Profile-QSAR: A Novel meta-QSAR Method that Combines Activities across the Kinase Family To Accurately Predict Affinity, Selectivity, and Cellular Activity

Abstract

Profile-QSAR is a novel 2D predictive model building method for kinases. This "meta-QSAR" method models the activity of each compound against a new kinase target as a linear combination of its predicted activities against a large panel of 92 previously studied kinases comprised from 115 assays. Profile-QSAR starts with a sparse incomplete kinase by compound (KxC) activity matrix, used to generate Bayesian QSAR models for the 92 "basis-set" kinases. These Bayesian QSARs generate a complete "synthetic" KxC activity matrix of predictions. These synthetic activities are used as "chemical descriptors" to train partial-least squares (PLS) models, from modest amounts of medium-throughput screening data, for predicting activity against new kinases. The Profile-QSAR predictions for the 92 kinases (115 assays) gave a median external R²(ext) = 0.59 on 25% held-out test sets. The method has proven accurate enough to predict pairwise kinase selectivities with a median correlation of R²(ext) = 0.61 for 958 kinase pairs with at least 600 common compounds. It has been further expanded by adding a "C(k)XC" cellular activity matrix to the KxC matrix to predict cellular activity for 42 kinase driven cellular assays with median R²(ext) = 0.58 for 24 target modulation assays and R²(ext) = 0.41 for 18 cell proliferation assays. The 2D Profile-QSAR, along with the 3D Surrogate AutoShim, are the foundations of an internally developed iterative medium-throughput screening (IMTS) methodology for virtual screening (VS) of compound archives as an alternative to experimental high-throughput screening (HTS). The method has been applied to 20 actual prospective kinase projects. Biological results have so far been obtained in eight of them. Q² values ranged from 0.3 to 0.7. Hit-rates at 10 uM for experimentally tested compounds varied from 25% to 80%, except in K5, which was a special case aimed specifically at finding "type II" binders, where none of the compounds were predicted to be active at 10 μM. These overall results are particularly striking as chemical novelty was an important criterion in selecting compounds for testing. The method is completely automated. Predicted activities for nearly 4 million internal and commercial compounds across 115 kinase assays and 42 cellular assays are stored in the corporate database. Like computed physical properties, this predicted kinase activity profile can be computed and stored as each compound is registered.

Perspective on computational and structural aspects of kinase discovery from IPK2014

“…9)[7][13]. These were applied to predicting polypharmacology, modes-of-action for phenotypic screens, toxicity profiling, and selecting commercial compounds with diverse selectivity profiles for chemical archive enhancement.…”

Large‐Scale QSAR in Target Prediction and Phenotypic HTS Assessment

“…Classification in this context, while still quantitative, does not explicitly attempt to predict binding affinities, but rather to predict relative probability of target modulation. Alternatively, a more quantitative use of Bayesian models called Profile‐QSAR have been implemented at Novartis 17. Profile‐QSAR first computes Bayesian model scores from a panel of targets, which is in turn used as a descriptor to train partial least squares models from modest amounts of medium‐throughput screening data…”

Cheminformatics aspects of high throughput screening: from robots to models: symposium summary

“…Profile-QSAR [1], is a 2D substructure-based meta-QSAR. It requires about 500 experimental IC 50 s for a new kinase, used to train a new model using predicted activities from 100 historical kinase Quantitative Structure-Activity Relationships (QSARs) as compound descriptors.…”