We consider lead discovery as active search in a space of labelled graphs. In particular, we extend our recent data-driven adaptive Markov chain approach, and evaluate it on a focused drug design problem, where we search for an antagonist of an αv integrin, the target protein that belongs to a group of Arg-Gly-Asp integrin receptors. This group of integrin receptors is thought to play a key role in idiopathic pulmonary fibrosis, a chronic lung disease of significant pharmaceutical interest. As an in silico proxy of the binding affinity, we use a molecular docking score to an experimentally determined αvβ6 protein structure. The search is driven by a probabilistic surrogate of the activity of all molecules from that space. As the process evolves and the algorithm observes the activity scores of the previously designed molecules, the hypothesis of the activity is refined. The algorithm is guaranteed to converge in probability to the best hypothesis from an a priori specified hypothesis space. In our empirical evaluations, the approach achieves a large structural variety of designed molecular structures for which the docking score is better than the desired threshold. Some novel molecules, suggested to be active by the surrogate model, provoke a significant interest from the perspective of medicinal chemistry and warrant prioritization for synthesis. Moreover, the approach discovered 19 out of the 24 active compounds which are known to be active from previous biological assays.
Due to limited computational resources, acoustic models of early automatic speech recognition (ASR) systems were built in lowdimensional feature spaces that incur considerable information loss at the outset of the process. Several comparative studies of automatic and human speech recognition suggest that this information loss can adversely affect the robustness of ASR systems. To mitigate that and allow for learning of robust models, we propose a deep 2D convolutional network in the waveform domain. The first layer of the network decomposes waveforms into frequency sub-bands, thereby representing them in a structured high-dimensional space. This is achieved by means of a parametric convolutional block defined via cosine modulations of compactly supported windows. The next layer embeds the waveform in an even higher-dimensional space of high-resolution spectro-temporal patterns, implemented via a 2D convolutional block. This is followed by a gradual compression phase that selects most relevant spectro-temporal patterns using wide-pass 2D filtering. Our results show that the approach significantly outperforms alternative waveform-based models on both noisy and spontaneous conversational speech (24% and 11% relative error reduction, respectively). Moreover, this study provides empirical evidence that learning directly from the waveform domain could be more effective than learning using hand-crafted features.
Abstract. Data understanding is an iterative process in which domain experts combine their knowledge with the data at hand to explore and confirm hypotheses. One important set of tools for exploring hypotheses about data are visualizations. Often, however, traditional, unsupervised dimensionality reduction algorithms are used for visualization. These tools allow for interaction, i.e., exploring different visualizations, only by means of manipulating some technical parameters of the algorithm. Therefore, instead of being able to intuitively interact with the visualization, domain experts have to learn and argue about these technical parameters. In this paper we propose a knowledge-based kernel PCA approach that allows for intuitive interaction with data visualizations. Each embedding direction is given by a non-convex quadratic optimization problem over an ellipsoid and has a globally optimal solution in the kernel feature space. A solution can be found in polynomial time using the algorithm presented in this paper. To facilitate direct feedback, i.e., updating the whole embedding with a sufficiently high frame-rate during interaction, we reduce the computational complexity further by incremental up-and down-dating. Our empirical evaluation demonstrates the flexibility and utility of this approach.
Random Fourier features is a widely used, simple, and effective technique for scaling up kernel methods. The existing theoretical analysis of the approach, however, remains focused on specific learning tasks and typically gives pessimistic bounds which are at odds with the empirical results. We tackle these problems and provide the first unified risk analysis of learning with random Fourier features using the squared error and Lipschitz continuous loss functions. In our bounds, the trade-off between the computational cost and the expected risk convergence rate is problem specific and expressed in terms of the regularization parameter and the number of effective degrees of freedom. We study both the standard random Fourier features method for which we improve the existing bounds on the number of features required to guarantee the corresponding minimax risk convergence rate of kernel ridge regression, as well as a data-dependent modification which samples features proportional to ridge leverage scores and further reduces the required number of features. As ridge leverage scores are expensive to compute, we devise a simple approximation scheme which provably reduces the computational cost without loss of statistical efficiency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.