Multi-omics profiling of a CHO cell culture system unravels the effect of culture pH on cell growth, antibody titer, and product quality.

A robust monoclonal antibody (mAb) bioprocess requires physiological parameters such as temperature, pH, or dissolved oxygen to be well-controlled as even small variations in them could potentially impact the final product quality. For instance, pH substantially affects N-glycosylation, protein aggregation, and charge variant profiles, as well as mAb productivity. However, relatively less is known about how pH jointly influences product quality and titer. In this study, we investigated the effect of pH on culture performance, product titer, and quality profiles by applying longitudinal multi-omics profiling, including transcriptomics, proteomics, metabolomics, and glycomics, at three different culture pH set points. The subsequent systematic analysis of multi-omics data showed that pH set points differentially regulated various intracellular pathways including intracellular vesicular trafficking, cell cycle, and apoptosis, thereby resulting in differences in specific productivity, product titer, and quality profiles. In addition, a time-dependent variation in mAb N-glycosylation profiles, independent of pH, was identified to be mainly due to the accumulation of mAb proteins in the endoplasmic reticulum disrupting cellular homeostasis over culture time. Overall, this multi-omics-based study provides an in-depth understanding of the intracellular processes in mAb-producing CHO cell line under varied pH conditions, and could serve as a baseline for enabling the quality optimization and control of mAb production.

Extreme Gradient Boosting as a Method for Quantitative Structure-Activity Relationships.

In the pharmaceutical industry it is common to generate many QSAR models from training sets containing a large number of molecules and a large number of descriptors. The best QSAR methods are those that can generate the most accurate predictions but that are not overly expensive computationally. In this paper we compare eXtreme Gradient Boosting (XGBoost) to random forest and single-task deep neural nets on 30 in-house data sets. While XGBoost has many adjustable parameters, we can define a set of standard parameters at which XGBoost makes predictions, on the average, better than those of random forest and almost as good as those of deep neural nets. The biggest strength of XGBoost is its speed. Whereas efficient use of random forest requires generating each tree in parallel on a cluster, and deep neural nets are usually run on GPUs, XGBoost can be run on a single CPU in less than a third of the wall-clock time of either of the other methods.

Analysis of the ToxCast Chemical-Assay Space Using the Comparative Toxicogenomics Database.

Many studies have attempted to predict in vivo hazards based on the ToxCast in vitro assay results with the goal of using these predictions to prioritize compounds for conventional toxicity testing. Most of these conventional studies rely on in vivo end points observed using preclinical species (e.g., mice and rats). Although the preclinical animal studies provide valuable insights, there can often be significant disconnects between these studies and safety concerns in humans. One way to address these concerns, for an admittedly more limited set of compounds, is to explore relationships between the in vitro data from human cell lines and observations from human related studies. The Comparative Toxicogenomics Database (CTD; http://ctdbase.org ) is a rich source of data linking chemicals to human diseases/adverse events and pathways. In this study we explored the relationships between ToxCast chemicals, their ToxCast in vitro test results, and their annotations of human disease/adverse event end points as captured in the CTD database. We mined these associations to identify potentially interesting, statistically significant in vitro assay and in vivo toxicity correlations. To the best of our knowledge, this is one of the first studies analyzing the relationships between the ToxCast in vitro assays results and the CTD disease/adverse event end point annotations. The in vitro profiles identified in this analysis may prove useful for prioritizing compounds for toxicity testing, suggesting mechanisms of toxicity, and forecasting potential in vivo human drug induced injury.

Comparing bioassay response and similarity ensemble approaches to probing protein pharmacology.

MOTIVATION: Networks to predict protein pharmacology can be created using ligand similarity or using known bioassay response profiles of ligands. Recent publications indicate that similarity methods can be highly accurate, but it has been unclear how similarity methods compare to methods that use bioassay response data directly. RESULTS: We created protein networks based on ligand similarity (Similarity Ensemble Approach or SEA) and ligand bioassay response-data (BARD) using 155 Pfizer internal BioPrint assays. Both SEA and BARD successfully cluster together proteins with known relationships, and predict some non-obvious relationships. Although the approaches assess target relations from different perspectives, their networks overlap considerably (40% overlap of the top 2% of correlated edges). They can thus be considered as comparable methods, with a distinct advantage of the similarity methods that they only require simple computations (similarity of compound) as opposed to extensive experimental data. CONTACTS: djwild@indiana.edu; eric.gifford@pfizer.com. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Using open source computational tools for predicting human metabolic stability and additional absorption, distribution, metabolism, excretion, and toxicity properties.

Ligand-based computational models could be more readily shared between researchers and organizations if they were generated with open source molecular descriptors [e.g., chemistry development kit (CDK)] and modeling algorithms, because this would negate the requirement for proprietary commercial software. We initially evaluated open source descriptors and model building algorithms using a training set of approximately 50,000 molecules and a test set of approximately 25,000 molecules with human liver microsomal metabolic stability data. A C5.0 decision tree model demonstrated that CDK descriptors together with a set of Smiles Arbitrary Target Specification (SMARTS) keys had good statistics [κ = 0.43, sensitivity = 0.57, specificity = 0.91, and positive predicted value (PPV) = 0.64], equivalent to those of models built with commercial Molecular Operating Environment 2D (MOE2D) and the same set of SMARTS keys (κ = 0.43, sensitivity = 0.58, specificity = 0.91, and PPV = 0.63). Extending the dataset to ∼193,000 molecules and generating a continuous model using Cubist with a combination of CDK and SMARTS keys or MOE2D and SMARTS keys confirmed this observation. When the continuous predictions and actual values were binned to get a categorical score we observed a similar κ statistic (0.42). The same combination of descriptor set and modeling method was applied to passive permeability and P-glycoprotein efflux data with similar model testing statistics. In summary, open source tools demonstrated predictive results comparable to those of commercial software with attendant cost savings. We discuss the advantages and disadvantages of open source descriptors and the opportunity for their use as a tool for organizations to share data precompetitively, avoiding repetition and assisting drug discovery.

Chemical space: missing pieces in cheminformatics.

Cheminformatics is at a turning point, the pharmaceutical industry benefits from using the various methods developed over the last twenty years, but in our opinion we need to see greater development of novel approaches that non-experts can use. This will be achieved by more collaborations between software companies, academics and the evolving pharmaceutical industry. We suggest that cheminformatics should also be looking to other industries that use high performance computing technologies for inspiration. We describe the needs and opportunities which may benefit from the development of open cheminformatics technologies, mobile computing, the movement of software to the cloud and precompetitive initiatives.

ADMET in silico modelling: towards prediction paradise?

Following studies in the late 1990s that indicated that poor pharmacokinetics and toxicity were important causes of costly late-stage failures in drug development, it has become widely appreciated that these areas should be considered as early as possible in the drug discovery process. However, in recent years, combinatorial chemistry and high-throughput screening have significantly increased the number of compounds for which early data on absorption, distribution, metabolism, excretion (ADME) and toxicity (T) are needed, which has in turn driven the development of a variety of medium and high-throughput in vitro ADMET screens. Here, we describe how in silico approaches will further increase our ability to predict and model the most relevant pharmacokinetic, metabolic and toxicity endpoints, thereby accelerating the drug discovery process.

Development of CYP3A4 inhibition models: comparisons of machine-learning techniques and molecular descriptors.

Computational models of cytochrome P450 3A4 inhibition were developed based on high-throughput screening data for 4470 proprietary compounds. Multiple models differentiating inhibitors (IC(50) <3 microM) and noninhibitors were generated using various machine-learning algorithms (recursive partitioning [RP], Bayesian classifier, logistic regression, k-nearest-neighbor, and support vector machine [SVM]) with structural fingerprints and topological indices. Nineteen models were evaluated by internal 10-fold cross-validation and also by an independent test set. Three most predictive models, Barnard Chemical Information (BCI)-fingerprint/SVM, MDL-keyset/SVM, and topological indices/RP, correctly classified 249, 248, and 236 compounds of 291 noninhibitors and 135, 137, and 147 compounds of 179 inhibitors in the validation set. Their overall accuracies were 82%, 82%, and 81%, respectively. Investigating applicability of the BCI/SVM model found a strong correlation between the predictive performance and the structural similarity to the training set. Using Tanimoto similarity index as a confidence measurement for the predictions, the limitation of the extrapolation was 0.7 in the case of the BCI/SVM model. Taking consensus of the 3 best models yielded a further improvement in predictive capability, kappa = 0.65 and accuracy = 83%. The consensus model could also be tuned to minimize either false positives or false negatives depending on the emphasis of the screening.

In silico ADME prediction: data, models, facts and myths.

A critical review of a very recent work in the field of in silico ADME prediction is presented with emphasis on the work published during the period 2000-2002, and several other review articles are mentioned in order to offer a broader view of the field. We find that not much progress has been made in developing robust and predictive models, and that the lack of accurate data, together with the use of questionable modeling end-points, has greatly hindered the real progress in defining generally applicable models. Due to the largely empirical nature of QSAR/QSPR approaches, general and truly predictive models for complex phenomena, such as absorption and clearance, may still be chimeric. The development of local models for use within focused chemical series may be the most appropriate way of utilizing in silico ADME predictions, once experience and data have been gained on a given project and/or structural class.

Prediction of drug-like molecular properties: modeling cytochrome p450 interactions.

Preventing drug-drug interactions and reducing drug-related mortalities dictate cleaner and costlier medicines. The cost to bring a new drug to market has increased dramatically over the last 10 years, with post-discovery activities (preclinical and clinical) costs representing the majority of the spend. With the ever-increasing scrutiny that new drug candidates undergo in the post-discovery assessment phases, there is increasing pressure on discovery to deliver higher-quality drug candidates. Given that compound attrition in the early clinical stages can often be attributed to metabolic liabilities, it has been of great interest lately to implement predictive measures of metabolic stability/ liability in the drug design stage of discovery. The solution to this issue is wrapped in understanding the basic of the cytochrome P450 (CYP) enzymes functions and structures. Recently, experimental information on the structure of a variety of cytochrome P450 enzymes, major contributors to phase I metabolism, has become readily available. This, coupled with the availability of experimental information on substrate specificities, has lead to the development of numerous computational models (macromolecular, pharmacophore, and structure-activity) for the rationalization and prediction of CYP liabilities. A comprehensive review of these models is presented in this chapter.

Implementation of an ADME enabling selection and visualization tool for drug discovery.

The pharmaceutical industry has large investments in compound library enrichment, high throughput biological screening, and biopharmaceutical (ADME) screening. As the number of compounds submitted for in vitro ADME screens increases, data analysis, interpretation, and reporting will become rate limiting in providing ADME-structure-activity relationship information to guide the synthetic strategy for chemical series. To meet these challenges, a software tool was developed and implemented that enables scientists to explore in vitro and in silico ADME and chemistry data in a multidimensional framework. The present work integrates physicochemical and ADME data, encompassing results for Caco-2 permeability, human liver microsomal half-life, rat liver microsomal half-life, kinetic solubility, measured log P, rule of 5 descriptors (molecular weight, hydrogen bond acceptors, hydrogen bond donors, calculated log P), polar surface area, chemical stability, and CYP450 3A4 inhibition. To facilitate interpretation of this data, a semicustomized software solution using Spotfire was designed that allows for multidimensional data analysis and visualization. The solution also enables simultaneous viewing and export of chemical structures with the corresponding ADME properties, enabling a more facile analysis of ADME-structure-activity relationship. In vitro and in silico ADME data were generated for 358 compounds from a series of human immunodeficiency virus protease inhibitors, resulting in a data set of 5370 experimental values which were subsequently analyzed and visualized using the customized Spotfire application. Implementation of this analysis and visualization tool has accelerated the selection of molecules for further development based on optimum ADME characteristics, and provided medicinal chemistry with specific, data driven structural recommendations for improvements in the ADME profile.

Systems chemical biology and the Semantic Web: what they mean for the future of drug discovery research.

Systems chemical biology, the integration of chemistry, biology and computation to generate understanding about the way small molecules affect biological systems as a whole, as well as related fields such as chemogenomics, are central to emerging new paradigms of drug discovery such as drug repurposing and personalized medicine. Recent Semantic Web technologies such as RDF and SPARQL are technical enablers of systems chemical biology, facilitating the deployment of advanced algorithms for searching and mining large integrated datasets. In this paper, we aim to demonstrate how these technologies together can change the way that drug discovery is accomplished.

The development and validation of a computational model to predict rat liver microsomal clearance.

As the cost of discovering and developing new pharmaceutically relevant compounds continues to rise, it is increasingly important to select the right molecules to prosecute very early in drug discovery. The development of high throughput in vitro assays of hepatic metabolic clearance has allowed for vast quantities of data generation; however, these large screens are still costly and remain dependant on animal usage. To further expand the value of these screens and ultimately aid in animal usage reduction, we have developed an in silico model of rat liver microsomal (RLM) clearance. This model combines a large amount of rat clearance data (n = 27,697) generated at multiple Pfizer laboratories to represent the broadest possible chemistry space. The model predicts RLM stability (with 82% accuracy and a kappa value of 0.65 for test data set) based solely on chemical structural inputs, and provides a clear assessment of confidence in the prediction. The current in silico model should help accelerate the drug discovery process by using confidence-based stability-driven prioritization, and reduce cost by filtering out the most unstable/undesirable molecules. The model can also increase efficiency in the evaluation of chemical series by optimizing iterative testing and promoting rational drug design.

In silico prediction of ionization constants of drugs.

Most pharmacologically active molecules contain one or more ionizing groups, and it is well-known that knowledge of the ionization state of a drug, indicated by the pKa value, is critical for understanding many properties important to the drug discovery and development process. The ionization state of a compound directly influences such important pharmaceutical characteristics as aqueous solubility, permeability, crystal structure, etc. Tremendous advances have been made in the field of experimental determination of pKa, in terms of both quantity/speed and quality/accuracy. However, there still remains a need for accurate in silico predictions of pKa both to estimate this parameter for virtual compounds and to focus screening efforts of real compounds. The computer program SPARC (SPARC Performs Automated Reasoning in Chemistry) was used to predict the ionization state of a drug. This program has been developed based on the solid physical chemistry of reactivity models and applied to successfully predict numerous physical properties as well as chemical reactivity parameters. SPARC predicts both macroscopic and microscopic pKa values strictly from molecular structure. In this paper, we describe the details of the SPARC reactivity computational methods and its performance on predicting the pKa values of known drugs as well as Pfizer internal discovery/development compounds. A high correlation (r2=0.92) between experimental and the SPARC calculated pKa values was obtained with root-mean-square error (RMSE) of 0.78 log unit for a set of 123 compounds including many known drugs. For a set of 537 compounds from the Pfizer internal dataset, correlation coefficient r2=0.80 and RMSE=1.05 were obtained.