Recognizing novel chemicals/drugs for anatomical therapeutic chemical classes with a heat diffusion algorithm

PDATC-NCPMKL: Predicting drug's Anatomical Therapeutic Chemical (ATC) codes based on network consistency projection and multiple kernel learning

The development and discovery of new drugs is time-consuming and needs lots of human and material resources. Therefore, discovery of novel effects of existing drugs is an important alternative way, which can accelerate the process of designing "new" drugs. The anatomical Therapeutic Chemical (ATC) classification system recommended by World Health Organization (WHO) is a basic research area in this regard. A novel ATC code of an existing drug suggests its novel effects. Some computational models have been proposed, which can predict the drug-ATC code associations. However, their performance is not very high. There still exist spaces for improvement. In this study, a new recommendation system (named PDATC-NCPMKL), which incorporated network consistency projection and multi-kernel learning, was designed to identify drug-ATC code associations. For drugs or ATC codes, several kernels were constructed, which were fused by a multiple kernel learning method and an additional kernel integration scheme. To enhance the performance, the drug-ATC code association adjacency matrix was reformulated by a variant of weighted K nearest known neighbors (WKNKN). The reformulated adjacency matrix, drug and ATC code kernels were fed into network consistency projection to generate the association score matrix. The proposed recommendation system was tested on the ATC codes at the second, third and fourth levels in drug ATC classification system using ten-fold cross-validation. The results indicated that all AUROC and AUPR values were close to or exceeded 0.96. Such performance was higher than some existing computational models. Some additional tests were conducted to prove the utility of adjacency matrix reformulation and to analyze the importance of drug and ATC code kernels.

Polypharmacy prevalence and associated factors in patients with systemic lupus erythematosus: A single-centre, cross-sectional study

OBJECTIVES

This study aimed to clarify factors associated with polypharmacy among patients with systemic lupus erythematosus.

METHODS

This single-centre cross-sectional study was conducted by reviewing the medical records and questionnaire data of 261 systemic lupus erythematosus patients at a teaching hospital in Japan from 1 September to 30 November 2020. Polypharmacy was defined as the regular administration of five or more oral medications; excessive polypharmacy consisted of the regular use of 10 or more oral medications. This study investigated (1) the prevalence of polypharmacy and excessive polypharmacy, (2) the distribution of medication types, and (3) the factors associated with polypharmacy and excessive polypharmacy.

RESULTS

The proportions of patients who exhibited polypharmacy and excessive polypharmacy were 70% and 19%, respectively. Polypharmacy was associated with older age, long duration of systemic lupus erythematosus, high disease activity, and administration of glucocorticoids or immunosuppressive agents. Excessive polypharmacy was associated with a higher updated Charlson comorbidity index, history of visits to multiple internal medicine clinics, and presence of public assistance.

CONCLUSIONS

Polypharmacy and excessive polypharmacy in patients with systemic lupus erythematosus are related to medical aspects such as disease severity and comorbidities in addition to social aspects such as hospital visitation patterns and economic status.

Prevalence and factors associated with polypharmacy among patients with rheumatoid arthritis: a single-centre, cross-sectional study

OBJECTIVE

This study aimed to identify factors associated with polypharmacy, including social aspects, among patients with rheumatoid arthritis.

METHODS

We conducted this single-centre, cross-sectional study at a 715-bed regional tertiary care teaching hospital in Japan from 1 September to 30 November 2020. Polypharmacy was defined as having five or more medications administered orally regularly, and excessive polypharmacy was defined as having 10 or more medications administered orally regularly. The prevalence of polypharmacy and excessive polypharmacy, distribution of medication types, and factors associated with polypharmacy and excessive polypharmacy were investigated among patients with rheumatoid arthritis.

RESULTS

The proportions of polypharmacy and excessive polypharmacy were 61% and 15%, respectively, in 991 patients. Polypharmacy and excessive polypharmacy were associated with older age (odds ratio, 1.03 and 1.03, respectively), high Health Assessment Questionnaire Disability Index (odds ratio, 1.45 and 2.03, respectively), medication with glucocorticoids (odds ratio, 5.57 and 2.42, respectively), high Charlson comorbidity index (odds ratio, 1.28 and 1.36, respectively), and a history of hospitalisation in internal medicine (odds ratio, 1.92 and 1.87, respectively) and visits to other internal medicine clinics (odds ratio, 2.93 and 2.03, respectively). Moreover, excessive polypharmacy was associated with the presence of public assistance (odds ratio, 3.80).

CONCLUSIONS

Considering that polypharmacy and excessive polypharmacy are associated with a history of hospitalisation and glucocorticoid medication in patients with rheumatoid arthritis, medications during hospitalisation should be monitored, and glucocorticoids should be discontinued. Key points • The proportion of polypharmacy (five or more medications administered orally regularly) was 61%. • The proportion of excessive polypharmacy (10 or more medications administered orally regularly) was 15%. • Medications during hospitalisation should be reviewed and examined, and glucocorticoids should be discontinued.

The association between prescription drugs and colorectal cancer prognosis: a nationwide cohort study using a medication-wide association study

BACKGROUND

With the availability of health insurance claim data, pharmacovigilance for various drugs has been suggested; however, it is necessary to establish an appropriate analysis method. To detect unintended drug effects and to generate new hypotheses, we conducted a hypothesis-free study to systematically examine the relationship between all prescription nonanticancer drugs and the mortality of colorectal cancer patients.

METHODS

We used the Korean National Health Insurance Service-National Sample Cohort database. A total of 2,618 colorectal cancer patients diagnosed between 2004 and 2015 were divided into drug discovery and drug validation sets (1:1) through random sampling. Drugs were classified using the Anatomical Therapeutic Chemical (ATC) classification system: 76 drugs classified as ATC level 2 and 332 drugs classified as ATC level 4 were included in the analysis. We used a Cox proportional hazard model adjusted for sex, age, colorectal cancer treatment, and comorbidities. The relationship between all prescription nonanticancer drugs and the mortality of colorectal cancer patients was analyzed, controlling for multiple comparisons with the false discovery rate.

RESULTS

We found that one ATC level-2 drug (drugs that act on the nervous system, including parasympathomimetics, addictive disorder drugs, and antivertigo drugs) showed a protective effect related to colorectal cancer prognosis. At the ATC level 4 classification, 4 drugs were significant: two had a protective effect (anticholinesterases and opioid anesthetics), and the other two had a detrimental effect (magnesium compounds and Pregnen [4] derivatives).

CONCLUSIONS

In this hypothesis-free study, we identified four drugs linked to colorectal cancer prognosis. The MWAS method can be useful in real-world data analysis.

Identification of drug side effects with a path-based method

The study of drug side effects is a significant task in drug discovery. Candidate drugs with unaccepted side effects must be eliminated to prevent risks for both patients and pharmaceutical companies. Thus, all side effects for any candidate drug should be determined. However, this task, which is carried out through traditional experiments, is time-consuming and expensive. Building computational methods has been increasingly used for the identification of drug side effects. In the present study, a new path-based method was proposed to determine drug side effects. A heterogeneous network was built to perform such method, which defined drugs and side effects as nodes. For any drug and side effect, the proposed path-based method determined all paths with limited length that connects them and further evaluated the association between them based on these paths. The strong association indicates that the drug has a side effect with a high probability. By using two types of jackknife test, the method yielded good performance and was superior to some other network-based methods. Furthermore, the effects of one parameter in the method and heterogeneous network was analyzed.

Similarity-Based Method with Multiple-Feature Sampling for Predicting Drug Side Effects

Drugs can treat different diseases but also bring side effects. Undetected and unaccepted side effects for approved drugs can greatly harm the human body and bring huge risks for pharmaceutical companies. Traditional experimental methods used to determine the side effects have several drawbacks, such as low efficiency and high cost. One alternative to achieve this purpose is to design computational methods. Previous studies modeled a binary classification problem by pairing drugs and side effects; however, their classifiers can only extract one feature from each type of drug association. The present work proposed a novel multiple-feature sampling scheme that can extract several features from one type of drug association. Thirteen classification algorithms were employed to construct classifiers with features yielded by such scheme. Their performance was greatly improved compared with that of the classifiers that use the features yielded by the original scheme. Best performance was observed for the classifier based on random forest with MCC of 0.8661, AUROC of 0.969, and AUPR of 0.977. Finally, one key parameter in the multiple-feature sampling scheme was analyzed.

Identification of Novel Choroidal Neovascularization-Related Genes Using Laplacian Heat Diffusion Algorithm

Choroidal neovascularization (CNV) is a type of eye disease that can cause vision loss. In recent years, many studies have attempted to investigate the major pathological processes and molecular pathogenic mechanisms of CNV. Because many diseases are related to genes, the genes associated with CNV need to be identified. In this study, we proposed a network-based approach for identifying novel CNV-associated genes. To execute such method, we first employed a protein-protein interaction network reported in STRING. Then, we applied a network diffusion algorithm, Laplacian heat diffusion, on this network by selecting validated CNV-related genes as the seed nodes. As a result, some novel genes that had unknown but strong relationships with validated genes were identified. Furthermore, we used a screening procedure to extract the most essential genes. Eleven latent CNV-related genes were finally obtained. Extensive analyses were performed to confirm that these genes are novel CNV-related genes.

Deep fusion learning facilitates anatomical therapeutic chemical recognition in drug repurposing and discovery

The advent of large-scale biomedical data and computational algorithms provides new opportunities for drug repurposing and discovery. It is of great interest to find an appropriate data representation and modeling method to facilitate these studies. The anatomical therapeutic chemical (ATC) classification system, proposed by the World Health Organization (WHO), is an essential source of information for drug repurposing and discovery. Besides, computational methods are applied to predict drug ATC classification. We conducted a systematic review of ATC computational prediction studies and revealed the differences in data sets, data representation, algorithm approaches, and evaluation metrics. We then proposed a deep fusion learning (DFL) framework to optimize the ATC prediction model, namely DeepATC. The methods based on graph convolutional network, inferring biological network and multimodel attentive fusion network were applied in DeepATC to extract the molecular topological information and low-dimensional representation from the molecular graph and heterogeneous biological networks. The results indicated that DeepATC achieved superior model performance with area under the curve (AUC) value at 0.968. Furthermore, the DFL framework was performed for the transcriptome data-based ATC prediction, as well as another independent task that is significantly relevant to drug discovery, namely drug-target interaction. The DFL-based model achieved excellent performance in the above-extended validation task, suggesting that the idea of aggregating the heterogeneous biological network and node's (molecule or protein) self-topological features will bring inspiration for broader drug repurposing and discovery research.