Computational drug repositioning based on the relationships between substructure-indication

SDDSynergy: Learning Important Molecular Substructures for Explainable Anticancer Drug Synergy Prediction

Drug combination therapies are well-established strategies for the treatment of cancer with low toxicity and fewer adverse effects. Computational drug synergy prediction approaches can accelerate the discovery of novel combination therapies, but the existing methods do not explicitly consider the key role of important substructures in producing synergistic effects. To this end, we propose a significant substructure-aware anticancer drug synergy prediction method, named SDDSynergy, to adaptively identify critical functional groups in drug synergy. SDDSynergy splits the task of predicting drug synergy into predicting the effect of individual substructures on cancer cell lines and highlights the impact of important substructures through a novel drug-cell line attention mechanism. And a substructure pair attention mechanism is incorporated to capture the information on internal substructure pairs interaction in drug combinations, which aids in predicting synergy. The substructures of different sizes and shapes are directly obtained from the molecular graph of the drugs by multilayer substructure information passing networks. Extensive experiments on three real-world data sets demonstrate that SDDSynergy outperforms other state-of-the-art methods. We also verify that many of the novel drug combinations predicted by SDDSynergy are supported by previous studies or clinical trials through an in-depth literature survey.

DAPredict: a database for drug action phenotype prediction

The phenotypes of drug action, including therapeutic actions and adverse drug reactions (ADRs), are important indicators for evaluating the druggability of new drugs and repositioning the approved drugs. Here, we provide a user-friendly database, DAPredict (http://bio-bigdata.hrbmu.edu.cn/DAPredict), in which our novel original drug action phenotypes prediction algorithm (Yang,J., Zhang,D., Liu,L. et al. (2021) Computational drug repositioning based on the relationships between substructure-indication. Brief. Bioinformatics, 22, bbaa348) was embedded. Our algorithm integrates characteristics of chemical genomics and pharmacogenomics, breaking through the limitations that traditional drug development process based on phenotype cannot analyze the mechanism of drug action. Predicting phenotypes of drug action based on the local active structures of drugs and proteins can achieve more innovative drug discovery across drug categories and simultaneously evaluate drug efficacy and safety, rather than traditional one-by-one evaluation. DAPredict contains 305 981 predicted relationships between 1748 approved drugs and 454 ADRs, 83 117 predicted relationships between 1478 approved drugs and 178 Anatomical Therapeutic Chemicals (ATC). More importantly, DAPredict provides an online prediction tool, which researchers can use to predict the action phenotypic spectrum of more than 110 000 000 compounds (including about 168 000 natural products) and corresponding proteins to analyze their potential effect mechanisms. DAPredict can also help researchers obtain the phenotype-corresponding active structures for structural optimization of new drug candidates, making it easier to evaluate the druggability of new drug candidates and develop more innovative drugs across drug categories. Database URL:  http://bio-bigdata.hrbmu.edu.cn/DAPredict/.

Self-Supervised Learning for Label Sparsity in Computational Drug Repositioning

The computational drug repositioning aims to discover new uses for marketed drugs, which can accelerate the drug development process and play an important role in the existing drug discovery system. However, the number of validated drug-disease associations is scarce compared to the number of drugs and diseases in the real world. Too few labeled samples will make the classification model unable to learn effective latent factors of drugs, resulting in poor generalization performance. In this work, we propose a multi-task self-supervised learning framework for computational drug repositioning. The framework tackles label sparsity by learning a better drug representation. Specifically, we take the drug-disease association prediction problem as the main task, and the auxiliary task is to use data augmentation strategies and contrast learning to mine the internal relationships of the original drug features, so as to automatically learn a better drug representation without supervised labels. And through joint training, it is ensured that the auxiliary task can improve the prediction accuracy of the main task. More precisely, the auxiliary task improves drug representation and serving as additional regularization to improve generalization. Furthermore, we design a multi-input decoding network to improve the reconstruction ability of the autoencoder model. We evaluate our model using three real-world datasets. The experimental results demonstrate the effectiveness of the multi-task self-supervised learning framework, and its predictive ability is superior to the state-of-the-art model.

The Computational Drug Repositioning Without Negative Sampling

Computational drug repositioning technology is an effective tool to accelerate drug development. Although this technique has been widely used and successful in recent decades, many existing models still suffer from multiple drawbacks such as the massive number of unvalidated drug-disease associations and the inner product. The limitations of these works are mainly due to the following two reasons: firstly, previous works used negative sampling techniques to treat unvalidated drug-disease associations as negative samples, which is invalid in real-world settings; secondly, the inner product cannot fully take into account the feature information contained in the latent factor of drug and disease. In this paper, we propose a novel PUON framework for addressing the above deficiencies, which models the risk estimator of computational drug repositioning only using validated (Positive) and unvalidated (Unlabelled) drug-disease associations without employing negative sampling techniques. The PUON also proposed an Outer Neighborhood-based classifier for modeling the cross-feature information of the latent facotor. For a comprehensive comparison, we considered 6 popular baselines. Extensive experiments in four real-world datasets showed that PUON model achieved the best performance based on 6 evaluation metrics.

New frontier radioiodinated probe based on in silico resveratrol repositioning for microtubules dynamic targeting

PURPOSE

As the 'de novo' drug discovery faces a highly attrition rates, drug repositioning procures a heighten concern in identifying novel uses for existing medications. This study aimed to fabricate radioiodinated resveratrol as a potent microtubules interfering agent for cancer theragnosis.

METHODS

Resveratrol was radiolabeled with radioactive iodine where the radioiodination efficiency was enlightened and the computational approaches were employed to investigate the affinity and specificity with tubulins. Furthermore, the in-vivo distribution and pharmacokinetic studies in normal and tumor induced mice were investigated.

RESULTS

The maximum radioiodination yield (94.6 ± 1.66) was achieved at optimum preparation parameters stated as 100 μg/mL of oxidizing agent, 100 μg/ml of resveratrol, reaction time of 30 min and reaction pH 5. The in silico studies showed that di-iodinated resveratrol (compound 6) exhibited the best binding score (-34.46) and interaction with the β-tubulin binding site. The in vivo distribution in tumor models revealed a significant accumulation (4.02% ID/g) in tumor lesion at 60 min p.i. The rate of drug elimination demonstrated a mono-exponential decline of radioactivity versus time in the blood.

CONCLUSION

Radioiodinated resveratrol revealed good microtubules targeting which render it as a novel theranostic probe for cancer management.

Guiding Drug Repositioning for Cancers Based on Drug Similarity Networks

Drug repositioning aims to discover novel clinical benefits of existing drugs, is an effective way to develop drugs for complex diseases such as cancer and may facilitate the process of traditional drug development. Meanwhile, network-based computational biology approaches, which allow the integration of information from different aspects to understand the relationships between biomolecules, has been successfully applied to drug repurposing. In this work, we developed a new strategy for network-based drug repositioning against cancer. Combining the mechanism of action and clinical efficacy of the drugs, a cancer-related drug similarity network was constructed, and the correlation score of each drug with a specific cancer was quantified. The top 5% of scoring drugs were reviewed for stability and druggable potential to identify potential repositionable drugs. Of the 11 potentially repurposable drugs for non-small cell lung cancer (NSCLC), 10 were confirmed by clinical trial articles and databases. The targets of these drugs were significantly enriched in cancer-related pathways and significantly associated with the prognosis of NSCLC. In light of the successful application of our approach to colorectal cancer as well, it provides an effective clue and valuable perspective for drug repurposing in cancer.

Concepts and applications of chemical fingerprint for hit and lead screening

Molecular fingerprints are used to represent chemical (structural, physicochemical, etc.) properties of large-scale chemical sets in a low computational cost way. They have a prominent role in transforming chemical data sets into consistent input formats (bit strings or numeric values) suitable for in silico approaches. In this review, we summarize and classify common and state-of-the-art fingerprints into eight different types (dictionary based, circular, topological, pharmacophore, protein-ligand interaction, shape based, reinforced, and multi). We also highlight applications of fingerprints in early drug research and development (R&D). Thus, this review provides a guide for the selection of appropriate fingerprints of compounds (or ligand-protein complexes) for use in drug R&D.

Cascade Deep Forest With Heterogeneous Similarity Measures for Drug-Target Interaction Prediction

Drug repositioning is a method of systematically identifying potential molecular targets that known drugs may act on. Compared with traditional methods, drug repositioning has been extensively studied due to the development of multi-omics technology and system biology methods. Because of its biological network properties, it is possible to apply machine learning related algorithms for prediction. Based on various heterogeneous network model, this paper proposes a method named THNCDF for predicting drug-target interactions. Various heterogeneous networks are integrated to build a tripartite network, and similarity calculation methods are used to obtain similarity matrix. Then, the cascade deep forest method is used to make prediction. Results indicate that THNCDF outperforms the previously reported methods based on the 10-fold cross-validation on the benchmark data sets proposed by Y. Yamanishi. The area under Precision Recall curve (AUPR) value on the Enzyme, GPCR, Ion Channel, and Nuclear Receptor data sets is 0.988, 0.980, 0.938, and 0.906 separately. The experimental results well illustrate the feasibility of this method.