Meir Glick

Enrichment of High-Throughput Screening Data with Increasing Levels of Noise Using Support Vector Machines, Recursive Partitioning, and Laplacian-Modified Naive Bayesian Classifiers

High-throughput screening (HTS) plays a pivotal role in lead discovery for the pharmaceutical industry. In tandem, cheminformatics approaches are employed to increase the probability of the identification of novel biologically active compounds by mining the HTS data. HTS data is notoriously noisy, and therefore, the selection of the optimal data mining method is important for the success of such an analysis. Here, we describe a retrospective analysis of four HTS data sets using three mining approaches: Laplacian-modified naive Bayes, recursive partitioning, and support vector machine (SVM) classifiers with increasing stochastic noise in the form of false positives and false negatives. All three of the data mining methods at hand tolerated increasing levels of false positives even when the ratio of misclassified compounds to true active compounds was 5:1 in the training set. False negatives in the ratio of 1:1 were tolerated as well. SVM outperformed the other two methods in capturing active compounds and scaffolds in the top 1%. A Murcko scaffold analysis could explain the differences in enrichments among the four data sets. This study demonstrates that data mining methods can add a true value to the screen even when the data is contaminated with a high level of stochastic noise.

Virtual Fragment Linking : An Approach To Identify Potent Binders from Low Affinity Fragment Hits

In this work we explore the possibilities of using fragment-based screening data to prioritize compounds from a full HTS library, a method we call virtual fragment linking (VFL). The ability of VFL to identify compounds of nanomolar potency based on micromolar fragment binding data was tested on 75 target classes from the WOMBAT database and succeeded in 57 cases. Further, the method was demonstrated for seven drug targets from in-house screening programs that performed both FBS of 8800 fragments and screens of the full library. VFL captured between 28% and 67% of the hits (IC 50 < 10microM) in the top 5% of the ranked library for four of the targets (enrichment between 5-fold and 13-fold). Our findings lead us to conclude that proper coverage of chemical space by the fragment library is crucial for the VFL methodology to be successful in prioritizing HTS libraries from fragment-based screening data.

A Screening Pattern Recognition Method Finds New and Divergent Targets for Drugs and Natural Products

Computational target prediction methods using chemical descriptors have been applied exhaustively in drug discovery to elucidate the mechanisms-of-action (MOAs) of small molecules. To predict truly novel and unexpected small molecule-target interactions, compounds must be compared by means other than their chemical structure alone. Here we investigated predictions made by a method, HTS fingerprints (HTSFPs), that matches patterns of activities in experimental screens. Over 1,400 drugs and 1,300 natural products (NPs) were screened in more than 200 diverse assays, creating encodable activity patterns. The comparison of these activity patterns to an MOA-annotated reference panel led to the prediction of 5,281 and 2,798 previously unknown targets for the NP and drug sets, respectively. Intriguingly, there was limited overlap among the targets predicted; the drugs were more biased toward membrane receptors and the NPs toward soluble enzymes, consistent with the idea that they represent unexplored pharmacologies. Importantly, HTSFPs inferred targets that were beyond the prediction capabilities of standard chemical descriptors, especially for NPs but also for the more explored drug set. Of 65 drug-target predictions that we tested in vitro, 48 (73.8%) were confirmed with AC50 values ranging from 38 nM to 29 μM. Among these interactions was the inhibition of cyclooxygenases 1 and 2 by the HIV protease inhibitor Tipranavir. These newly discovered targets that are phylogenetically and phylochemically distant to the primary target provide an explanation for spontaneous bleeding events observed for patients treated with this drug, a physiological effect that was previously difficult to reconcile with the drugs known MOA.

Public Domain HTS Fingerprints: Design and Evaluation of Compound Bioactivity Profiles from PubChem’s Bioassay Repository

Molecular profiling efforts aim at characterizing the biological actions of small molecules by screening them in hundreds of different biochemical and/or cell-based assays. Together, these assays yield a rich data landscape of target-based and phenotypic effects of the tested compounds. However, submitting an entire compound library to a molecular profiling panel can easily become cost-prohibitive. Here, we make use of historical screening assays to create comprehensive bioactivity profiles for more than 300 000 small molecules. These bioactivity profiles, termed PubChem high-throughput screening fingerprints (PubChem HTSFPs), report small molecule activities in 243 different PubChem bioassays. Although the assays originate from originally independently pursued drug or probe discovery projects, we demonstrate their value as molecular signatures when used in combination. We use these PubChem HTSFPs as molecular descriptors in hit expansion experiments for 33 different targets and phenotypes, showing that, on average, they lead to 27 times as many hits in a set of 1000 chosen molecules as a random screening subset of the same size (average ROC score: 0.82). Moreover, we demonstrate that PubChem HTSFPs retrieve hits that are structurally diverse and distinct from active compounds retrieved by chemical similarity-based hit expansion methods. PubChem HTSFPs are made freely available for the chemical biology research community.

Pattern recognition and massively distributed computing.

A feature of Peter Kollmans research was his exploitation of the latest computational techniques to devise novel applications of the free energy perturbation method. He would certainly have seized upon the opportunities offered by massively distributed computing. Here we describe the use of over a million personal computers to perform virtual screening of 3.5 billion druglike molecules against protein targets by pharmacophore pattern matching, together with other applications of pattern recognition such as docking ligands without any a priori knowledge about the binding site location.

Bioturbo Similarity Searching: Combining Chemical and Biological Similarity To Discover Structurally Diverse Bioactive Molecules

Virtual screening using bioactivity profiles has become an integral part of currently applied hit finding methods in pharmaceutical industry. However, a significant drawback of this approach is that it is only applicable to compounds that have been biologically tested in the past and have sufficient activity annotations for meaningful profile comparisons. Although bioactivity data generated in pharmaceutical institutions are growing on an unprecedented scale, the number of biologically annotated compounds still covers only a minuscule fraction of chemical space. For a newly synthesized compound or an isolated natural product to be biologically characterized across multiple assays, it may take a considerable amount of time. Consequently, this chemical matter will not be included in virtual screening campaigns based on bioactivity profiles. To overcome this problem, we herein introduce bioturbo similarity searching that uses chemical similarity to map molecules without biological annotations into bioactivity space and then searches for biologically similar compounds in this reference system. In benchmark calculations on primary screening data, we demonstrate that our approach generally achieves higher hit rates and identifies structurally more diverse compounds than approaches using chemical information only. Furthermore, our method is able to discover hits with novel modes of inhibition that traditional 2D and 3D similarity approaches are unlikely to discover. Test calculations on a set of natural products reveal the practical utility of the approach for identifying novel and synthetically more accessible chemical matter.

Activity-Aware Clustering of High Throughput Screening Data and Elucidation of Orthogonal Structure–Activity Relationships

From a medicinal chemistry point of view, one of the primary goals of high throughput screening (HTS) hit list assessment is the identification of chemotypes with an informative structure-activity relationship (SAR). Such chemotypes may enable optimization of the primary potency, as well as selectivity and phamacokinetic properties. A common way to prioritize them is molecular clustering of the hits. Typical clustering techniques, however, rely on a general notion of chemical similarity or standard rules of scaffold decomposition and are thus insensitive to molecular features that are enriched in biologically active compounds. This hinders SAR analysis, because compounds sharing the same pharmacophore might not end up in the same cluster and thus are not directly compared to each other by the medicinal chemist. Similarly, common chemotypes that are not related to activity may contaminate clusters, distracting from important chemical motifs. We combined molecular similarity and Bayesian models and introduce (I) a robust, activity-aware clustering approach and (II) a feature mapping method for the elucidation of distinct SAR determinants in polypharmacologic compounds. We evaluated the method on 462 dose-response assays from the Pubchem Bioassay repository. Activity-aware clustering grouped compounds sharing molecular cores that were specific for the target or pathway at hand, rather than grouping inactive scaffolds commonly found in compound series. Many of these core structures we also found in literature that discussed SARs of the respective targets. A numerical comparison of cores allowed for identification of the structural prerequisites for polypharmacology, i.e., distinct bioactive regions within a single compound, and pointed toward selectivity-conferring medchem strategies. The method presented here is generally applicable to any type of activity data and may help bridge the gap between hit list assessment and designing a medchem strategy.

Pinpointing anthrax-toxin inhibitors

118 findings often generate such hyperbole, and so biotechnology companies would benefit by keeping their own appraisals modest and emphasizing the often long-term nature of biomedical research findings. 3. Scientists working in areas that involve difficult or controversial ethical issues should seek ethical advice from external sources. Acting on this principle, ACT invited a distinguished group of bioethicists, health-care lawyers, clinical medical specialists, and community members to form an independent Ethics Advisory Board to furnish advice and guidelines for our research. Chaired by Ronald M. Green of Dartmouth College, this Board has met on a quarterly basis since the inception of our therapeutic cloning research and has laid down strict guidelines for the conduct of that research and the associated egg donor program. Members of that EAB have no financial stake in ACT’s research and remain free to publicly criticize our conduct. We are by no means trying to suggest that everything we have done is flawless. Like others working in a new and controversial area of research, we are trying to steer our way through a thicket of challenging new issues and are learning as we proceed. The opportunities afforded by cellular reprogramming through nuclear transfer are broad and could substantially affect future health-care practice. The ability to manufacture nearly any cell type through a nuclear transfer–derived embryonic stem-cell line could make it possible to produce many cells not currently available to treat a wide array of disorders including Parkinson’s disease, diabetes, heart failure, and renal failure, as well as many others. Therefore, we at ACT regard our role in this debate with the highest degree of gravity. The debate is greater than any of us. The accusation that ACT is, by its actions, inviting an outright legislative ban on therapeutic cloning research is therefore a serious charge. We would point out that the US House of Representatives voted to ban all uses of cloning in the human species (including therapeutic cloning) months before ACT’s report and that similar prohibitions were actively being discussed in the US Senate. To advise that researchers working in this controversial area must halt their work or withdraw publication of their results until legislators make a final law is, in our opinion, to display a lack of confidence in the strength of US democracy. The United States plays an important role as one of the leaders in biotechnology. It is not only our opportunity, but our duty, to inform the public of our research objectives, keep the public appraised of our progress, and display confidence that a free and informed public is capable of appreciating the motives of the biotechnology industry. Robert P. Lanza, Jose B. Cibelli, and Michael D. West, Advanced Cell Technology, Worcester, MA 01605 (rlanza@advancedcell.com)

Potent, Selective, and Orally Bioavailable Inhibitors of VPS34 Provide Chemical Tools to Modulate Autophagy in Vivo

Autophagy is a dynamic process that regulates lysosomal-dependent degradation of cellular components. Until recently the study of autophagy has been hampered by the lack of reliable pharmacological tools, but selective inhibitors are now available to modulate the PI 3-kinase VPS34, which is required for autophagy. Here we describe the discovery of potent and selective VPS34 inhibitors, their pharmacokinetic (PK) properties, and ability to inhibit autophagy in cellular and mouse models.

Experimental Design Strategy: Weak Reinforcement Leads to Increased Hit Rates and Enhanced Chemical Diversity

High Throughput Screening (HTS) is a common approach in life sciences to discover chemical matter that modulates a biological target or phenotype. However, low assay throughput, reagents cost, or a flowchart that can deal with only a limited number of hits may impair screening large numbers of compounds. In this case, a subset of compounds is assayed, and in silico models are utilized to aid in iterative screening design, usually to expand around the found hits and enrich subsequent rounds for relevant chemical matter. However, this may lead to an overly narrow focus, and the diversity of compounds sampled in subsequent iterations may suffer. Active learning has been recently successfully applied in drug discovery with the goal of sampling diverse chemical space to improve model performance. Here we introduce a robust and straightforward iterative screening protocol based on naı̈ve Bayes models. Instead of following up on the compounds with the highest scores in the in silico model, we pursue compounds with very low but positive values. This includes unique chemotypes of weakly active compounds that enhance the applicability domain of the model and increase the cumulative hit rates. We show in a retrospective application to 81 Novartis assays that this protocol leads to consistently higher compound and scaffold hit rates compared to a standard expansion around hits or an active learning approach. We recommend using the weak reinforcement strategy introduced herein for iterative screening workflows.