Using Information from Historical High-Throughput Screens to Predict Active Compounds

Abstract

Modern high-throughput screening (HTS) is a well-established approach for hit finding in drug discovery that is routinely employed in the pharmaceutical industry to screen more than a million compounds within a few weeks. However, as the industry shifts to more disease-relevant but more complex phenotypic screens, the focus has moved to piloting smaller but smarter chemically/biologically diverse subsets followed by an expansion around hit compounds. One standard method for doing this is to train a machine-learning (ML) model with the chemical fingerprints of the tested subset of molecules and then select the next compounds based on the predictions of this model. An alternative approach would be to take advantage of the wealth of bioactivity information contained in older (full-deck) screens using so-called HTS fingerprints, where each element of the fingerprint corresponds to the outcome of a particular assay, as input to machine-learning algorithms. We constructed HTS fingerprints using two collections of data: 93 in-house assays and 95 publicly available assays from PubChem. For each source, an additional set of 51 and 46 assays, respectively, was collected for testing. Three different ML methods, random forest (RF), logistic regression (LR), and naïve Bayes (NB), were investigated for both the HTS fingerprint and a chemical fingerprint, Morgan2. RF was found to be best suited for learning from HTS fingerprints yielding area under the receiver operating characteristic curve (AUC) values >0.8 for 78% of the internal assays and enrichment factors at 5% (EF(5%)) >10 for 55% of the assays. The RF(HTS-fp) generally outperformed the LR trained with Morgan2, which was the best ML method for the chemical fingerprint, for the majority of assays. In addition, HTS fingerprints were found to retrieve more diverse chemotypes. Combining the two models through heterogeneous classifier fusion led to a similar or better performance than the best individual model for all assays. Further validation using a pair of in-house assays and data from a confirmatory screen--including a prospective set of around 2000 compounds selected based on our approach--confirmed the good performance. Thus, the combination of machine-learning with HTS fingerprints and chemical fingerprints utilizes information from both domains and presents a very promising approach for hit expansion, leading to more hits. The source code used with the public data is provided.

MetMaxStruct: A Tversky-Similarity-Based Strategy for Analysing the (Sub)Structural Similarities of Drugs and Endogenous Metabolites

“…In a similar vein, as before (O'Hagan and Kell, 2015b,c; O'Hagan et al, 2015), we used the KNIME software (see http://knime.org/ and e.g., Berthold et al, 2008; Mazanetz et al, 2012; Beisken et al, 2013) to create workflows for our analyses. In particular, substantial use was made of the RDKit nodes (see http://rdkit.org/ and e.g., Landrum et al, 2011; Landrum and Stiefl, 2012; Riniker and Landrum, 2013; Riniker et al, 2013, 2014; O'Hagan and Kell, 2015b), noting the very useful “fraggle” (http://www.rdkit.org/Python_Docs/rdkit.Chem.Fraggle-module.html). The Tv similarity calculations were obtained using a node from the Indigo library (see Saubern et al, 2011).…”

Every Jack has His Jill: Finding a Target for Your Combinatorial Library

“…Quite new is the inverse approach-to create ligand bioactivity fingerprints encoding the hit status of compounds from HTS campaigns [19,20]. In combination with conventional ligand fingerprints those allow to identify chemically similar ligands that should have similar bioactivity profiles.…”

A Multimodal Data Analysis Approach for Targeted Drug Discovery Involving Topological Data Analysis (TDA)

“…With this knowledge, we can recursively add more compounds from those families to our initial library, as we know those families may contain certain important features. This method of expanding compound libraries around the hit compounds is becoming more prevalent in the pharmaceutical industry [24]. …”

“…For example, prior research has shown that a machine-learning model trained on HTS and chemical fingerprints performed similar or better than a model trained on either subset alone [24]. But even such approaches suffer from the same problem of selectively favoring compounds that perform well in the tested assays.…”