Anatomy of fingerprint search calculations on structurally diverse sets of active compounds

Similarity searching using molecular fingerprints is a widely used approach for the identification of novel hits. A fingerprint search involves many pairwise comparisons of bit string representations of known active molecules with those precomputed for database compounds. Bit string overlap, as evaluated by various similarity metrics, is used as a measure of molecular similarity. Results of a number of studies focusing on fingerprints suggest that it is difficult, if not impossible, to develop generally applicable search parameters and strategies, irrespective of the compound classes under investigation. Rather, more or less, each individual search problem requires an adjustment of calculation conditions. Thus, there is a need for diagnostic tools to analyze fingerprint-based similarity searching. We report an analysis of fingerprint search calculations on different sets of structurally diverse active compounds. Calculations on five biological activity classes were carried out with two fingerprints in two compound source databases, and the results were analyzed in histograms. Tanimoto coefficient (Tc) value ranges where active compounds were detected were compared to the distribution of Tc values in the database. The analysis revealed that compound class-specific effects strongly influenced the outcome of these fingerprint calculations. Among the five diverse compound sets studied, very different search results were obtained. The analysis described here can be applied to determine Tc intervals where scaffold hopping occurs. It can also be used to benchmark fingerprint calculations or estimate their probability of success.     

Introduction of the conditional correlated Bernoulli model of similarity value distributions and its application to the prospective prediction of fingerprint search performance

A statistical approach named the conditional correlated Bernoulli model is introduced for modeling of similarity scores and predicting the potential of fingerprint search calculations to identify active compounds. Fingerprint features are rationalized as dependent Bernoulli variables and conditional distributions of Tanimoto similarity values of database compounds given a reference molecule are assessed. The conditional correlated Bernoulli model is utilized in the context of virtual screening to estimate the position of a compound obtaining a certain similarity value in a database ranking. Through the generation of receiver operating characteristic curves from cumulative distribution functions of conditional similarity values for known active and random database compounds, one can predict how successful a fingerprint search might be. The comparison of curves for different fingerprints makes it possible to identify fingerprints that are most likely to identify new active molecules in a database search given a set of known reference molecules.     

Balancing the influence of molecular complexity on fingerprint similarity searching

Differences in molecular complexity and size are known to bias the evaluation of fingerprint similarity. For example, complex molecules tend to produce fingerprints with higher bit density than simple ones, which often leads to artificially high similarity values in search calculations. We introduce here a variant of the Tversky coefficient that makes it possible to modulate or eliminate molecular complexity effects when evaluating fingerprint similarity. This has enabled us to study in detail the role of molecular complexity in similarity searching and the relationship between reference and active database compounds. Balancing complexity effects leads to constant distributions of similarity values for reference and database molecules, independent of how compound contributions are weighted. When searching for active compounds with varying complexity, hit rates can be optimized by modulating complexity effects, rather than eliminating them, and adjusting relative compound weights. For reference molecules and active database compounds having different complexity, preferred parameter settings are identified.     

Application of machine learning to improve the results of high-throughput docking against the HIV-1 protease

We have previously reported that the application of a Laplacian-modified naive Bayesian (NB) classifier may be used to improve the ranking of known inhibitors from a random database of compounds after High-Throughput Docking (HTD). The method relies upon the frequency of substructural features among the active and inactive compounds from 2D fingerprint information of the compounds. Here we present an investigation of the role of extended connectivity fingerprints in training the NB classifier against HTD studies on the HIV-1 protease using three docking programs: Glide, FlexX, and GOLD. The results show that the performance of the NB classifier is due to the presence of a large number of features common to the set of known active compounds rather than a single structural or substructural scaffold. We demonstrate that the Laplacian-modified naive Bayesian classifier trained with data from high-throughput docking is superior at identifying active compounds from a target database in comparison to conventional two-dimensional substructure search methods alone.     

Evaluation of similarity measures for searching the dictionary of natural products database

Similarity searches using combinations of seven different similarity coefficients and six different representations have been carried out on the Dictionary of Natural Products database. The objective was to discover if any special methods of searching apply to this database, which is very different in nature from the many synthetic databases that have been the subject of previous studies of similarity searching. Search effectiveness was assessed by a recall analysis of the search outputs from sets of pharmacologically active target structures. The different target sets produce exceptional but contradictory results for the Russell-Rao and Forbes coefficients, which have been shown to be due to a dependence on molecular size; these are the coefficients of choice in the case of large and small structures, respectively. Rankings from these results have been combined using a data fusion scheme and some small gains in performance were normally obtained by using substructural fingerprints and molecular holograms in combination with the Squared Euclidean or Tanimoto coefficients.     

Similarity search profiling reveals effects of fingerprint scaling in virtual screening

Fingerprint scaling is a method to increase the performance of similarity search calculations. It is based on the detection of bit patterns in keyed fingerprints that are signatures of specific compound classes. Application of scaling factors to consensus bits that are mostly set on emphasizes signature bit patterns during similarity searching and has been shown to improve search results for different fingerprints. Similarity search profiling has recently been introduced as a method to analyze similarity search calculations. Profiles separately monitor correctly identified hits and other detected database compounds as a function of similarity threshold values and make it possible to estimate whether virtual screening calculations can be successful or to evaluate why they fail. This similarity search profile technique has been applied here to study fingerprint scaling in detail and better understand effects that are responsible for its performance. In particular, we have focused on the qualitative and quantitative analysis of similarity search profiles under scaling conditions. Therefore, we have carried out systematic similarity search calculations for 23 biological activity classes under scaling conditions over a wide range of scaling factors in a compound database containing approximately 1.3 million molecules and monitored these calculations in similarity search profiles. Analysis of these profiles confirmed increases in hit rates as a consequence of scaling and revealed that scaling influences similarity search calculations in different ways. Based on scaled similarity search profiles, compound sets could be divided into different categories. In a number of cases, increases in search performance under scaling conditions were due to a more significant relative increase in correctly identified hits than detected false-positives. This was also consistent with the finding that preferred similarity threshold values increased due to fingerprint scaling, which was well illustrated by similarity search profiling.     

Large-scale similarity search profiling of ChEMBL compound data sets

A large-scale similarity search investigation has been carried out on 266 well-defined compound activity classes extracted from the ChEMBL database. The analysis was performed using two widely applied two-dimensional (2D) fingerprints that mark opposite ends of the current performance spectrum of these types of fingerprints, i.e., MACCS structural keys and the extended connectivity fingerprint with bond diameter four (ECFP4). For each fingerprint, three nearest neighbor search strategies were applied. On the basis of these search calculations, a similarity search profile of the ChEMBL database was generated. Overall, the fingerprint search campaign was surprisingly successful. In 203 of 266 test cases (～76%), a compound recovery rate of at least 50% was observed with at least the better performing fingerprint and one search strategy. The similarity search profile also revealed several general trends. For example, fingerprint searching was often characterized by an early enrichment of active compounds in database selection sets. In addition, compound activity classes have been categorized according to different similarity search performance levels, which helps to put the results of benchmark calculations into perspective. Therefore, a compendium of activity classes falling into different search performance categories is provided. On the basis of our large-scale investigation, the performance range of state-of-the-art 2D fingerprinting has been delineated for compound data sets directed against a wide spectrum of pharmaceutical targets.     

Detection of illicit substances in fingerprints by infrared spectral imaging

FTIR and Raman spectral imaging can be used to simultaneously image a latent fingerprint and detect exogenous substances deposited within it. These substances might include drugs of abuse or traces of explosives or gunshot residue. In this work, spectral searching algorithms were tested for their efficacy in finding targeted substances deposited within fingerprints. “Reverse” library searching, where a large number of possibly poor-quality spectra from a spectral image are searched against a small number of high-quality reference spectra, poses problems for common search algorithms as they are usually implemented. Out of a range of algorithms which included conventional Euclidean distance searching, the spectral angle mapper (SAM) and correlation algorithms gave the best results when used with second-derivative image and reference spectra. All methods tested gave poorer performances with first derivative and undifferentiated spectra. In a search against a caffeine reference, the SAM and correlation methods were able to correctly rank a set of 40 confirmed but poor-quality caffeine spectra at the top of a dataset which also contained 4,096 spectra from an image of an uncontaminated latent fingerprint. These methods also successfully and individually detected aspirin, diazepam and caffeine that had been deposited together in another fingerprint, and they did not indicate any of these substances as a match in a search for another substance which was known not to be present. The SAM was used to successfully locate explosive components in fingerprints deposited on silicon windows. The potential of other spectral searching algorithms used in the field of remote sensing is considered, and the applicability of the methods tested in this work to other modes of spectral imaging is discussed.     

Scaffold hopping using clique detection applied to reduced graphs

Similarity-based methods for virtual screening are widely used. However, conventional searching using 2D chemical fingerprints or 2D graphs may retrieve only compounds which are structurally very similar to the original target molecule. Of particular current interest then is scaffold hopping, that is, the ability to identify molecules that belong to different chemical series but which could form the same interactions with a receptor. Reduced graphs provide summary representations of chemical structures and, therefore, offer the potential to retrieve compounds that are similar in terms of their gross features rather than at the atom-bond level. Using only a fingerprint representation of such graphs, we have previously shown that actives retrieved were more diverse than those found using Daylight fingerprints. Maximum common substructures give an intuitively reasonable view of the similarity between two molecules. However, their calculation using graph-matching techniques is too time-consuming for use in practical similarity searching in larger data sets. In this work, we exploit the low cardinality of the reduced graph in graph-based similarity searching. We reinterpret the reduced graph as a fully connected graph using the bond-distance information of the original graph. We describe searches, using both the maximum common induced subgraph and maximum common edge subgraph formulations, on the fully connected reduced graphs and compare the results with those obtained using both conventional chemical and reduced graph fingerprints. We show that graph matching using fully connected reduced graphs is an effective retrieval method and that the actives retrieved are likely to be topologically different from those retrieved using conventional 2D methods.     

Multifingerprint based similarity searches for targeted class compound selection

Molecular fingerprints are widely used for similarity-based virtual screening in drug discovery projects. In this paper we discuss the performance and the complementarity of nine two-dimensional fingerprints (Daylight, Unity, AlFi, Hologram, CATS, TRUST, Molprint 2D, ChemGPS, and ALOGP) in retrieving active molecules by similarity searching against a set of query compounds. For this purpose, we used biological data from HTS screening campaigns of four protein families (GPCRs, kinases, ion channels, and proteases). We have established threshold values for the similarity index (Tanimoto index) to be used as starting points for similarity searches. Based on the complementarities between the selections made by using different fingerprints we propose a multifingerprint approach as an efficient tool to balance the strengths and weaknesses of various fingerprints.     

Interpretation of Ligand-Based Activity Cliff Prediction Models Using the Matched Molecular Pair Kernel

Activity cliffs (ACs) are formed by two structurally similar compounds with a large difference in potency. Accurate AC prediction is expected to help researchers’ decisions in the early stages of drug discovery. Previously, predictive models based on matched molecular pair (MMP) cliffs have been proposed. However, the proposed methods face a challenge of interpretability due to the black-box character of the predictive models. In this study, we developed interpretable MMP fingerprints and modified a model-specific interpretation approach for models based on a support vector machine (SVM) and MMP kernel. We compared important features highlighted by this SVM-based interpretation approach and the SHapley Additive exPlanations (SHAP) as a major model-independent approach. The model-specific approach could capture the difference between AC and non-AC, while SHAP assigned high weights to the features not present in the test instances. For specific MMPs, the feature weights mapped by the SVM-based interpretation method were in agreement with the previously confirmed binding knowledge from X-ray co-crystal structures, indicating that this method is able to interpret the AC prediction model in a chemically intuitive manner.