Significant advances have been made in the in silico prediction of molecular and pharmacokinetic properties associated with successful drug-like molecules (Leeson et al., 2021; Lombardo et al., 2017). These cheminformatics advances have laid the foundation for further enhancements in drug candidate screening, prioritization for advancement into in vivo studies, and clinical candidate selection (Maurer et al., 2021). Despite these impressive improvements in molecular property predictions, a considerable challenge remains in accurately predicting the affinity/potency of a ligand-protein interaction (LPI), also known as a drug-target interaction (DTI) (Yamanishi et al., 2008). Drugs convey their phenotypic effects through interactions with a variety of biological targets with varying affinities (Swinney & Anthony, 2011). Some interactions produce desirable outcomes and phenotypes, while others can create undesired side effects and/or safety risks (Waring et al., 2015). Accurately predicting the affinities of ligand-protein interactions would enable drug discovery teams to better design and prioritize the synthesis of molecules that interact with intended protein targets, while minimizing undesired interactions with off-targets like hERG and liver enzymes, ultimately increasing the chances of preclinical success.

Accurate prediction of protein-ligand binding affinities is crucial for drug development. Recent advances in machine learning show promising results on this task. However, these methods typically rely heavily on labeled data, which can be scarce or unreliable, or they rely on assumptions like Boltzmann-distributed data that may not hold true in practice. Here, we present DualBind, a novel framework that integrates supervised mean squared error (MSE) with unsupervised denoising score matching (DSM) to accurately learn the binding energy function. DualBind not only addresses the limitations of DSM-only models by providing more accurate absolute affinity predictions but also improves generalizability and reduces reliance on labeled data compared to MSE-only models. Our experimental results demonstrate that DualBind excels in predicting binding affinities and can effectively utilize both labeled and unlabeled data to enhance performance.

Identification of high affinity drug-target interactions (DTI) is a major research question in drug discovery. In this study, we propose a novel methodology to predict drug-target binding affinity using only ligand SMILES information. We represent proteins using the word-embeddings of the SMILES representations of their strong binding ligands. Each SMILES is represented in the form of a set of chemical words and a protein is described by the set of chemical words with the highest Term Frequency- Inverse Document Frequency (TF-IDF) value. We then utilize the Support Vector Regression (SVR) algorithm to predict protein - drug binding affinities in the Davis and KIBA Kinase datasets. We also compared the performance of SMILES representation with the recently proposed DeepSMILES representation and found that using DeepSMILES yields better performance in the prediction task. Using only SMILESVec, which is a strictly string based representation of the proteins based on their interacting ligands, we were able to predict drug-target binding affinity as well as or better than the KronRLS or SimBoost models that utilize protein sequence.

We present approaches to handle diverse assignments in multi-cycle assignment problems. The goal is to assign a task to different agents in each cycle, such that all possible combinations are made over time. Our method combines the original profit value, that is to be optimized by the assignment problem with an additional assignment preference. By merging both, we steer the optimization towards diverse assignments without large trade-offs in the original profits.