Systematic Data Analysis and Diagnostic Machine Learning Reveal Differences between Compounds with Single- and Multitarget Activity.

Small molecules with multitarget activity are capable of triggering polypharmacological effects and are of high interest in drug discovery. Compared to single-target compounds, promiscuity also affects drug distribution and pharmacodynamics and alters ADMET characteristics. Features distinguishing between compounds with single- and multitarget activity are currently only little understood. On the basis of systematic data analysis, we have assembled large sets of promiscuous compounds with activity against related or functionally distinct targets and the corresponding compounds with single-target activity. Machine learning predicted promiscuous compounds with surprisingly high accuracy. Molecular similarity analysis combined with control calculations under varying conditions revealed that accurate predictions were largely determined by structural nearest-neighbor relationships between compounds from different classes. We also found that large proportions of promiscuous compounds with activity against related or unrelated targets and corresponding single-target compounds formed analog series with distinct chemical space coverage, which further rationalized the predictions. Moreover, compounds with activity against proteins from functionally distinct classes were often active against unique targets that were not covered by other promiscuous compounds. The results of our analysis revealed that nearest-neighbor effects determined the prediction of promiscuous compounds and that preferential partitioning of compounds with single- and multitarget activity into structurally distinct analog series was responsible for such effects, hence providing a rationale for the presence of different structure-promiscuity relationships.

DeepCOMO: from structure-activity relationship diagnostics to generative molecular design using the compound optimization monitor methodology.

The compound optimization monitor (COMO) approach was originally developed as a diagnostic approach to aid in evaluating development stages of analog series and progress made during lead optimization. COMO uses virtual analog populations for the assessment of chemical saturation of analog series and has been further developed to bridge between optimization diagnostics and compound design. Herein, we discuss key methodological features of COMO in its scientific context and present a deep learning extension of COMO for generative molecular design, leading to the introduction of DeepCOMO. Applications on exemplary analog series are reported to illustrate the entire DeepCOMO repertoire, ranging from chemical saturation and structure-activity relationship progression diagnostics to the evaluation of different analog design strategies and prioritization of virtual candidates for optimization efforts, taking into account the development stage of individual analog series.

SeMPI: a genome-based secondary metabolite prediction and identification web server.

The secondary metabolism of bacteria, fungi and plants yields a vast number of bioactive substances. The constantly increasing amount of published genomic data provides the opportunity for an efficient identification of gene clusters by genome mining. Conversely, for many natural products with resolved structures, the encoding gene clusters have not been identified yet. Even though genome mining tools have become significantly more efficient in the identification of biosynthetic gene clusters, structural elucidation of the actual secondary metabolite is still challenging, especially due to as yet unpredictable post-modifications. Here, we introduce SeMPI, a web server providing a prediction and identification pipeline for natural products synthesized by polyketide synthases of type I modular. In order to limit the possible structures of PKS products and to include putative tailoring reactions, a structural comparison with annotated natural products was introduced. Furthermore, a benchmark was designed based on 40 gene clusters with annotated PKS products. The web server of the pipeline (SeMPI) is freely available at: http://www.pharmaceutical-bioinformatics.de/sempi.

Identifying Promiscuous Compounds with Activity against Different Target Classes.

Compounds with multitarget activity are of high interest for polypharmacological drug discovery. Such promiscuous compounds might be active against closely related target proteins from the same family or against distantly related or unrelated targets. Compounds with activity against distinct targets are not only of interest for polypharmacology but also to better understand how small molecules might form specific interactions in different binding site environments. We have aimed to identify compounds with activity against drug targets from different classes. To these ends, a systematic analysis of public biological screening data was carried out. Care was taken to exclude compounds from further consideration that were prone to experimental artifacts and false positive activity readouts. Extensively assayed compounds were identified and found to contain molecules that were consistently inactive in all assays, active against a single target, or promiscuous. The latter included more than 1000 compounds that were active against 10 or more targets from different classes. These multiclass ligands were further analyzed and exemplary compounds were found in X-ray structures of complexes with distinct targets. Our collection of multiclass ligands should be of interest for pharmaceutical applications and further exploration of binding characteristics at the molecular level. Therefore, these highly promiscuous compounds are made publicly available.

A preclinical secondary pharmacology resource illuminates target-adverse drug reaction associations of marketed drugs.

In vitro secondary pharmacology assays are an important tool for predicting clinical adverse drug reactions (ADRs) of investigational drugs. We created the Secondary Pharmacology Database (SPD) by testing 1958 drugs using 200 assays to validate target-ADR associations. Compared to public and subscription resources, 95% of all and 36% of active (AC50 < 1 µM) results are unique to SPD, with bias towards higher activity in public resources. Annotating drugs with free maximal plasma concentrations, we find 684 physiologically relevant unpublished off-target activities. Furthermore, 64% of putative ADRs linked to target activity in key literature reviews are not statistically significant in SPD. Systematic analysis of all target-ADR pairs identifies several putative associations supported by publications. Finally, candidate mechanisms for known ADRs are proposed based on SPD off-target activities. Here we present a freely-available resource for benchmarking ADR predictions, explaining phenotypic activity and investigating clinical properties of marketed drugs.

Structured data sets of compounds with multi-target and corresponding single-target activity from biological assays.

AIM: Providing compound data sets for promiscuity analysis with single-target (ST) and multi-target (MT) activity, taking confirmed inactivity against targets into account. METHODOLOGY: Compounds and target annotations are extracted from screening assays. For a given combination of targets, MT and ST compounds are identified, ensuring test data completeness. EXEMPLARY RESULTS & DATA: A total of 1242 MT compounds active against five or more targets and 6629 corresponding ST compounds are characterized, organized and made freely available. LIMITATIONS & NEXT STEPS: Screening campaigns typically cover a smaller target space than compounds from the medicinal chemistry literature and their activity annotations might be of lesser quality. Reported compound groups will be subjected to target set-based promiscuity analysis and predictions.

Predicting Isoform-Selective Carbonic Anhydrase Inhibitors via Machine Learning and Rationalizing Structural Features Important for Selectivity.

Carbonic anhydrases (CAs) catalyze the physiological hydration of carbon dioxide and are among the most intensely studied pharmaceutical target enzymes. A hallmark of CA inhibition is the complexation of the catalytic zinc cation in the active site. Human (h) CA isoforms belonging to different families are implicated in a wide range of diseases and of very high interest for therapeutic intervention. Given the conserved catalytic mechanisms and high similarity of many hCA isoforms, a major challenge for CA-based therapy is achieving inhibitor selectivity for hCA isoforms that are associated with specific pathologies over other widely distributed isoforms such as hCA I or hCA II that are of critical relevance for the integrity of many physiological processes. To address this challenge, we have attempted to predict compounds that are selective for isoform hCA IX, which is a tumor-associated protein and implicated in metastasis, over hCA II on the basis of a carefully curated data set of selective and nonselective inhibitors. Machine learning achieved surprisingly high accuracy in predicting hCA IX-selective inhibitors. The results were further investigated, and compound features determining successful predictions were identified. These features were then studied on the basis of X-ray structures of hCA isoform-inhibitor complexes and found to include substructures that explain compound selectivity. Our findings lend credence to selectivity predictions and indicate that the machine learning models derived herein have considerable potential to aid in the identification of new hCA IX-selective compounds.

Integrating computational lead optimization diagnostics with analog design and candidate selection.

AIM: Combining computational lead optimization diagnostics with analog design and computational approaches for assessing optimization efforts are discussed and the compound optimization monitor is introduced. METHODS: Approaches for compound potency prediction are described and a new analog design algorithm is introduced. Calculation protocols are detailed. RESULTS & DISCUSSION: The study rationale is explained. Compound optimization monitor diagnostics are combined with a thoroughly evaluated approach for compound design and candidate prioritization. The diagnostic scoring scheme is further extended. FUTURE PERSPECTIVE: Opportunities for practical applications of the integrated computational methodology are described and further development perspectives are discussed.

From SAR Diagnostics to Compound Design: Development Chronology of the Compound Optimization Monitor (COMO) Method.

In medicinal chemistry, compound optimization largely depends on chemical knowledge, experience, and intuition, and progress in hit-to-lead and lead optimization projects is difficult to estimate. Accordingly, approaches are sought after that aid in assessing the odds of success with an optimization project and making decisions whether to continue or discontinue work on an analog series at a given stage. However, currently there are only very few approaches available that are capable of providing decision support. We introduce a computational methodology designed to combine the assessment of chemical saturation of analog series and structure-activity relationship (SAR) progression. The current endpoint of these development efforts, the compound optimization monitor (COMO), further extends lead optimization diagnostics to compound design and activity prediction. Hence, COMO plays dual role in supporting lead optimization campaigns.

Analysis of Biological Screening Compounds with Single- or Multi-Target Activity via Diagnostic Machine Learning.

Predicting compounds with single- and multi-target activity and exploring origins of compound specificity and promiscuity is of high interest for chemical biology and drug discovery. We present a large-scale analysis of compound promiscuity including two major components. First, high-confidence datasets of compounds with multi- and corresponding single-target activity were extracted from biological screening data. Positive and negative assay results were taken into account and data completeness was ensured. Second, these datasets were investigated using diagnostic machine learning to systematically distinguish between compounds with multi- and single-target activity. Models built on the basis of chemical structure consistently produced meaningful predictions. These findings provided evidence for the presence of structural features differentiating promiscuous and non-promiscuous compounds. Machine learning under varying conditions using modified datasets revealed a strong influence of nearest neighbor relationship on the predictions. Many multi-target compounds were found to be more similar to other multi-target compounds than single-target compounds and vice versa, which resulted in consistently accurate predictions. The results of our study confirm the presence of structural relationships that differentiate promiscuous and non-promiscuous compounds.

Computational Method to Evaluate Progress in Lead Optimization.

In medicinal chemistry, lead optimization is a critically important task and a highly empirical process, largely driven by chemical knowledge and intuition. Only very few approaches are available to guide and evaluate optimization efforts. It is often very difficult to understand when a compound series is exhausted and the generation of additional analogs unlikely to yield further progress toward potent and efficacious candidates. Rationalizing lead optimization remains an essentially unsolved problem. Herein, we introduce a new computational method to aid in evaluating whether sufficient numbers of analogs have been made and further progress is unlikely. The approach integrates the assessment of chemical saturation and structure-activity relationship progression of compound series. Easy-to-calculate scores characterize evolving analog series and identify candidates with high or low priority for further chemical exploration.

Redundancy in two major compound databases.

Public repositories of compounds and activity data are of prime importance for pharmaceutical research in academic and industrial settings. Major databases have evolved over the years. Their growth is accompanied by an increasing tendency toward data sharing. This is a positive development but not without potential problems. Using ChEMBL and PubChem as examples, we show that crosstalk between databases also leads to substantial data redundancy that might not be obvious. Redundancy is an important issue because it biases data analysis and knowledge extraction and leads to inflated views of available compounds, assays and activity data. Going forward it will be important to further refine data exchange and deposition criteria and make redundancy as transparent as possible.

Computational Assessment of Chemical Saturation of Analogue Series under Varying Conditions.

Assessing the degree to which analogue series are chemically saturated is of major relevance in compound optimization. Decisions to continue or discontinue series are typically made on the basis of subjective judgment. Currently, only very few methods are available to aid in decision making. We further investigate and extend a computational concept to quantitatively assess the progression and chemical saturation of a series. To these ends, existing analogues and virtual candidates are compared in chemical space and compound neighborhoods are systematically analyzed. A large number of analogue series from different sources are studied, and alternative chemical space representations and virtual analogues of different designs are explored. Furthermore, evolving analogue series are distinguished computationally according to different saturation levels. Taken together, our findings provide a basis for practical applications of computational saturation analysis in compound optimization.