsartan, Acalabrutinib, Luliconazole, Sitagliptin, Meloxicam (Mobic), Succinyl sulfathiazole, Fluconazole, and Pranlukast could be repurposed as effective drugs for COVID-19. Fragment-based scaffold analysis and R-group decomposition uncovered pyrrolidine and the indole molecular scaffolds as the potent fragments for designing and synthesizing the novel drug-like molecules for targeting SARS-CoV-2. This comprehensive and systematic assessment of small-molecule viral therapeutics' entire chemical space realised critical insights to potentially privileged scaffolds that could aid in enrichment and rapid discovery of efficacious antiviral drugs for COVID-19.
| S-EPMC7771909 | biostudies-literature
Project description:BackgroundThe Complete Blood Count (CBC) is a commonly used low-cost test that measures white blood cells, red blood cells, and platelets in a person's blood. It is a useful tool to support medical decisions, as intrinsic variations of each analyte bring relevant insights regarding potential diseases. In this study, we aimed at developing machine learning models for COVID-19 diagnosis through CBCs, unlocking the predictive power of non-linear relationships between multiple blood analytes.MethodsWe collected 809,254 CBCs and 1,088,385 RT-PCR tests for SARS-Cov-2, of which 21% (234,466) were positive, from 900,220 unique individuals. To properly screen COVID-19, we also collected 120,807 CBCs of 16,940 individuals who tested positive for other respiratory viruses. We proposed an ensemble procedure that combines machine learning models for different respiratory infections and analyzed the results in both the first and second waves of COVID-19 cases in Brazil.ResultsWe obtain a high-performance AUROC of 90 + % for validations in both scenarios. We show that models built solely of SARS-Cov-2 data are biased, performing poorly in the presence of infections due to other RNA respiratory viruses.ConclusionsWe demonstrate the potential of a novel machine learning approach for COVID-19 diagnosis based on a CBC and show that aggregating information about other respiratory diseases was essential to guarantee robustness in the results. Given its versatile nature, low cost, and speed, we believe that our tool can be particularly useful in a variety of scenarios-both during the pandemic and after.
| S-EPMC9199341 | biostudies-literature
Project description:Increasing age is a risk factor for many diseases; therefore developing pharmacological interventions that slow down ageing and consequently postpone the onset of many age-related diseases is highly desirable. In this work we analyse data from the DrugAge database, which contains chemical compounds and their effect on the lifespan of model organisms. Predictive models were built using the machine learning method random forests to predict whether or not a chemical compound will increase Caenorhabditis elegans' lifespan, using as features Gene Ontology (GO) terms annotated for proteins targeted by the compounds and chemical descriptors calculated from each compound's chemical structure. The model with the best predictive accuracy used both biological and chemical features, achieving a prediction accuracy of 80%. The top 20 most important GO terms include those related to mitochondrial processes, to enzymatic and immunological processes, and terms related to metabolic and transport processes. We applied our best model to predict compounds which are more likely to increase C. elegans' lifespan in the DGIdb database, where the effect of the compounds on an organism's lifespan is unknown. The top hit compounds can be broadly divided into four groups: compounds affecting mitochondria, compounds for cancer treatment, anti-inflammatories, and compounds for gonadotropin-releasing hormone therapies.
| S-EPMC5559171 | biostudies-literature
Project description:Adverse drug reactions (ADRs) have become one of the primary reasons for the failure of drugs and a leading cause of deaths. Owing to the severe effects of ADRs, there is an urgent need for the generation of effective models which can accurately predict ADRs during early stages of drug development based on integration of various features of drugs. In the current study, we have focused on neurological ADRs and have used various properties of drugs that include biological properties (targets, transporters and enzymes), chemical properties (substructure fingerprints), phenotypic properties (side effects (SE) and therapeutic indications) and a combinations of the two and three levels of features. We employed relief-based feature selection technique to identify relevant properties and used machine learning approach to generated learned model systems which would predict neurological ADRs prior to preclinical testing. Additionally, in order to explain the efficiency and applicability of the models, we tested them to predict the ADRs for already existing anti-Alzheimer drugs and uncharacterized drugs, respectively in side effect resource (SIDER) database. The generated models were highly accurate and our results showed that the models based on chemical (accuracy 93.20%), phenotypic (accuracy 92.41%) and combination of three properties (accuracy 94.18%) were highly accurate while the models based on biological properties (accuracy 82.11%) were highly informative.
| S-EPMC5429831 | biostudies-literature
Project description:Homogeneous catalysis using transition metal complexes is ubiquitously used for organic synthesis, as well as technologically relevant in applications such as water splitting and CO2 reduction. The key steps underlying homogeneous catalysis require a specific combination of electronic and steric effects from the ligands bound to the metal center. Finding the optimal combination of ligands is a challenging task due to the exceedingly large number of possibilities and the non-trivial ligand-ligand interactions. The classic example of Vaska's complex, trans-[Ir(PPh3)2(CO)(Cl)], illustrates this scenario. The ligands of this species activate iridium for the oxidative addition of hydrogen, yielding the dihydride cis-[Ir(H)2(PPh3)2(CO)(Cl)] complex. Despite the simplicity of this system, thousands of derivatives can be formulated for the activation of H2, with a limited number of ligands belonging to the same general categories found in the original complex. In this work, we show how DFT and machine learning (ML) methods can be combined to enable the prediction of reactivity within large chemical spaces containing thousands of complexes. In a space of 2574 species derived from Vaska's complex, data from DFT calculations are used to train and test ML models that predict the H2-activation barrier. In contrast to experiments and calculations requiring several days to be completed, the ML models were trained and used on a laptop on a time-scale of minutes. As a first approach, we combined Bayesian-optimized artificial neural networks (ANN) with features derived from autocorrelation and deltametric functions. The resulting ANNs achieved high accuracies, with mean absolute errors (MAE) between 1 and 2 kcal mol-1, depending on the size of the training set. By using a Gaussian process (GP) model trained with a set of selected features, including fingerprints, accuracy was further enhanced. Remarkably, this GP model minimized the MAE below 1 kcal mol-1, by using only 20% or less of the data available for training. The gradient boosting (GB) method was also used to assess the relevance of the features, which was used for both feature selection and model interpretation purposes. Features accounting for chemical composition, atom size and electronegativity were found to be the most determinant in the predictions. Further, the ligand fragments with the strongest influence on the H2-activation barrier were identified.
| S-EPMC7659707 | biostudies-literature