Computational models for tuberculosis drug discovery

Bayesian Modeling and Intrabacterial Drug Metabolism Applied to Drug-Resistant Staphylococcus aureus

We present the application of Bayesian modeling to identify chemical tools and/or drug discovery entities pertinent to drug-resistant Staphylococcus aureus infections. The quinoline JSF-3151 was predicted by modeling and then empirically demonstrated to be active against in vitro cultured clinical methicillin- and vancomycin-resistant strains while also exhibiting efficacy in a mouse peritonitis model of methicillin-resistant S. aureus infection. We highlight the utility of an intrabacterial drug metabolism (IBDM) approach to probe the mechanism by which JSF-3151 is transformed within the bacteria. We also identify and then validate two mechanisms of resistance in S. aureus: one mechanism involves increased expression of a lipocalin protein, and the other arises from the loss of function of an azoreductase. The computational and experimental approaches, discovery of an antibacterial agent, and elucidated resistance mechanisms collectively hold promise to advance our understanding of therapeutic regimens for drug-resistant S. aureus.

Machine Learning Platform to Discover Novel Growth Inhibitors of Neisseria gonorrhoeae

PURPOSE

To advance fundamental biological and translational research with the bacterium Neisseria gonorrhoeae through the prediction of novel small molecule growth inhibitors via naïve Bayesian modeling methodology.

METHODS

Inspection and curation of data from the publicly available ChEMBL web site for small molecule growth inhibition data of the bacterium Neisseria gonorrhoeae resulted in a training set for the construction of machine learning models. A naïve Bayesian model for bacterial growth inhibition was utilized in a workflow to predict novel antibacterial agents against this bacterium of global health relevance from a commercial library of >10⁵ drug-like small molecules. Follow-up efforts involved empirical assessment of the predictions and validation of the hits.

RESULTS

Specifically, two small molecules were found that exhibited promising activity profiles and represent novel chemotypes for agents against N. gonorrrhoeae.

CONCLUSIONS

This represents, to the best of our knowledge, the first machine learning approach to successfully predict novel growth inhibitors of this bacterium. To assist the chemical tool and drug discovery fields, we have made our curated training set available as part of the Supplementary Material and the Bayesian model is accessible via the web. Graphical Abstract.

GCAC: galaxy workflow system for predictive model building for virtual screening

Background

Traditional drug discovery approaches are time-consuming, tedious and expensive. Identifying a potential drug-like molecule using high throughput screening (HTS) with high confidence is always a challenging task in drug discovery and cheminformatics. A small percentage of molecules that pass the clinical trial phases receives FDA approval. This whole process takes 10–12 years and millions of dollar of investment. The inconsistency in HTS is also a challenge for reproducible results. Reproducible research in computational research is highly desirable as a measure to evaluate scientific claims and published findings. This paper describes the development and availability of a knowledge based predictive model building system using the R Statistical Computing Environment and its ensured reproducibility using Galaxy workflow system.

Results

We describe a web-enabled data mining analysis pipeline which employs reproducible research approaches to confront the issue of availability of tools in high throughput virtual screening. The pipeline, named as “Galaxy for Compound Activity Classification (GCAC)” includes descriptor calculation, feature selection, model building, and screening to extract potent candidates, by leveraging the combined capabilities of R statistical packages and literate programming tools contained within a workflow system environment with automated configuration.

Conclusion

GCAC can serve as a standard for screening drug candidates using predictive model building under galaxy environment, allowing for easy installation and reproducibility. A demo site of the tool is available at http://ccbb.jnu.ac.in/gcac

Electronic supplementary material

The online version of this article (10.1186/s12859-018-2492-8) contains supplementary material, which is available to authorized users.

Virtual screening and repositioning of inconclusive molecules of beta-lactamase Bioassays-A data mining approach

This study focuses on the best possible way forward in utilizing inconclusive molecules of PubChem bioassays AID 1332, AID 434987 and AID 434955, which are related to beta-lactamase inhibitors of Mycobacterium tuberculosis (Mtb). The inadequacy in the experimental methods that were observed during the invitro screening resulted in an inconclusive dataset. This could be due to certain moieties present within the molecules. In order to reconsider such molecules, insilico methods can be suggested in place of invitro methods For instance, datamining and medicinal chemistry methods: have been adopted to prioritise the inconclusive dataset into active or inactive molecules. These include the Random Forest algorithm for dataminning, Lilly MedChem rules for virtually screening out the promiscuity, and Self Organizing Maps (SOM) for clustering the active molecules and enlisting them for repositioning through the use of artificial neural networks. These repositioned molecules could then be prioritized for downstream drug discovery analysis.

Collaborative drug discovery for More Medicines for Tuberculosis (MM4TB)

Neglected disease drug discovery is generally poorly funded compared with major diseases and hence there is an increasing focus on collaboration and precompetitive efforts such as public-private partnerships (PPPs). The More Medicines for Tuberculosis (MM4TB) project is one such collaboration funded by the EU with the goal of discovering new drugs for tuberculosis. Collaborative Drug Discovery has provided a commercial web-based platform called CDD Vault which is a hosted collaborative solution for securely sharing diverse chemistry and biology data. Using CDD Vault alongside other commercial and free cheminformatics tools has enabled support of this and other large collaborative projects, aiding drug discovery efforts and fostering collaboration. We will describe CDD's efforts in assisting with the MM4TB project.

Computational Analysis and Predictive Cheminformatics Modeling of Small Molecule Inhibitors of Epigenetic Modifiers

BACKGROUND

The dynamic and differential regulation and expression of genes is majorly governed by the complex interactions of a subset of biomolecules in the cell operating at multiple levels starting from genome organisation to protein post-translational regulation. The regulatory layer contributed by the epigenetic layer has been one of the favourite areas of interest recently. This layer of regulation as we know today largely comprises of DNA modifications, histone modifications and noncoding RNA regulation and the interplay between each of these major components. Epigenetic regulation has been recently shown to be central to development of a number of disease processes. The availability of datasets of high-throughput screens for molecules for biological properties offer a new opportunity to develop computational methodologies which would enable in-silico screening of large molecular libraries.

METHODS

In the present study, we have used data from high throughput screens for the inhibitors of epigenetic modifiers. Computational predictive models were constructed based on the molecular descriptors. Machine learning algorithms for supervised training, Naive Bayes and Random Forest, were used to generate predictive models for the small molecule inhibitors of histone methyl-transferases and demethylases. Random forest, with the accuracy of 80%, was identified as the most accurate classifier. Further we complemented the study with substructure search approach filtering out the probable pharmacophores from the active molecules leading to drug molecules.

RESULTS

We show that effective use of appropriate computational algorithms could be used to learn molecular and structural correlates of biological activities of small molecules. The computational models developed could be potentially used to screen and identify potential new biological activities of molecules from large molecular libraries and prioritise them for in-depth biological assays. To the best of our knowledge, this is the first and most comprehensive computational analysis towards understanding activities of small molecules inhibitors of epigenetic modifiers.

Predicting Mouse Liver Microsomal Stability with "Pruned" Machine Learning Models and Public Data

PURPOSE

Mouse efficacy studies are a critical hurdle to advance translational research of potential therapeutic compounds for many diseases. Although mouse liver microsomal (MLM) stability studies are not a perfect surrogate for in vivo studies of metabolic clearance, they are the initial model system used to assess metabolic stability. Consequently, we explored the development of machine learning models that can enhance the probability of identifying compounds possessing MLM stability.

METHODS

Published assays on MLM half-life values were identified in PubChem, reformatted, and curated to create a training set with 894 unique small molecules. These data were used to construct machine learning models assessed with internal cross-validation, external tests with a published set of antitubercular compounds, and independent validation with an additional diverse set of 571 compounds (PubChem data on percent metabolism).

RESULTS

"Pruning" out the moderately unstable / moderately stable compounds from the training set produced models with superior predictive power. Bayesian models displayed the best predictive power for identifying compounds with a half-life ≥1 h.

CONCLUSIONS

Our results suggest the pruning strategy may be of general benefit to improve test set enrichment and provide machine learning models with enhanced predictive value for the MLM stability of small organic molecules. This study represents the most exhaustive study to date of using machine learning approaches with MLM data from public sources.

Combining Metabolite-Based Pharmacophores with Bayesian Machine Learning Models for Mycobacterium tuberculosis Drug Discovery

Integrated computational approaches for Mycobacterium tuberculosis (Mtb) are useful to identify new molecules that could lead to future tuberculosis (TB) drugs. Our approach uses information derived from the TBCyc pathway and genome database, the Collaborative Drug Discovery TB database combined with 3D pharmacophores and dual event Bayesian models of whole-cell activity and lack of cytotoxicity. We have prioritized a large number of molecules that may act as mimics of substrates and metabolites in the TB metabolome. We computationally searched over 200,000 commercial molecules using 66 pharmacophores based on substrates and metabolites from Mtb and further filtering with Bayesian models. We ultimately tested 110 compounds in vitro that resulted in two compounds of interest, BAS 04912643 and BAS 00623753 (MIC of 2.5 and 5 μg/mL, respectively). These molecules were used as a starting point for hit-to-lead optimization. The most promising class proved to be the quinoxaline di-N-oxides, evidenced by transcriptional profiling to induce mRNA level perturbations most closely resembling known protonophores. One of these, SRI58 exhibited an MIC = 1.25 μg/mL versus Mtb and a CC₅₀ in Vero cells of >40 μg/mL, while featuring fair Caco-2 A-B permeability (2.3 x 10⁻⁶ cm/s), kinetic solubility (125 μM at pH 7.4 in PBS) and mouse metabolic stability (63.6% remaining after 1 h incubation with mouse liver microsomes). Despite demonstration of how a combined bioinformatics/cheminformatics approach afforded a small molecule with promising in vitro profiles, we found that SRI58 did not exhibit quantifiable blood levels in mice.

Open Source Bayesian Models. 2. Mining a "Big Dataset" To Create and Validate Models with ChEMBL

In an associated paper, we have described a reference implementation of Laplacian-corrected naïve Bayesian model building using extended connectivity (ECFP)- and molecular function class fingerprints of maximum diameter 6 (FCFP)-type fingerprints. As a follow-up, we have now undertaken a large-scale validation study in order to ensure that the technique generalizes to a broad variety of drug discovery datasets. To achieve this, we have used the ChEMBL (version 20) database and split it into more than 2000 separate datasets, each of which consists of compounds and measurements with the same target and activity measurement. In order to test these datasets with the two-state Bayesian classification, we developed an automated algorithm for detecting a suitable threshold for active/inactive designation, which we applied to all collections. With these datasets, we were able to establish that our Bayesian model implementation is effective for the large majority of cases, and we were able to quantify the impact of fingerprint folding on the receiver operator curve cross-validation metrics. We were also able to study the impact that the choice of training/testing set partitioning has on the resulting recall rates. The datasets have been made publicly available to be downloaded, along with the corresponding model data files, which can be used in conjunction with the CDK and several mobile apps. We have also explored some novel visualization methods which leverage the structural origins of the ECFP/FCFP fingerprints to attribute regions of a molecule responsible for positive and negative contributions to activity. The ability to score molecules across thousands of relevant datasets across organisms also may help to access desirable and undesirable off-target effects as well as suggest potential targets for compounds derived from phenotypic screens.

A common feature pharmacophore for FDA-approved drugs inhibiting the Ebola virus

We are currently faced with a global infectious disease crisis which has been anticipated for decades. While many promising biotherapeutics are being tested, the search for a small molecule has yet to deliver an approved drug or therapeutic for the Ebola or similar filoviruses that cause haemorrhagic fever. Two recent high throughput screens published in 2013 did however identify several hits that progressed to animal studies that are FDA approved drugs used for other indications. The current computational analysis uses these molecules from two different structural classes to construct a common features pharmacophore. This ligand-based pharmacophore implicates a possible common target or mechanism that could be further explored. A recent structure based design project yielded nine co-crystal structures of pyrrolidinone inhibitors bound to the viral protein 35 (VP35). When receptor-ligand pharmacophores based on the analogs of these molecules and the protein structures were constructed, the molecular features partially overlapped with the common features of solely ligand-based pharmacophore models based on FDA approved drugs. These previously identified FDA approved drugs with activity against Ebola were therefore docked into this protein. The antimalarials chloroquine and amodiaquine docked favorably in VP35. We propose that these drugs identified to date as inhibitors of the Ebola virus may be targeting VP35. These computational models may provide preliminary insights into the molecular features that are responsible for their activity against Ebola virus in vitro and in vivo and we propose that this hypothesis could be readily tested.

A common feature pharmacophore for FDA-approved drugs inhibiting the Ebola virus

We are currently faced with a global infectious disease crisis which has been anticipated for decades. While many promising biotherapeutics are being tested, the search for a small molecule has yet to deliver an approved drug or therapeutic for the Ebola or similar filoviruses that cause haemorrhagic fever. Two recent high throughput screens published in 2013 did however identify several hits that progressed to animal studies that are FDA approved drugs used for other indications. The current computational analysis uses these molecules from two different structural classes to construct a common features pharmacophore. This ligand-based pharmacophore implicates a possible common target or mechanism that could be further explored. A recent structure based design project yielded nine co-crystal structures of pyrrolidinone inhibitors bound to the viral protein 35 (VP35). When receptor-ligand pharmacophores based on the analogs of these molecules and the protein structures were constructed, the molecular features partially overlapped with the common features of solely ligand-based pharmacophore models based on FDA approved drugs. These previously identified FDA approved drugs with activity against Ebola were therefore docked into this protein. The antimalarials chloroquine and amodiaquine docked favorably in VP35. We propose that these drugs identified to date as inhibitors of the Ebola virus may be targeting VP35. These computational models may provide preliminary insights into the molecular features that are responsible for their activity against Ebola virus in vitro and in vivo and we propose that this hypothesis could be readily tested.

Bigger data, collaborative tools and the future of predictive drug discovery

Over the past decade we have seen a growth in the provision of chemistry data and cheminformatics tools as either free websites or software as a service commercial offerings. These have transformed how we find molecule-related data and use such tools in our research. There have also been efforts to improve collaboration between researchers either openly or through secure transactions using commercial tools. A major challenge in the future will be how such databases and software approaches handle larger amounts of data as it accumulates from high throughput screening and enables the user to draw insights, enable predictions and move projects forward. We now discuss how information from some drug discovery datasets can be made more accessible and how privacy of data should not overwhelm the desire to share it at an appropriate time with collaborators. We also discuss additional software tools that could be made available and provide our thoughts on the future of predictive drug discovery in this age of big data. We use some examples from our own research on neglected diseases, collaborations, mobile apps and algorithm development to illustrate these ideas.

Are bigger data sets better for machine learning? Fusing single-point and dual-event dose response data for Mycobacterium tuberculosis

Tuberculosis is a major, neglected disease for which the quest to find new treatments continues. There is an abundance of data from large phenotypic screens in the public domain against Mycobacterium tuberculosis (Mtb). Since machine learning methods can learn from past data, we were interested in addressing whether more data builds better models. We now describe using Bayesian machine learning to assess whether we can improve our models by combining the large quantities of single-point data with the much smaller (higher quality) dual-event data sets, which use both dose-response data for both whole-cell antitubercular activity and Vero cell cytotoxicity. We have evaluated 12 models ranging from different single-point, dual-event dose-response, single-point and dual-event dose-response as well as combined data sets for three distinct data sets from the same laboratory. We used a fourth data set of active and inactive compounds from the same group as well as a smaller set of 177 active compounds from GlaxoSmithKline as test sets. Our data suggest combining single-point with dual-event dose-response data does not diminish the internal or external predictive ability of the models based on the receiver operator curve (ROC) for these models (internal ROC range 0.83-0.91, external ROC range 0.62-0.83) compared to the orders of magnitude smaller dual-event models (internal ROC range 0.6-0.83 and external ROC 0.54-0.83). In conclusion, models developed with 1200-5000 compounds appear to be as predictive as those generated with 25 000-350 000 molecules. Our results have implications for justifying further high-throughput screening versus focused testing based on model predictions.

Looking back to the future: predicting in vivo efficacy of small molecules versus Mycobacterium tuberculosis

Selecting and translating in vitro leads for a disease into molecules with in vivo activity in an animal model of the disease is a challenge that takes considerable time and money. As an example, recent years have seen whole-cell phenotypic screens of millions of compounds yielding over 1500 inhibitors of Mycobacterium tuberculosis (Mtb). These must be prioritized for testing in the mouse in vivo assay for Mtb infection, a validated model utilized to select compounds for further testing. We demonstrate learning from in vivo active and inactive compounds using machine learning classification models (Bayesian, support vector machines, and recursive partitioning) consisting of 773 compounds. The Bayesian model predicted 8 out of 11 additional in vivo actives not included in the model as an external test set. Curation of 70 years of Mtb data can therefore provide statistically robust computational models to focus resources on in vivo active small molecule antituberculars. This highlights a cost-effective predictor for in vivo testing elsewhere in other diseases.

Bayesian models for screening and TB Mobile for target inference with Mycobacterium tuberculosis

The search for compounds active against Mycobacterium tuberculosis is reliant upon high-throughput screening (HTS) in whole cells. We have used Bayesian machine learning models which can predict anti-tubercular activity to filter an internal library of over 150,000 compounds prior to in vitro testing. We used this to select and test 48 compounds in vitro; 11 were active with MIC values ranging from 0.4 μM to 10.2 μM, giving a high hit rate of 22.9%. Among the hits, we identified several compounds belonging to the same series including five quinolones (including ciprofloxacin), three molecules with long aliphatic linkers and three singletons. This approach represents a rapid method to prioritize compounds for testing that can be used alongside medicinal chemistry insight and other filters to identify active molecules. Such models can significantly increase the hit rate of HTS, above the usual 1% or lower rates seen. In addition, the potential targets for the 11 molecules were predicted using TB Mobile and clustering alongside a set of over 740 molecules with known M. tuberculosis target annotations. These predictions may serve as a mechanism for prioritizing compounds for further optimization.

Fusing dual-event data sets for Mycobacterium tuberculosis machine learning models and their evaluation

The search for new tuberculosis treatments continues as we need to find molecules that can act more quickly, be accommodated in multidrug regimens, and overcome ever increasing levels of drug resistance. Multiple large scale phenotypic high-throughput screens against Mycobacterium tuberculosis (Mtb) have generated dose response data, enabling the generation of machine learning models. These models also incorporated cytotoxicity data and were recently validated with a large external data set. A cheminformatics data-fusion approach followed by Bayesian machine learning, Support Vector Machine, or Recursive Partitioning model development (based on publicly available Mtb screening data) was used to compare individual data sets and subsequent combined models. A set of 1924 commercially available molecules with promising antitubercular activity (and lack of relative cytotoxicity to Vero cells) were used to evaluate the predictive nature of the models. We demonstrate that combining three data sets incorporating antitubercular and cytotoxicity data in Vero cells from our previous screens results in external validation receiver operator curve (ROC) of 0.83 (Bayesian or RP Forest). Models that do not have the highest 5-fold cross-validation ROC scores can outperform other models in a test set dependent manner. We demonstrate with predictions for a recently published set of Mtb leads from GlaxoSmithKline that no single machine learning model may be enough to identify compounds of interest. Data set fusion represents a further useful strategy for machine learning construction as illustrated with Mtb. Coverage of chemistry and Mtb target spaces may also be limiting factors for the whole-cell screening data generated to date.

Curing TB with open science

There are many funded efforts going on focused on tuberculosis research and drug or vaccine development. There is little if any global coordination or collaboration and subsequently there are likely to be huge data silos and duplication of efforts. We now propose steps to remedy this by fostering more open science in TB research.

Computational models for neglected diseases: gaps and opportunities

Neglected diseases, such as Chagas disease, African sleeping sickness, and intestinal worms, affect millions of the world's poor. They disproportionately affect marginalized populations, lack effective treatments or vaccines, or existing products are not accessible to the populations affected. Computational approaches have been used across many of these diseases for various aspects of research or development, and yet data produced by computational approaches are not integrated and widely accessible to others. Here, we identify gaps in which computational approaches have been used for some neglected diseases and not others. We also make recommendations for the broad-spectrum integration of these techniques into a neglected disease drug discovery and development workflow.