Toward more realistic drug–target interaction predictions

By Tapio Pahikkala, Antti Airola, Sami Pietilä, Sushil Kumar Shakyawar, Agnieszka Szwajda, Jing Tang, Tero Aittokallio. Briefings Bioinform., 2014

514 citations recorded by the source corpus.

A number of supervised machine learning models have recently been introduced for the prediction of drug–target interactions based on chemical structure and genomic sequence information. Although these models could offer improved means for many network pharmacology applications, such as repositioning of drugs for new therapeutic uses, the prediction models are often being constructed and evaluated under overly simplified settings that do not reflect the real-life problem in practical applications. Using quantitative drug–target bioactivity assays for kinase inhibitors, as well as a popular benchmarking data set of binary drug–target interactions for enzyme, ion channel, nuclear receptor and G protein-coupled receptor targets, we illustrate here the effects of four factors that may lead to dramatic differences in the prediction results: (i) problem formulation (standard binary classification or more realistic regression formulation), (ii) evaluation data set (drug and target families in the application use case), (iii) evaluation procedure (simple or nested cross-validation) and (iv) experimental setting (whether training and test sets share common drugs and targets, only drugs or targets or neither). Each of these factors should be taken into consideration to avoid reporting overoptimistic drug–target interaction prediction results. We also suggest guidelines on how to make the supervised drug–target interaction prediction studies more realistic in terms of such model formulations and evaluation setups that better address the inherent complexity of the prediction task in the practical applications, as well as novel benchmarking data sets that capture the continuous nature of the drug–target interactions for kinase inhibitors.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/5118d7d97271bcae11b56ac36c6375925c8ce8e8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Materials Chemistry

In Molecular Biology

Citations in the corpus

Interpretable Drug Target Prediction Using Deep Neural Representation (2018, background): “[Pahikkala et al. , 2014] suggested that there are 4 experimental settings under which the model can be learned and applied to predict the label between a drug (candidate) and a protein target d and p : We split proteins and drugs into those that should be observed in training and those that should…”
Neighborhood Regularized Logistic Matrix Factorization for Drug-Target Interaction Prediction (2016, unknown): “We conducted CV under three different settings as follows [19, 27, 41].”
SimBoost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines (2017, methodology): “Pahik-kala et al. [4] introduces the method KronRLS which predicts continuous drug–target binding affinity values.”
Machine learning approaches and databases for prediction of drug–target interaction: a survey paper (2020, methodology): “In recent years, pharmaceutical scientists have been highly focused on novel drug development strategies that rely on knowledge about existing drugs [ 1–5].”
Pre-training Molecular Graph Representation with 3D Geometry (2021, unknown): “7, 28 [71] Tapio Pahikkala, Antti Airola, Sami Pietilä, Sushil Shakyawar, Agnieszka Szwajda, Jing Tang, and Tero Aittokallio.”
Predicting commercially available antiviral drugs that may act on the novel coronavirus (SARS-CoV-2) through a drug-target interaction deep learning model (2020, unknown): “Neverthless, MT-DTI showed the best performance [12] when compared to a deep learning-based (DeepDTA) approach [21] and two traditional machine learning-based algorithms SimBoost [22], and KronRLS [23], with the KIBA [24] and DAVIS [25] data sets.”
MolTrans: Molecular Interaction Transformer for drug–target interaction prediction (2020, unknown): “hree. 4.2. Baselines We compared MolTrans with the following baselines. We focus on state-ofthe-art deep learning models as they have demonstrated superior performance over shallow models. 1. KronRLS [13] applies a kernel least square method on the similarity matrix of drug and protein features. 2. ”
DeepDTA: deep drug–target binding affinity prediction (2018, methodology): “These values correspond to the negative pairs that either have very weak binding affinities ( K d > 10000 nM ) or are not observed in the primary screen [42].”
DeepPurpose: a deep learning library for drug–target interaction prediction (2020, methodology): “To demonstrate the use of DeepPurpose, we compare DeepPurpose with KronRLS [Pahikkala et al., 2015], a popular DTI method, and GraphDTA [Nguyen et al.”