A review on compound-protein interaction prediction methods: Data, format, representation and model

Abstract

There has recently been a rapid progress in computational methods for determining protein targets of small molecule drugs, which will be termed as compound protein interaction (CPI). In this review, we comprehensively review topics related to computational prediction of CPI. Data for CPI has been accumulated and curated significantly both in quantity and quality. Computational methods have become powerful ever to analyze such complex the data. Thus, recent successes in the improved quality of CPI prediction are due to use of both sophisticated computational techniques and higher quality information in the databases. The goal of this article is to provide reviews of topics related to CPI, such as data, format, representation, to computational models, so that researchers can take full advantages of these resources to develop novel prediction methods. Chemical compounds and protein data from various resources were discussed in terms of data formats and encoding schemes. For the CPI methods, we grouped prediction methods into five categories from traditional machine learning techniques to state-of-the-art deep learning techniques. In closing, we discussed emerging machine learning topics to help both experimental and computational scientists leverage the current knowledge and strategies to develop more powerful and accurate CPI prediction methods.

DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations

“…In contrast to ligand-based approaches, structure-based methods (Lim et al, 2021) usually take structures of protein targets and/or protein-ligand complexes as inputs for affinity prediction. Some work (Wallach et al, 2015;Li et al, 2021b) predicts the binding affinity from experimentally determined proteinligand co-crystal structures, but such data is highly expensive and time-consuming to obtain in practice.…”

Machine learning models for classification tasks related to drug safety

“…The latter two techniques are involved as standard, classical, well-known techniques mainly for benchmarking; on the other hand, SVM, tree-based algorithms and neural networks are trending now in all aspects of data science. ML algorithms are routinely used in (i) bioactivity [5], as well as property predictions of drug related compounds [6]; (ii) de novo drug design, i.e., generation of new chemical structures of practical interest [7]; (iii) virtual screening [8]; (iv) prediction of reaction pathways [9] and v) compound-protein interactions [10], etc. ML algorithms are mainly aimed at prediction, for which a great selection of descriptors and chemical representations, as well as many ML algorithms can be combined [11].…”

Artificial intelligence in the prediction of protein–ligand interactions: recent advances and future directions

“…Recently, Lim’s team [ 41 ] published a review paper on compound protein interaction (CPI) prediction models that includes a precise description of the data format used, the techniques associated with model development and emerging methods. They also provide an overview of databases as chemistry-centric, protein-centric and integrated database and analyzed the diversified methods of AI like, tree, neural network, kernel and graph-based methods in the field of CPI.…”