In Silicotarget fishing: addressing a “Big Data” problem by ligand-based similarity rankings with data fusion

Abstract

BackgroundLigand-based in silico target fishing can be used to identify the potential interacting target of bioactive ligands, which is useful for understanding the polypharmacology and safety profile of existing drugs. The underlying principle of the approach is that known bioactive ligands can be used as reference to predict the targets for a new compound.ResultsWe tested a pipeline enabling large-scale target fishing and drug repositioning, based on simple fingerprint similarity rankings with data fusion. A large library containing 533 drug relevant targets with 179,807 active ligands was compiled, where each target was defined by its ligand set. For a given query molecule, its target profile is generated by similarity searching against the ligand sets assigned to each target, for which individual searches utilizing multiple reference structures are then fused into a single ranking list representing the potential target interaction profile of the query compound. The proposed approach was validated by 10-fold cross validation and two external tests using data from DrugBank and Therapeutic Target Database (TTD). The use of the approach was further demonstrated with some examples concerning the drug repositioning and drug side-effects prediction. The promising results suggest that the proposed method is useful for not only finding promiscuous drugs for their new usages, but also predicting some important toxic liabilities.ConclusionsWith the rapid increasing volume and diversity of data concerning drug related targets and their ligands, the simple ligand-based target fishing approach would play an important role in assisting future drug design and discovery.

Systemic QSAR and phenotypic virtual screening: chasing butterflies in drug discovery

“…In our implementation, a query ligand was considered to bind to a database target if its average molecular similarity (based on Tc) with the top three closest ligands reported in the database for that target was >0.55 or >0.85 for the closest ligand. In a tenfold cross-validation experiment, the prediction performance of our implementation was similar to the performance reported in [62]. In this way, we were able to obtain a predicted binding profile for the 28 147 ligands in our PD-relevant chemogenomics space.…”

“…Therefore, we can predict ligand—target interactions to identify the set of targets potentially involved in the biological processes perturbed by a ligand at a system level, although we cannot be 100% certain about these interactions. Several approaches for the prediction of ligand—target interactions or target fishing have been reported [62–64]. The foundations, advantages, and limitations of representative target-fishing approaches are reviewed in [65].…”

“…For target fishing, we implemented the approach proposed by Liu et al [62]. Although more sophisticated approaches are available that can be used for target fishing, we used this one because of its simplicity and easy implementation.…”

How reliable are ligand-centric methods for Target Fishing?

“…Moreover, this database is periodically updated and will eventually incorporate a flood of new data that is being extracted from the patent literature (Papadatos et al, 2016). As previously discussed (CeretoMassagué et al, 2015), TF methods have been categorized into those based on molecular similarity (Liu et al, 2014), machine learning (van Laarhoven et al, 2011), protein structure analysis (Gao et al, 2008), and bioactivity spectra analysis (Füllbeck et al, 2009;Holbeck et al, 2010). Some of these methods have been made available as web servers (Wang et al, 2013;Gfeller et al, 2014).…”

Large-Scale Prediction of Drug-Target Interaction: a Data-Centric Review

“…An extension to SEAwas proposed recently by Zheng et al, termed weighted ensemble similarity (WES) (53). There are also other SEA-like approaches, e.g., SuperPred (54) and similarity ranking with data fusion (55).…”