Active Learning with Support Vector Machines in the Drug Discovery Process

By Manfred K. Warmuth, Jun Liao, Gunnar Rätsch, M. Mathieson, S. Putta, Christian Lemmen. Journal of chemical information and computer sciences, 2003

345 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Spectroscopy

View Paper: https://www.semanticscholar.org/paper/c9172a3571e3c0b7032509dffdb5f16b4081241b

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 Theory and Mathematics

In Spectroscopy

Citations in the corpus

Generative Adversarial Active Learning (2017, methodology): “This simple and effective method is widely applied in many studies, e.g., (Goh et al., 2004; Warmuth et al., 2002).”
Molecular similarity analysis in virtual screening: foundations, limitations and novel approaches. (2007, methodology): “For example, there has been much interest in support vector machines (SVMs) for compound classification and class label predictions [ 13 ,14].”
Interactive machine learning for health informatics: when do we need the human-in-the-loop? (2016, methodology): “A good example was presented by Warmuth et al. [75] wherein they investigated the following data mining problem from computer-aided drug design: From a large collection of compounds, ﬁnd those that bind to a target molecule in as few iterations of biochemical testing as possible.”
Applications of Support Vector Machine (SVM) Learning in Cancer Genomics. (2018, methodology): “Warmuth et al. (43) used active learning to develop an SVM model for selecting active compounds.”
A Structure-Based Drug Discovery Paradigm (2019, methodology): “SVMs with supervised ML algorithms use binary activity prediction to distinguish between a drug and nondrug [98,99] or between specific and nonspecific compounds [100,101].”
Large-Scale Off-Target Identification Using Fast and Accurate Dual Regularized One-Class Collaborative Filtering and Its Application to Drug Repurposing (2016, neutral): “In addition, the time and memory efficiencyof REMAP makes it possible to apply active learning to overcome the cold start problem [43–46].”
Large‐scale image‐based screening and profiling of cellular phenotypes (2017, methodology): “To overcome this limitation, a semi-supervised learning method, called “active learning,” may be used (117,118).”
Toward Supervised Anomaly Detection (2014, methodology): “The idea of the method is to choose the point that is closest to the decision hypersphere (Almgren & Jonsson, 2004; Warmuth et al., 2003) to be presented to the expert:”