Identifying novel drug-target interactions is a critical and rate-limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, here we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Here we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training to improve binding predictions for novel proteins and ligands. We validate AI-Bind predictions via docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. AI-Bind is a high-throughput approach to identify drug-target combinations with the potential of becoming a powerful tool in drug discovery.

No abstract

Data driven decision making is becoming increasingly an important aspect for successful business execution. More and more organizations are moving towards taking informed decisions based on the data that they are generating. Most of this data are in temporal format - time series data. Effective analysis across time series data sets, in an efficient and quick manner is a challenge. The most interesting and valuable part of such analysis is to generate insights on correlation and causation across multiple time series data sets. This paper looks at methods that can be used to analyze such data sets and gain useful insights from it, primarily in the form of correlation and causation analysis. This paper focuses on two methods for doing so, Two Sample Test with Dynamic Time Warping and Hierarchical Clustering and looks at how the results returned from both can be used to gain a better understanding of the data. Moreover, the methods used are meant to work with any data set, regardless of the subject domain and idiosyncrasies of the data set, primarily, a data agnostic approach.

Identifying novel drug-target interactions (DTI) is a critical and rate limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We first unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Then, we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training, allowing us to limit the annotation imbalance and improve binding predictions for novel proteins and ligands. We illustrate the value of AI-Bind by predicting drugs and natural compounds with binding affinity to SARS-CoV-2 viral proteins and the associated human proteins. We also validate these predictions via auto-docking simulations and comparison with recent experimental evidence. Overall, AI-Bind offers a powerful high-throughput approach to identify drug-target combinations, with the potential of becoming a powerful tool in drug discovery.