A major cause of the paucity of new starting points for drug discovery is the lack of interaction between academia and industry. Much of the global resource in biology is present in universities, whereas the focus of medicinal chemistry is still largely within industry. Open source drug discovery, with sharing of information, is clearly a first step towards overcoming this gap. But the interface could especially be bridged through a scale-up of open sharing of physical compounds, which would accelerate the finding of new starting points for drug discovery. The Medicines for Malaria Venture Malaria Box is a collection of over 400 compounds representing families of structures identified in phenotypic screens of pharmaceutical and academic libraries against the Plasmodium falciparum malaria parasite. The set has now been distributed to almost 200 research groups globally in the last two years, with the only stipulation that information from the screens is deposited in the public domain. This paper reports for the first time on 236 screens that have been carried out against the Malaria Box and compares these results with 55 assays that were previously published, in a format that allows a meta-analysis of the combined dataset. The combined biochemical and cellular assays presented here suggest mechanisms of action for 135 (34%) of the compounds active in killing multiple life-cycle stages of the malaria parasite, including asexual blood, liver, gametocyte, gametes and insect ookinete stages. In addition, many compounds demonstrated activity against other pathogens, showing hits in assays with 16 protozoa, 7 helminths, 9 bacterial and mycobacterial species, the dengue fever mosquito vector, and the NCI60 human cancer cell line panel of 60 human tumor cell lines. Toxicological, pharmacokinetic and metabolic properties were collected on all the compounds, assisting in the selection of the most promising candidates for murine proof-of-concept experiments and medicinal chemistry programs. The data for all of these assays are presented and analyzed to show how outstanding leads for many indications can be selected. These results reveal the immense potential for translating the dispersed expertise in biological assays involving human pathogens into drug discovery starting points, by providing open access to new families of molecules, and emphasize how a small additional investment made to help acquire and distribute compounds, and sharing the data, can catalyze drug discovery for dozens of different indications. Another lesson is that when multiple screens from different groups are run on the same library, results can be integrated quickly to select the most valuable starting points for subsequent medicinal chemistry efforts.

Most small-molecule drug candidates fail before entering the market, frequently because of unexpected toxicity. Often, toxicity is detected only late in drug development, because many types of toxicities, especially idiosyncratic adverse drug reactions (IADRs), are particularly hard to predict and detect. Moreover, drug-induced liver injury (DILI) is the most frequent reason drugs are withdrawn from the market and causes 50% of acute liver failure cases in the United States. A common mechanism often underlies many types of drug toxicities, including both DILI and IADRs. Drugs are bioactivated by drug-metabolizing enzymes into reactive metabolites, which then conjugate to sites in proteins or DNA to form adducts. DNA adducts are often mutagenic and may alter the reading and copying of genes and their regulatory elements, causing gene dysregulation and even triggering cancer. Similarly, protein adducts can disrupt their normal biological functions and induce harmful immune responses. Unfortunately, reactive metabolites are not reliably detected by experiments, and it is also expensive to test drug candidates for potential to form DNA or protein adducts during the early stages of drug development. In contrast, computational methods have the potential to quickly screen for covalent binding potential, thereby flagging problematic molecules and reducing the total number of necessary experiments. Here, we train a deep convolution neural network—the XenoSite reactivity model—using literature data to accurately predict both sites and probability of reactivity for molecules with glutathione, cyanide, protein, and DNA. On the site level, cross-validated predictions had area under the curve (AUC) performances of 89.8% for DNA and 94.4% for protein. Furthermore, the model separated molecules electrophilically reactive with DNA and protein from nonreactive molecules with cross-validated AUC performances of 78.7% and 79.8%, respectively. On both the site- and molecule-level, the model’s performances significantly outperformed reactivity indices derived from quantum simulations that are reported in the literature. Moreover, we developed and applied a selectivity score to assess preferential reactions with the macromolecules as opposed to the common screening traps. For the entire data set of 2803 molecules, this approach yielded totals of 257 (9.2%) and 227 (8.1%) molecules predicted to be reactive only with DNA and protein, respectively, and hence those that would be missed by standard reactivity screening experiments. Site of reactivity data is an underutilized resource that can be used to not only predict if molecules are reactive, but also show where they might be modified to reduce toxicity while retaining efficacy. The XenoSite reactivity model is available at .

Cytochromes P450 (CYPs) oxidize alkylated amines commonly found in drugs and other biologically active molecules, cleaving them into an amine and an aldehyde. Metabolic studies usually neglect to report or investigate aldehydes, even though they can be toxic. It is assumed that they are efficiently detoxified into carboxylic acids and alcohols. Nevertheless, some aldehydes are reactive and escape detoxification pathways to cause adverse events by forming DNA and protein adducts. Herein, we modeled N-dealkylations that produce both amine and aldehyde metabolites and then predicted the reactivity of the aldehyde. This model used a deep learning approach previously developed by our group to predict other types of drug metabolism. In this study, we trained the model to predict N-dealkylation by human liver microsomes (HLM), finding that including isozyme-specific metabolism data alongside HLM data significantly improved results. The final HLM model accurately predicted the site of N-dealkylation within metabolized substrates (97% top-two and 94% area under the ROC curve). Next, we combined the metabolism, metabolite structure prediction, and previously published reactivity models into a bioactivation model. This combined model predicted the structure of the most likely reactive metabolite of a small validation set of drug-like molecules known to be bioactivated by N-dealkylation. Applying this model to approved and withdrawn medicines, we found that aldehyde metabolites produced from N-dealkylation may explain the hepatotoxicity of several drugs: indinavir, piperacillin, verapamil, and ziprasidone. Our results suggest that N-dealkylation may be an under-appreciated bioactivation pathway, especially in clinical contexts where aldehyde detoxification pathways are inhibited. Moreover, this is the first report of a bioactivation model constructed by combining a metabolism and reactivity model. These results raise hope that more comprehensive models of bioactivation are possible. The model developed in this study is available at http://swami.wustl.edu/xenosite/ .

Structural alerts are commonly used in drug discovery to identify molecules likely to form reactive metabolites and thereby become toxic. Unfortunately, as useful as structural alerts are, they do not effectively model if, when, and why metabolism renders safe molecules toxic. Toxicity due to a specific structural alert is highly conditional, depending on the metabolism of the alert, the reactivity of its metabolites, dosage, and competing detoxification pathways. A systems approach, which explicitly models these pathways, could more effectively assess the toxicity risk of drug candidates. In this study, we demonstrated that mathematical models of P450 metabolism can predict the context-specific probability that a structural alert will be bioactivated in a given molecule. This study focuses on the furan, phenol, nitroaromatic, and thiophene alerts. Each of these structural alerts can produce reactive metabolites through certain metabolic pathways but not always. We tested whether our metabolism modeling approach, XenoSite, can predict when a given molecule’s alerts will be bioactivated. Specifically, we used models of epoxidation, quinone formation, reduction, and sulfur-oxidation to predict the bioactivation of furan-, phenol-, nitroaromatic-, and thiophene-containing drugs. Our models separated bioactivated and not-bioactivated furan-, phenol-, nitroaromatic-, and thiophene-containing drugs with AUC performances of 100%, 73%, 93%, and 88%, respectively. Metabolism models accurately predict whether alerts are bioactivated and thus serve as a practical approach to improve the interpretability and usefulness of structural alerts. We expect that this same computational approach can be extended to most other structural alerts and later integrated into toxicity risk models. This advance is one necessary step toward our long-term goal of building comprehensive metabolic models of bioactivation and detoxification to guide assessment and design of new therapeutic molecules.

During drug development, it is critical to evaluate the metabolism of drug candidates, which affects absorption, efficacy, excretion, and toxicity profiles. In vitro experiments with human liver microsomes and in vivo animal models are commonly used to estimate the metabolism of a drug candidate in human. Unfortunately, it is expensive to comprehensively test the metabolism of vast numbers of candidates during early stages drug development. Computational metabolism models can rapidly and cost‐effectively predict which atoms or bonds of a molecule are modified during metabolism—site of metabolism—on thousands of drug candidates, thereby significantly reducing the number of experiments needed. However, current computational metabolism models are unable to predict what specific metabolic transformations would happen at certain sites. Identification of metabolism type is important for metabolite prediction, especially in the case of Phase I metabolism which includes many reaction types. Without knowledge of potential metabolite structures, medicinal chemists cannot differentiate harmful metabolic transformations from beneficial ones. To address this shortcoming, the current study modeled not only the site but also the type of human Phase I metabolism. We trained a neural network model on a literature‐derived data set of 20736 human Phase I reaction records. Among the covered reaction types were dealkylation, dehydrogenation, epoxidation, hydrolysis, hydroxylation, and reduction. Our model differentiated between these metabolic reactions with cross‐validated accuracy of 97.1% area under the curve. The model developed in this study is available at http://swami.wustl.edu/xenosite/PhaseI. Support or Funding Information The research was supported by the National Library Of Medicine of the National Institutes of Health under award number R01LM012222 and R01LM012482. Computations were performed using the facilities of the Washington University Center for High Performance Computing, which were partially funded by National Institutes of Health (NIH) grants numbers 1S10RR022984‐01A1 and 1S10OD018091‐01. This abstract is from the Experimental Biology 2018 Meeting. There is no full text article associated with this abstract published in The FASEB Journal.