Understanding the phenotypic drug response on cancer cell lines plays a vital role in anti-cancer drug discovery and re-purposing. The Genomics of Drug Sensitivity in Cancer (GDSC) database provides open data for researchers in phenotypic screening to build and test their models. Previously, most research in these areas starts from the molecular fingerprints or physiochemical features of drugs, instead of their structures. In this paper, a model called twin Convolutional Neural Network for drugs in SMILES format (tCNNS) is introduced for phenotypic screening. tCNNS uses a convolutional network to extract features for drugs from their simplified molecular input line entry specification (SMILES) format and uses another convolutional network to extract features for cancer cell lines from the genetic feature vectors respectively. After that, a fully connected network is used to predict the interaction between the drugs and the cancer cell lines. When the training set and the testing set are divided based on the interaction pairs between drugs and cell lines, tCNNS achieves 0.826, 0.831 for the mean and top quartile of the coefficient of determinant (R2) respectively and 0.909, 0.912 for the mean and top quartile of the Pearson correlation (Rp) respectively, which are significantly better than those of the previous works (Ammad-Ud-Din et al., J Chem Inf Model 54:2347–9, 2014), (Haider et al., PLoS ONE 10:0144490, 2015), (Menden et al., PLoS ONE 8:61318, 2013). However, when the training set and the testing set are divided exclusively based on drugs or cell lines, the performance of tCNNS decreases significantly and Rp and R2 drop to barely above 0. Our approach is able to predict the drug effects on cancer cell lines with high accuracy, and its performance remains stable with less but high-quality data, and with fewer features for the cancer cell lines. tCNNS can also solve the problem of outliers in other feature space. Besides achieving high scores in these statistical metrics, tCNNS also provides some insights into the phenotypic screening. However, the performance of tCNNS drops in the blind test.

Molecular docking can be used to predict how strongly small‐molecule binders and their chemical derivatives bind to a macromolecular target using its available three‐dimensional structures. Scoring functions (SFs) are employed to rank these molecules by their predicted binding affinity (potency). A classical SF assumes a predetermined theory‐inspired functional form for the relationship between the features characterizing the structure of the protein–ligand complex and its predicted binding affinity (this relationship is almost always assumed to be linear). Recent years have seen the prosperity of machine‐learning SFs, which are fast regression models built instead with contemporary supervised learning algorithms. In this review, we analyzed machine‐learning SFs for drug lead optimization in the 2015–2019 period. The performance gap between classical and machine‐learning SFs was large and has now broadened owing to methodological improvements and the availability of more training data. Against the expectations of many experts, SFs employing deep learning techniques were not always more predictive than those based on more established machine learning techniques and, when they were, the performance gain was small. More codes and webservers are available and ready to be applied to prospective structure‐based drug lead optimization studies. These have exhibited excellent predictive accuracy in compelling retrospective tests, outperforming in some cases much more computationally demanding molecular simulation‐based methods. A discussion of future work completes this review.This article is categorized under: Computer and Information Science > Chemoinformatics

Protein-ligand docking is a key computational method in the design of starting points for the drug discovery process. We are motivated by the desire to automate large-scale docking using our popular docking engine idock and thus have developed a publicly-accessible web platform called istar. Without tedious software installation, users can submit jobs using our website. Our istar website supports 1) filtering ligands by desired molecular properties and previewing the number of ligands to dock, 2) monitoring job progress in real time, and 3) visualizing ligand conformations and outputting free energy and ligand efficiency predicted by idock, binding affinity predicted by RF-Score, putative hydrogen bonds, and supplier information for easy purchase, three useful features commonly lacked on other online docking platforms like DOCK Blaster or iScreen. We have collected 17,224,424 ligands from the All Clean subset of the ZINC database, and revamped our docking engine idock to version 2.0, further improving docking speed and accuracy, and integrating RF-Score as an alternative rescoring function. To compare idock 2.0 with the state-of-the-art AutoDock Vina 1.1.2, we have carried out a rescoring benchmark and a redocking benchmark on the 2,897 and 343 protein-ligand complexes of PDBbind v2012 refined set and CSAR NRC HiQ Set 24Sept2010 respectively, and an execution time benchmark on 12 diverse proteins and 3,000 ligands of different molecular weight. Results show that, under various scenarios, idock achieves comparable success rates while outperforming AutoDock Vina in terms of docking speed by at least 8.69 times and at most 37.51 times. When evaluated on the PDBbind v2012 core set, our istar platform combining with RF-Score manages to reproduce Pearson's correlation coefficient and Spearman's correlation coefficient of as high as 0.855 and 0.859 respectively between the experimental binding affinity and the predicted binding affinity of the docked conformation. istar is freely available at http://istar.cse.cuhk.edu.hk/idock.

Docking scoring functions can be used to predict the strength of protein-ligand binding. It is widely believed that training a scoring function with low-quality data is detrimental for its predictive performance. Nevertheless, there is a surprising lack of systematic validation experiments in support of this hypothesis. In this study, we investigated to which extent training a scoring function with data containing low-quality structural and binding data is detrimental for predictive performance. We actually found that low-quality data is not only non-detrimental, but beneficial for the predictive performance of machine-learning scoring functions, though the improvement is less important than that coming from high-quality data. Furthermore, we observed that classical scoring functions are not able to effectively exploit data beyond an early threshold, regardless of its quality. This demonstrates that exploiting a larger data volume is more important for the performance of machine-learning scoring functions than restricting to a smaller set of higher data quality.

Studies have shown that the accuracy of Random Forest (RF)-based Scoring Functions (SFs), such as RF-Score-v3, increases with more training samples, whereas that of classical SFs, such as X-Score, does not. Nevertheless, the impact of the similarity between training and test samples on this matter has not been studied in a systematic manner. It is therefore unclear how these SFs would perform when only trained on protein-ligand complexes that are highly dissimilar or highly similar to the test set. It is also unclear whether SFs based on machine learning algorithms other than RF can also improve accuracy with increasing training set size and to what extent they learn from dissimilar or similar training complexes. We present a systematic study to investigate how the accuracy of classical and machine-learning SFs varies with protein-ligand complex similarities between training and test sets. We considered three types of similarity metrics, based on the comparison of either protein structures, protein sequences or ligand structures. Regardless of the similarity metric, we found that incorporating a larger proportion of similar complexes to the training set did not make classical SFs more accurate. By contrast, RF-Score-v3 was able to outperform X-Score even when trained on just 32% of the most dissimilar complexes, showing that its superior performance owes considerably to learning from dissimilar training complexes to those in the test set. In addition, we generated the first SF employing Extreme Gradient Boosting (XGBoost), XGB-Score, and observed that it also improves with training set size while outperforming the rest of SFs. Given the continuous growth of training datasets, the development of machine-learning SFs has become very appealing. https://github.com/HongjianLi/MLSF Supplementary data are available at Bioinformatics online.