The Influence Relevance Voter: An Accurate And Interpretable Virtual High Throughput Screening Method

By S. Joshua Swamidass, Chloé-Agathe Azencott, Ting-Wan Lin, H. Gramajo, S. Tsai, Pierre Baldi. 2009

56 citations recorded by the source corpus.

Given activity training data from Hight-Throughput Screening (HTS) experiments, virtual High-Throughput Screening (vHTS) methods aim to predict in silico the activity of untested chemicals. We present a novel method, the Influence Relevance Voter (IRV), specifically tailored for the vHTS task. The IRV is a low-parameter neural network which refines a k-nearest neighbor classifier by non-linearly combining the influences of a chemical's neighbors in the training set. Influences are decomposed, also non-linearly, into a relevance component and a vote component. The IRV is benchmarked using the data and rules of two large, open, competitions, and its performance compared to the performance of other participating methods, as well as of an in-house Support Vector Machine (SVM) method. On these benchmark datasets, IRV achieves state-of-the-art results, comparable to the SVM in one case, and significantly better than the SVM in the other, retrieving three times as many actives in the top 1% of its prediction-sorted list. The IRV presents several other important advantages over SVMs and other methods: (1) the output predictions have a probabilistic semantic; (2) the underlying inferences are interpretable; (3) the training time is very short, on the order of minutes even for very large data sets; (4) the risk of overfitting is minimal, due to the small number of free parameters; and (5) additional information can easily be incorporated into the IRV architecture. Combined with its performance, these qualities make the IRV particularly well suited for vHTS.

Subfields: Artificial Intelligence, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Chemistry & Drug Discovery

Citations in the corpus

Interpreting linear support vector machine models with heat map molecule coloring (2011, methodology): “Swamidass et al. [5] introduced the Influence Relevance Voter, an interpretable method based on a supervised artificial neural network in combination with a k-nearest neighbor approach.”
Molecular graph convolutions: moving beyond fingerprints (2016, background): “prints’’ [9] and influence relevance voter [36].”
Massively Multitask Networks for Drug Discovery (2015, background): “…has moved to more reﬁned models, such as the inﬂuence relevance voting method that combines low-complexity neural networks and k-nearest neighbors (Swamidass et al., 2009), and Bayesian belief networks that repurpose textual information retrieval methods for virtual screening (Abdo et al.,…”
Message passing neural networks for molecular property prediction (2019, methodology): “The models in [46] include MPNN [20], Weave [22], GraphConv, kernel ridge regression, gradient boosting [19], random forest [6], logistic regression [12], directed acyclic graph models [29], support vector machines [11], Deep Tensor Neural Networks [40], multitask networks [30], bypass networks [36]”
Accurate and efficient target prediction using a potency-sensitive influence-relevance voter (2015, unknown): “Fingerprint similarity is widely used in chemical informatics as a way of quantifying similarity between molecules [5, 30].”