Search

Motivation Accumulated clinical studies show that microbes living in humans interact closely with human hosts, and get involved in modulating drug efficacy and drug toxicity. Microbes have become novel targets for the development of antibacterial agents. Therefore, screening of microbe–drug associations can benefit greatly drug research and development. With the increase of microbial genomic and pharmacological datasets, we are greatly motivated to develop an effective computational method to identify new microbe–drug associations. Results In this article, we proposed a novel method, Graph2MDA, to predict microbe–drug associations by using variational graph autoencoder (VGAE). We constructed multi-modal attributed graphs based on multiple features of microbes and drugs, such as molecular structures, microbe genetic sequences and function annotations. Taking as input the multi-modal attribute graphs, VGAE was trained to learn the informative and interpretable latent representations of each node and the whole graph, and then a deep neural network classifier was used to predict microbe–drug associations. The hyperparameter analysis and model ablation studies showed the sensitivity and robustness of our model. We evaluated our method on three independent datasets and the experimental results showed that our proposed method outperformed six existing state-of-the-art methods. We also explored the meaning of the learned latent representations of drugs and found that the drugs show obvious clustering patterns that are significantly consistent with drug ATC classification. Moreover, we conducted case studies on two microbes and two drugs and found 75–95% predicted associations have been reported in PubMed literature. Our extensive performance evaluations validated the effectiveness of our proposed method. Availability and implementation Source codes and preprocessed data are available at https://github.com/moen-hyb/Graph2MDA. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation Accurate and efficient prediction of the molecular property is one of the fundamental problems in drug research and development. Recent advancements in representation learning have been shown to greatly improve the performance of molecular property prediction. However, due to limited labeled data, supervised learning-based molecular representation algorithms can only search limited chemical space and suffer from poor generalizability. Results In this work, we proposed a self-supervised learning method, ATMOL, for molecular representation learning and properties prediction. We developed a novel molecular graph augmentation strategy, referred to as attention-wise graph masking, to generate challenging positive samples for contrastive learning. We adopted the graph attention network as the molecular graph encoder, and leveraged the learned attention weights as masking guidance to generate molecular augmentation graphs. By minimization of the contrastive loss between original graph and augmented graph, our model can capture important molecular structure and higher order semantic information. Extensive experiments showed that our attention-wise graph mask contrastive learning exhibited state-of-the-art performance in a couple of downstream molecular property prediction tasks. We also verified that our model pretrained on larger scale of unlabeled data improved the generalization of learned molecular representation. Moreover, visualization of the attention heatmaps showed meaningful patterns indicative of atoms and atomic groups important to specific molecular property.

INTRODUCTION Thiopurine S-methyltransferase (TPTM) is a well known biomarker for thiopurine-induced leucopenia, which has limited value in Asia. Instead, NUDT15 C415T is a promising predictor in Asia. AIMS To explore whether an optimised strategy based on NUDT15 C415T genotypes affects thiopurine-induced leucopenia, as well as efficacy in Chinese patients with Crohn's disease. METHODS Patients with Crohn's disease and indications for thiopurines were included from two hospitals in China. They were randomly assigned to either the intervention or the control group. In the intervention group, those with genotype CC received a standard dose (control group), those with CT genotype received 50% of the standard dose, those with TT genotype received alternative drugs. The primary endpoint was thiopurine-induced leucopenia (

Background Identifying miRNA and disease associations helps us understand disease mechanisms of action from the molecular level. However, it is usually blind, time-consuming, and small-scale based on biological experiments. Hence, developing computational methods to predict unknown miRNA and disease associations is becoming increasingly important. Results In this work, we develop a computational framework called SMALF to predict unknown miRNA-disease associations. SMALF first utilizes a stacked autoencoder to learn miRNA latent feature and disease latent feature from the original miRNA-disease association matrix. Then, SMALF obtains the feature vector of representing miRNA-disease by integrating miRNA functional similarity, miRNA latent feature, disease semantic similarity, and disease latent feature. Finally, XGBoost is utilized to predict unknown miRNA-disease associations. We implement cross-validation experiments. Compared with other state-of-the-art methods, SAMLF achieved the best AUC value. We also construct three case studies, including hepatocellular carcinoma, colon cancer, and breast cancer. The results show that 10, 10, and 9 out of the top ten predicted miRNAs are verified in MNDR v3.0 or miRCancer, respectively. Conclusion The comprehensive experimental results demonstrate that SMALF is effective in identifying unknown miRNA-disease associations.

In view of the low-frequency noise problem in urban substation, the sound absorption (SA) properties of aluminum silicate fibers (ASF) with different materials, unit weight, plate thickness and cavity thickness were tested in this paper. It was found that the high-purity ASF with larger unit weight, plate thickness and cavity thickness had larger low-frequency SA coefficient, which provided technical support for the development of new low-frequency noise reduction materials for substation.

NUDT15 c.415CT was a novel genetic marker confirmed in our center for thiopurine-induced leukopenia in Chinese inflammatory bowel disease (IBD). For validation, a large cohort study is needed. Meanwhile, the newly discovered NUDT15 coding variants (c.36_37insGGAGTC and c.52 GA) have not been studied in patients with IBD. We aimed to further confirm the influence of 3 NUDT15 variants (c.415CT, c.36_37insGGAGTC, and c.52GA) on thiopurine-induced leukopenia in Chinese patients with IBD.Patients prescribed on thiopurines for at least 2 weeks were recruited from 4 tertiary hospitals. Clinical data were collected. NUDT15 genotypes were determined with polymerase chain reaction-RFLP and sequencing. The interactions between variants and leukopenia were analyzed.A total of 732 patients were included, 177 (24.3%) of whom developed leukopenia. There were strong associations of NUDT15 c.415CT, c.36_37insGGAGTC, and c.52GA with thiopurine-induced leukopenia (P = 1.81 × 10, P = 4.74 × 10 and P = 0.04, respectively), whereas there was no relevance for thiopurine S-methyltransferase genotypes (P = 0.25). The predictive sensitivity of NUDT15 c.415CT was 49.2%, whereas it increased to 55.4% when combined analysis with c.36_37insGGAGTC and c.52GA. Notably, not only the homozygotes with NUDT15 c.415CT but also the heterozygotes both carrying c.415CT and c.52GA developed early leukopenia. The median dosage for NUDT15 c.415CT carriers was significantly lower than that for wild-type (P0.001).We confirmed that NUDT15 c.415CT, c.36_37insGGAGTC, and c.52GA variants were risk factors for thiopurine-induced leukopenia. Combined detection of the 3 variants could increase the predictive sensitivity of thiopurine-induced leukopenia and help to distinguish early leukopenia in heterozygote of c.415CT in Chinese patients with IBD. Treatment monitoring by NUDT15 variants may be promising in individualized therapy.