CancerGATE: Prediction of cancer-driver genes using graph attention autoencoders.

Discovery of the cancer type specific-driver genes is important for understanding the molecular mechanisms of each cancer type and for providing proper treatment. Recently, graph deep learning methods became widely used in finding cancer-driver genes. However, previous methods had limited performance in individual cancer types due to a small number of cancer-driver genes used in training and biases toward the cancer-driver genes used in training the models. Here, we introduce a novel pipeline, CancerGATE that predicts the cancer-driver genes using graph attention autoencoder (GATE) to learn in a self-supervised manner and can be applied to each of the cancer types. CancerGATE utilizes biological network topology and multi-omics data from 15 types of cancer of 20,079 samples from the cancer genome atlas (TCGA). Attention coefficients calculated in the model are used to prioritize cancer-driver genes by comparing coefficients of cancer and normal contexts. CancerGATE shows a higher AUPRC with a difference ranging from 1.5 % to 36.5 % compared to the previous graph deep learning models in each cancer type. We also show that CancerGATE is free from the bias toward cancer-driver genes used in training, revealing mechanisms of the cancer-driver genes in specific cancer types. Finally, we propose novel cancer-driver gene candidates that could be therapeutic targets for specific cancer types.

Designing combinational herbal drugs based on target space analysis.

BACKGROUND: Traditional oriental medicines (TOMs) are a medical practice that follows different philosophies to pharmaceutical drugs and they have been in use for many years in different parts of the world. In this study, by integrating TOM formula and pharmaceutical drugs, we performed target space analysis between TOM formula target space and small-molecule drug target space. To do so, we manually curated 46 TOM formulas that are known to treat Anxiety, Diabetes mellitus, Epilepsy, Hypertension, Obesity, and Schizophrenia. Then, we employed Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET) properties such as human ether-a-go-go related gene (hERG) inhibition, Carcinogenicity, and AMES toxicity to filter out potentially toxic herbal ingredients. The target space analysis was performed between TOM formula and small-molecule drugs: (i) both are known to treat the same disease, and (ii) each known to treat different diseases. Statistical significance of the overlapped target space between the TOM formula and small-molecule drugs was measured using support value. Support value distribution from randomly selected target space was calculated to validate the result. Furthermore, the Si-Wu-Tang (SWT) formula and published literature were also used to evaluate our results. RESULT: This study tried to provide scientific evidence about the effectiveness of the TOM formula to treat the main indication with side effects that could come from the use of small-molecule drugs. The target space analysis between TOM formula and small-molecule drugs in which both are known to treat the same disease shows that many targets overlapped between the two medications with a support value of 0.84 and weighted average support of 0.72 for a TOM formula known to treat Epilepsy. Furthermore, support value distribution from randomly selected target spaces in this analysis showed that the number of overlapped targets is much higher between TOM formula and small-molecule drugs that are known to treat the same disease than in randomly selected target spaces. Moreover, scientific literature was also used to evaluate the medicinal efficacy of individual herbs. CONCLUSION: This study provides an evidence to the effectiveness of a TOM formula to treat the main indication as well as side effects associated with the use of pharmaceutical drugs, as demonstrated through target space analysis.

Community cohesion looseness in gene networks reveals individualized drug targets and resistance.

Community cohesion plays a critical role in the determination of an individual's health in social science. Intriguingly, a community structure of gene networks indicates that the concept of community cohesion could be applied between the genes as well to overcome the limitations of single gene-based biomarkers for precision oncology. Here, we develop community cohesion scores which precisely quantify the community ability to retain the interactions between the genes and their cellular functions in each individualized gene network. Using breast cancer as a proof-of-concept study, we measure the community cohesion score profiles of 950 case samples and predict the individualized therapeutic targets in 2-fold. First, we prioritize them by finding druggable genes present in the community with the most and relatively decreased scores in each individual. Then, we pinpoint more individualized therapeutic targets by discovering the genes which greatly contribute to the community cohesion looseness in each individualized gene network. Compared with the previous approaches, the community cohesion scores show at least four times higher performance in predicting effective individualized chemotherapy targets based on drug sensitivity data. Furthermore, the community cohesion scores successfully discover the known breast cancer subtypes and we suggest new targeted therapy targets for triple negative breast cancer (e.g. KIT and GABRP). Lastly, we demonstrate that the community cohesion scores can predict tamoxifen responses in ER+ breast cancer and suggest potential combination therapies (e.g. NAMPT and RXRA inhibitors) to reduce endocrine therapy resistance based on individualized characteristics. Our method opens new perspectives for the biomarker development in precision oncology.

Combination of UHPLC-MS/MS with context-specific network and cheminformatic approaches for identifying bioactivities and active components of propolis.

Discovering new bioactivities and identifying active compounds of food materials are major fields of study in food science. However, the process commonly requires extensive experiments and can be technically challenging. In the current study, we employed network biology and cheminformatic approaches to predict new target diseases, active components, and related molecular mechanisms of propolis. Applying UHPLC-MS/MS analysis results of propolis to Context-Oriented Directed Associations (CODA) and Combination-Oriented Natural Product Database with Unified Terminology (COCONUT) systems indicated atopic dermatitis as a novel target disease. Experimental validation using cell- and human tissue-based models confirmed the therapeutic potential of propolis against atopic dermatitis. Moreover, we were able to find the major contributing compounds as well as their combinatorial effects responsible for the bioactivity of propolis. The CODA/COCONUT system also provided compound-associated genes explaining the underlying molecular mechanism of propolis. These results highlight the potential use of big data-driven network biological approaches to aid in analyzing the impact of food constituents at a systematic level.

Interpretation of SNP combination effects on schizophrenia etiology based on stepwise deep learning with multi-precision data.

Schizophrenia genome-wide association studies (GWAS) have reported many genomic risk loci, but it is unclear how they affect schizophrenia susceptibility through interactions of multiple SNPs. We propose a stepwise deep learning technique with multi-precision data (SLEM) to explore the SNP combination effects on schizophrenia through intermediate molecular and cellular functions. The SLEM technique utilizes two levels of precision data for learning. It constructs initial backbone networks with more precise but small amount of multilevel assay data. Then, it learns strengths of intermediate interactions with the less precise but massive amount of GWAS data. The learned networks facilitate identifying effective SNP interactions from the intractably large space of all possible SNP combinations. We have shown that the extracted SNP combinations show higher accuracy than any single SNPs and preserve the accuracy in an independent dataset. The learned networks also provide interpretations of molecular and cellular interactions of SNP combinations toward schizophrenia etiology.

Identifying prognostic subgroups of luminal-A breast cancer using deep autoencoders and gene expressions.

Luminal-A breast cancer is the most frequently occurring subtype which is characterized by high expression levels of hormone receptors. However, some luminal-A breast cancer patients suffer from intrinsic and/or acquired resistance to endocrine therapies which are considered as first-line treatments for luminal-A breast cancer. This heterogeneity within luminal-A breast cancer has required a more precise stratification method. Hence, our study aims to identify prognostic subgroups of luminal-A breast cancer. In this study, we discovered two prognostic subgroups of luminal-A breast cancer (BPS-LumA and WPS-LumA) using deep autoencoders and gene expressions. The deep autoencoders were trained using gene expression profiles of 679 luminal-A breast cancer samples in the METABRIC dataset. Then, latent features of each samples generated from the deep autoencoders were used for K-Means clustering to divide the samples into two subgroups, and Kaplan-Meier survival analysis was performed to compare prognosis (recurrence-free survival) between them. As a result, the prognosis between the two subgroups were significantly different (p-value = 5.82E-05; log-rank test). This prognostic difference between two subgroups was validated using gene expression profiles of 415 luminal-A breast cancer samples in the TCGA BRCA dataset (p-value = 0.004; log-rank test). Notably, the latent features were superior to the gene expression profiles and traditional dimensionality reduction method in terms of discovering the prognostic subgroups. Lastly, we discovered that ribosome-related biological functions could be potentially associated with the prognostic difference between them using differentially expressed genes and co-expression network analysis. Our stratification method can be contributed to understanding a complexity of luminal-A breast cancer and providing a personalized medicine.

Reverse tracking from drug-induced transcriptomes through multilayer molecular networks reveals hidden drug targets.

Identifying molecular targets of a drug is an essential process for drug discovery and development. The recent in-silico approaches are usually based on the structure information of chemicals and proteins. However, 3D structure information is hard to obtain and machine-learning methods using 2D structure suffer from data imbalance problem. Here, we present a reverse tracking method from genes to target proteins using drug-perturbed gene transcriptional profiles and multilayer molecular networks. We scored how well the protein explains gene expression changes perturbed by a drug. We validated the protein scores of our method in predicting known targets of drugs. Our method performs better than other methods using the gene transcriptional profiles and shows the ability to suggest the molecular mechanism of drugs. Furthermore, our method has the potential to predict targets for objects that do not have rigid structural information, such as coronavirus.

Large-scale prediction of adverse drug reactions-related proteins with network embedding.

MOTIVATION: Adverse drug reactions (ADRs) are a major issue in drug development and clinical pharmacology. As most ADRs are caused by unintended activity at off-targets of drugs, the identification of drug targets responsible for ADRs becomes a key process for resolving ADRs. Recently, with the increase in the number of ADR-related data sources, several computational methodologies have been proposed to analyze ADR-protein relations. However, the identification of ADR-related proteins on a large scale with high reliability remains an important challenge. RESULTS: In this article, we suggest a computational approach, Large-scale ADR-related Proteins Identification with Network Embedding (LAPINE). LAPINE combines a novel concept called single-target compound with a network embedding technique to enable large-scale prediction of ADR-related proteins for any proteins in the protein-protein interaction network. Analysis of benchmark datasets confirms the need to expand the scope of potential ADR-related proteins to be analyzed, as well as LAPINE's capability for high recovery of known ADR-related proteins. Moreover, LAPINE provides more reliable predictions for ADR-related proteins (Value-added positive predictive value = 0.12), compared to a previously proposed method (P < 0.001). Furthermore, two case studies show that most predictive proteins related to ADRs in LAPINE are supported by literature evidence. Overall, LAPINE can provide reliable insights into the relationship between ADRs and proteomes to understand the mechanism of ADRs leading to their prevention. AVAILABILITY AND IMPLEMENTATION: The source code is available at GitHub (https://github.com/rupinas/LAPINE) and Figshare (https://figshare.com/articles/software/LAPINE/21750245) to facilitate its use. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

In silico activity and ADMET profiling of phytochemicals from Ethiopian indigenous aloes using pharmacophore models.

In silico profiling is used in identification of active compounds and guide rational use of traditional medicines. Previous studies on Ethiopian indigenous aloes focused on documentation of phytochemical compositions and traditional uses. In this study, ADMET and drug-likeness properties of phytochemicals from Ethiopian indigenous aloes were evaluated, and pharmacophore-based profiling was done using Discovery Studio to predict therapeutic targets. The targets were examined using KEGG pathway, gene ontology and network analysis. Using random-walk with restart algorithm, network propagation was performed in CODA network to find diseases associated with the targets. As a result, 82 human targets were predicted and found to be involved in several molecular functions and biological processes. The targets also were linked to various cancers and diseases of immune system, metabolism, neurological system, musculoskeletal system, digestive system, hematologic, infectious, mouth and dental, and congenital disorder of metabolism. 207 KEGG pathways were enriched with the targets, and the main pathways were metabolism of steroid hormone biosynthesis, lipid and atherosclerosis, chemical carcinogenesis, and pathways in cancer. In conclusion, in silico target fishing and network analysis revealed therapeutic activities of the phytochemicals, demonstrating that Ethiopian indigenous aloes exhibit polypharmacology effects on numerous genes and signaling pathways linked to many diseases.

Highly Adsorptive Au-TiO2 Nanocomposites for the SERS Face Mask Allow the Machine-Learning-Based Quantitative Assay of SARS-CoV-2 in Artificial Breath Aerosols.

Human respiratory aerosols contain diverse potential biomarkers for early disease diagnosis. Here, we report the direct and label-free detection of SARS-CoV-2 in respiratory aerosols using a highly adsorptive Au-TiO2 nanocomposite SERS face mask and an ablation-assisted autoencoder. The Au-TiO2 SERS face mask continuously preconcentrates and efficiently captures the oronasal aerosols, which substantially enhances the SERS signal intensities by 47% compared to simple Au nanoislands. The ultrasensitive Au-TiO2 nanocomposites also demonstrate the successful detection of SARS-CoV-2 spike proteins in artificial respiratory aerosols at a 100 pM concentration level. The deep learning-based autoencoder, followed by the partial ablation of nondiscriminant SERS features of spike proteins, allows a quantitative assay of the 101-104 pfu/mL SARS-CoV-2 lysates (comparable to 19-29 PCR cyclic threshold from COVID-19 patients) in aerosols with an accuracy of over 98%. The Au-TiO2 SERS face mask provides a platform for breath biopsy for the detection of various biomarkers in respiratory aerosols.

Combining empirical knowledge, in silico molecular docking and ADMET profiling to identify therapeutic phytochemicals from Brucea antidysentrica for acute myeloid leukemia.

Acute myeloid leukemia (AML) is one of the deadly cancers. Chemotherapy is the first-line treatment and the only curative intervention is stem cell transplantation which are intolerable for aged and comorbid patients. Therefore, finding complementary treatment is still an active research area. For this, empirical knowledge driven search for therapeutic agents have been carried out by long and arduous wet lab processes. Nonetheless, currently there is an accumulated bioinformatics data about natural products that enabled the use of efficient and cost effective in silico methods to find drug candidates. In this work, therefore, we set out to computationally investigate the phytochemicals from Brucea antidysentrica to identify therapeutic phytochemicals for AML. We performed in silico molecular docking of compounds against AML receptors IDH2, MCL1, FLT3 and BCL2. Phytochemicals were docked to AML receptors at the same site where small molecule drugs were bound and their binding affinities were examined. In addition, random compounds from PubChem were docked with AML targets and their docking score was compared with that of phytochemicals using statistical analysis. Then, non-covalent interactions between phytochemicals and receptors were identified and visualized using discovery studio and Protein-Ligand Interaction Profiler web tool (PLIP). From the statistical analysis, most of the phytochemicals exhibited significantly lower (p-value ≤ 0.05) binding energies compared with random compounds. Using cutoff binding energy of less than or equal to one standard deviation from the mean of the phytochemicals' binding energies for each receptor, 12 phytochemicals showed considerable binding affinity. Especially, hydnocarpin (-8.9 kcal/mol) and yadanzioside P (-9.4 kcal/mol) exhibited lower binding energy than approved drugs AMG176 (-8.6 kcal/mol) and gilteritinib (-9.1 kcal/mol) to receptors MCL1 and FLT3 respectively, indicating their potential to be lead molecules. In addition, most of the phytochemicals possessed acceptable drug-likeness and absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. Based on the binding affinities as exhibited by the molecular docking studies supported by the statistical analysis, 12 phytochemicals from Brucea antidysentrica (1,11-dimethoxycanthin-6-one, 1-methoxycanthin-6-one, 2-methoxycanthin-6-one, beta-carboline-1-propionic acid, bruceanol A, bruceanol D, bruceanol F, bruceantarin, bruceantin, canthin-6-one, hydnocarpin, and yadanzioside P) can be considered as candidate compounds to prevent and manage AML. However, the phytochemicals should be further studied using in vivo & in vitro experiments on AML models. Therefore, this study concludes that combination of empirical knowledge, in silico molecular docking and ADMET profiling is useful to find natural product-based drug candidates. This technique can be applied to other natural products with known empirical efficacy.

Computational Discovery of Cancer Immunotherapy Targets by Intercellular CRISPR Screens.

Cancer immunotherapy targets the interplay between immune and cancer cells. In particular, interactions between cytotoxic T lymphocytes (CTLs) and cancer cells, such as PD-1 (PDCD1) binding PD-L1 (CD274), are crucial for cancer cell clearance. However, immune checkpoint inhibitors targeting these interactions are effective only in a subset of patients, requiring the identification of novel immunotherapy targets. Genome-wide clustered regularly interspaced short palindromic repeats (CRISPR) screening in either cancer or immune cells has been employed to discover regulators of immune cell function. However, CRISPR screens in a single cell type complicate the identification of essential intercellular interactions. Further, pooled screening is associated with high noise levels. Herein, we propose intercellular CRISPR screens, a computational approach for the analysis of genome-wide CRISPR screens in every interacting cell type for the discovery of intercellular interactions as immunotherapeutic targets. We used two publicly available genome-wide CRISPR screening datasets obtained while triple-negative breast cancer (TNBC) cells and CTLs were interacting. We analyzed 4825 interactions between 1391 ligands and receptors on TNBC cells and CTLs to evaluate their effects on CTL function. Intercellular CRISPR screens discovered targets of approved drugs, a few of which were not identifiable in single datasets. To evaluate the method's performance, we used data for cytokines and costimulatory molecules as they constitute the majority of immunotherapeutic targets. Combining both CRISPR datasets improved the recall of discovering these genes relative to using single CRISPR datasets over two-fold. Our results indicate that intercellular CRISPR screens can suggest novel immunotherapy targets that are not obtained through individual CRISPR screens. The pipeline can be extended to other cancer and immune cell types to discover important intercellular interactions as potential immunotherapeutic targets.

Plant phenotype relationship corpus for biomedical relationships between plants and phenotypes.

Medicinal plants have demonstrated therapeutic potential for applicability for a wide range of observable characteristics in the human body, known as "phenotype," and have been considered favorably in clinical treatment. With an ever increasing interest in plants, many researchers have attempted to extract meaningful information by identifying relationships between plants and phenotypes from the existing literature. Although natural language processing (NLP) aims to extract useful information from unstructured textual data, there is no appropriate corpus available to train and evaluate the NLP model for plants and phenotypes. Therefore, in the present study, we have presented the plant-phenotype relationship (PPR) corpus, a high-quality resource that supports the development of various NLP fields; it includes information derived from 600 PubMed abstracts corresponding to 5,668 plant and 11,282 phenotype entities, and demonstrates a total of 9,709 relationships. We have also described benchmark results through named entity recognition and relation extraction systems to verify the quality of our data and to show the significant performance of NLP tasks in the PPR test set.

Predicting Ischemic Stroke in Patients with Atrial Fibrillation Using Machine Learning.

BACKGROUND: Atrial fibrillation (AF) is a well-known risk factor for stroke. Predicting the risk is important to prevent the first and secondary attacks of cerebrovascular diseases by determining early treatment. This study aimed to predict the ischemic stroke in AF patients based on the massive and complex Korean National Health Insurance (KNHIS) data through a machine learning approach. METHODS: We extracted 65-dimensional features, including demographics, health examination, and medical history information, of 754,949 patients with AF from KNHIS. Logistic regression was used to determine whether the extracted features had a statistically significant association with ischemic stroke occurrence. Then, we constructed the ischemic stroke prediction model using an attention-based deep neural network. The extracted features were used as input, and the occurrence of ischemic stroke after the diagnosis of AF was the output used to train the model. RESULTS: We found 48 features significantly associated with ischemic stroke occurrence through regression analysis (p-value < 0.001). When the proposed deep learning model was applied to 150,989 AF patients, it was confirmed that the occurrence ischemic stroke was predicted to be higher AUROC (AUROC = 0.727 ± 0.003) compared to CHA2DS2-VASc score (AUROC = 0.651 ± 0.007) and other machine learning methods. CONCLUSIONS: As part of preventive medicine, this study could help AF patients prepare for ischemic stroke prevention based on predicted stoke associated features and risk scores.

Paeonia lactiflora extract improves the muscle function of mdx mice, an animal model of Duchenne muscular dystrophy, via downregulating the high mobility group box 1 protein.

ETHNOPHARMACOLOGICAL RELEVANCE: Paeonia lactiflora Pall. is an ethnopharmacological medicine with a long history of human use for treating various inflammatory diseases in many Asian countries. AIM OF THE STUDY: Duchenne muscular dystrophy (DMD) is an X-linked degenerative muscle disease affecting 1 in 3500 males and is characterized by severe muscle inflammation and a progressive decline in muscle function. This study aimed to elucidate the effects of an ethanol extract of the root of Paeonia lactiflora Pall. (PL) on the muscle function in the muscular dystrophy X-linked (mdx) mouse, the most commonly used animal model of DMD. MATERIALS AND METHODS: Male mdx mice and wild-type controls aged 5 weeks were orally treated with PL for 4 weeks. The corticosteroid prednisolone was used as a comparator drug. Muscle strength and motor coordination were assessed via the grip-strength and rotarod tests, respectively. Muscle damage was evaluated via histological examination and assessment of plasma creatine-kinase activity. Proteomic analyses were conducted to identify the muscle proteins whose levels were significantly affected by PL (ProteomeXchange identifier: PXD028886). Muscle and plasma levels of these proteins, and their corresponding mRNAs were measured using western blotting and ELISA, and quantitative reverse transcription-polymerase chain reaction, respectively. RESULTS: The muscle strength and motor coordination of mdx mice were significantly increased by the oral treatment of PL. PL significantly reduced the histological muscle damage and plasma creatine-kinase activity. Proteomic analyses of the muscle showed that PL significantly downregulated the high mobility group box 1 (HMGB1) protein and Toll-like receptor (TLR) 4, thus suppressing the HMGB1-TLR4-NF-κB signaling, in the muscle of mdx mice. Consequently, the muscle levels of proinflammatory cytokines/chemokines, which play crucial roles in inflammation, were downregulated. CONCLUSION: PL improves the muscle function and reduces the muscle damage in mdx mice via suppressing the HMGB1-TLR4-NF-κB signaling and downregulating proinflammatory cytokines/chemokines.

Context-aware multi-token concept recognition of biological entities.

BACKGROUND: Concept recognition is a term that corresponds to the two sequential steps of named entity recognition and named entity normalization, and plays an essential role in the field of bioinformatics. However, the conventional dictionary-based methods did not sufficiently addressed the variation of the concepts in actual use in literature, resulting in the particularly degraded performances in recognition of multi-token concepts. RESULTS: In this paper, we propose a concept recognition method of multi-token biological entities using neural models combined with literature contexts. The key aspect of our method is utilizing the contextual information from the biological knowledge-bases for concept normalization, which is followed by named entity recognition procedure. The model showed improved performances over conventional methods, particularly for multi-token concepts with higher variations. CONCLUSIONS: We expect that our model can be utilized for effective concept recognition and variety of natural language processing tasks on bioinformatics.

EGR1/GADD45α Activation by ROS of Non-Thermal Plasma Mediates Cell Death in Thyroid Carcinoma.

(1) Background: Nonthermal plasma (NTP) induces cell death in various types of cancer cells, providing a promising alternative treatment strategy. Although recent studies have identified new mechanisms of NTP in several cancers, the molecular mechanisms underlying its therapeutic effect on thyroid cancer (THCA) have not been elucidated. (2) Methods: To investigate the mechanism of NTP-induced cell death, THCA cell lines were treated with NTP-activated medium -(NTPAM), and gene expression profiles were evaluated using RNA sequencing. (3) Results: NTPAM upregulated the gene expression of early growth response 1 (EGR1). NTPAM-induced THCA cell death was enhanced by EGR1 overexpression, whereas EGR1 small interfering RNA had the opposite effect. NTPAM-derived reactive oxygen species (ROS) affected EGR1 expression and apoptotic cell death in THCA. NTPAM also induced the gene expression of growth arrest and regulation of DNA damage-inducible 45α (GADD45A) gene, and EGR1 regulated GADD45A through direct binding to its promoter. In xenograft in vivo tumor models, NTPAM inhibited tumor progression of THCA by increasing EGR1 levels. (4) Conclusions: Our findings suggest that NTPAM induces apoptotic cell death in THCA through a novel mechanism by which NTPAM-induced ROS activates EGR1/GADD45α signaling. Furthermore, our data provide evidence that the regulation of the EGR1/GADD45α axis can be a novel strategy for the treatment of THCA.

Paeonia lactiflora extract suppresses cisplatin-induced muscle wasting via downregulation of muscle-specific ubiquitin E3 ligases, NF-κB signaling, and cytokine levels.

ETHNOPHARMACOLOGICAL RELEVANCE: The dried root of Paeonia lactiflora Pall. (Radix Paeoniae) has been traditionally used to treat various inflammatory diseases in many Asian countries. AIM OF THE STUDY: Cisplatin is a broad-spectrum anticancer drug used in diverse types of cancer. However, muscle wasting is a common side effect of cisplatin chemotherapy. This study aimed to elucidate the effects of an ethanol extract of the root of Paeonia lactiflora Pall. (Radix Paeoniae, RP) on cisplatin-induced muscle wasting along with its molecular mechanism. MATERIAL AND METHODS: C57BL/6 mice were intraperitoneally injected with cisplatin and orally treated with RP. Megestrol acetate was used as a comparator drug. Skeletal muscle mass was measured as the weight of gastrocnemius and quadriceps muscles, and skeletal muscle function was measured by treadmill running time and grip strength. Skeletal muscle tissues were analyzed by RNAseq, western blotting, ELISA, and immunofluorescence microscopy. RESULTS: In mice treated with cisplatin, skeletal muscle mass and skeletal muscle function were significantly reduced. However, oral administration of RP significantly restored skeletal muscle mass and function in the cisplatin-treated mice. In the skeletal muscle tissues of the cisplatin-treated mice, RP downregulated NF-κB signaling and cytokine levels. RP also downregulated muscle-specific ubiquitin E3 ligases, resulting in the restoration of myosin heavy chain (MyHC) and myoblast determination protein (MyoD), which play crucial roles in muscle contraction and muscle differentiation, respectively. CONCLUSION: RP restored skeletal muscle function and mass in cisplatin-treated mice by restoring the muscle levels of MyHC and MyoD proteins via downregulation of muscle-specific ubiquitin E3 ligases as well as muscle NF-κB signaling and cytokine levels.

Literature mining for context-specific molecular relations using multimodal representations (COMMODAR).

Biological contextual information helps understand various phenomena occurring in the biological systems consisting of complex molecular relations. The construction of context-specific relational resources vastly relies on laborious manual extraction from unstructured literature. In this paper, we propose COMMODAR, a machine learning-based literature mining framework for context-specific molecular relations using multimodal representations. The main idea of COMMODAR is the feature augmentation by the cooperation of multimodal representations for relation extraction. We leveraged biomedical domain knowledge as well as canonical linguistic information for more comprehensive representations of textual sources. The models based on multiple modalities outperformed those solely based on the linguistic modality. We applied COMMODAR to the 14 million PubMed abstracts and extracted 9214 context-specific molecular relations. All corpora, extracted data, evaluation results, and the implementation code are downloadable at https://github.com/jae-hyun-lee/commodar . CCS CONCEPTS: • Computing methodologies~Information extraction • Computing methodologies~Neural networks • Applied computing~Biological networks.

Compositional and functional differences of the mucosal microbiota along the intestine of healthy individuals.

Gut mucosal microbes evolved closest to the host, developing specialized local communities. There is, however, insufficient knowledge of these communities as most studies have employed sequencing technologies to investigate faecal microbiota only. This work used shotgun metagenomics of mucosal biopsies to explore the microbial communities' compositions of terminal ileum and large intestine in 5 healthy individuals. Functional annotations and genome-scale metabolic modelling of selected species were then employed to identify local functional enrichments. While faecal metagenomics provided a good approximation of the average gut mucosal microbiome composition, mucosal biopsies allowed detecting the subtle variations of local microbial communities. Given their significant enrichment in the mucosal microbiota, we highlight the roles of Bacteroides species and describe the antimicrobial resistance biogeography along the intestine. We also detail which species, at which locations, are involved with the tryptophan/indole pathway, whose malfunctioning has been linked to pathologies including inflammatory bowel disease. Our study thus provides invaluable resources for investigating mechanisms connecting gut microbiota and host pathophysiology.