Developing a Personalized Meal Recommendation System for Chinese Older Adults: Observational Cohort Study.

BACKGROUND: China's older population is facing serious health challenges, including malnutrition and multiple chronic conditions. There is a critical need for tailored food recommendation systems. Knowledge graph-based food recommendations offer considerable promise in delivering personalized nutritional support. However, the integration of disease-based nutritional principles and preference-related requirements needs to be optimized in current recommendation processes. OBJECTIVE: This study aims to develop a knowledge graph-based personalized meal recommendation system for community-dwelling older adults and to conduct preliminary effectiveness testing. METHODS: We developed ElCombo, a personalized meal recommendation system driven by user profiles and food knowledge graphs. User profiles were established from a survey of 96 community-dwelling older adults. Food knowledge graphs were supported by data from websites of Chinese cuisine recipes and eating history, consisting of 5 entity classes: dishes, ingredients, category of ingredients, nutrients, and diseases, along with their attributes and interrelations. A personalized meal recommendation algorithm was then developed to synthesize this information to generate packaged meals as outputs, considering disease-related nutritional constraints and personal dietary preferences. Furthermore, a validation study using a real-world data set collected from 96 community-dwelling older adults was conducted to assess ElCombo's effectiveness in modifying their dietary habits over a 1-month intervention, using simulated data for impact analysis. RESULTS: Our recommendation system, ElCombo, was evaluated by comparing the dietary diversity and diet quality of its recommended meals with those of the autonomous choices of 96 eligible community-dwelling older adults. Participants were grouped based on whether they had a recorded eating history, with 34 (35%) having and 62 (65%) lacking such data. Simulation experiments based on retrospective data over a 30-day evaluation revealed that ElCombo's meal recommendations consistently had significantly higher diet quality and dietary diversity compared to the older adults' own selections (P<.001). In addition, case studies of 2 older adults, 1 with and 1 without prior eating records, showcased ElCombo's ability to fulfill complex nutritional requirements associated with multiple morbidities, personalized to each individual's health profile and dietary requirements. CONCLUSIONS: ElCombo has shown enhanced potential for improving dietary quality and diversity among community-dwelling older adults in simulation tests. The evaluation metrics suggest that the food choices supported by the personalized meal recommendation system surpass autonomous selections. Future research will focus on validating and refining ElCombo's performance in real-world settings, emphasizing the robust management of complex health data. The system's scalability and adaptability pinpoint its potential for making a meaningful impact on the nutritional health of older adults.

[Development and Application of Ontology of Cancer Hallmarks].

Objective To develop a traceable cancer hallmark ontology with terminology including gene mutation,cancer hallmark,and cell line for knowledge integration,standardization,correlation,and discovery.Methods The Ontology Development 101 and the current ontology development methods were employed to determine the content coverage,structural layers,reusable terms,and new terms of the cancer hallmark ontology.Taking colorectal cancer as a study case,we extracted the knowledge related with colorectal cancer hallmarks using text mining and text classification technology from PubMed,and then formalized the extracted knowledge into the cancer hallmark ontology.Moreover,we made use of existing cancer hallmark evidence in Catalogue of Somatic Mutations in Cancer and further semantic retrieval to discover new knowledge.Results The established cancer hallmark ontology comprised 9910 classes and 6138 instances,which realized the semantic representation of 2310 article abstracts about colorectal cancer and 26 pieces of evidence about genes and their cancer hallmarks.Compared with the Catalogue of Somatic Mutations in Cancer,new evidence for more genes associated with colorectal cancer hallmarks was found based on cancer hallmark ontology.Conclusion This study is of great significance to the research on the cancer pathogenesis at the molecular level,the revealing of specific roles of genes and mutations in the occurrence of cancer,and the rapid knowledge discovery of cancer hallmarks.

Employing Molecular Conformations for Ligand-Based Virtual Screening with Equivariant Graph Neural Network and Deep Multiple Instance Learning.

Ligand-based virtual screening (LBVS) is a promising approach for rapid and low-cost screening of potentially bioactive molecules in the early stage of drug discovery. Compared with traditional similarity-based machine learning methods, deep learning frameworks for LBVS can more effectively extract high-order molecule structure representations from molecular fingerprints or structures. However, the 3D conformation of a molecule largely influences its bioactivity and physical properties, and has rarely been considered in previous deep learning-based LBVS methods. Moreover, the relative bioactivity benchmark dataset is still lacking. To address these issues, we introduce a novel end-to-end deep learning architecture trained from molecular conformers for LBVS. We first extracted molecule conformers from multiple public molecular bioactivity data and consolidated them into a large-scale bioactivity benchmark dataset, which totally includes millions of endpoints and molecules corresponding to 954 targets. Then, we devised a deep learning-based LBVS called EquiVS to learn molecule representations from conformers for bioactivity prediction. Specifically, graph convolutional network (GCN) and equivariant graph neural network (EGNN) are sequentially stacked to learn high-order molecule-level and conformer-level representations, followed with attention-based deep multiple-instance learning (MIL) to aggregate these representations and then predict the potential bioactivity for the query molecule on a given target. We conducted various experiments to validate the data quality of our benchmark dataset, and confirmed EquiVS achieved better performance compared with 10 traditional machine learning or deep learning-based LBVS methods. Further ablation studies demonstrate the significant contribution of molecular conformation for bioactivity prediction, as well as the reasonability and non-redundancy of deep learning architecture in EquiVS. Finally, a model interpretation case study on CDK2 shows the potential of EquiVS in optimal conformer discovery. The overall study shows that our proposed benchmark dataset and EquiVS method have promising prospects in virtual screening applications.

Drug-disease association prediction with literature based multi-feature fusion.

Introduction: Exploring the potential efficacy of a drug is a valid approach for drug development with shorter development times and lower costs. Recently, several computational drug repositioning methods have been introduced to learn multi-features for potential association prediction. However, fully leveraging the vast amount of information in the scientific literature to enhance drug-disease association prediction is a great challenge. Methods: We constructed a drug-disease association prediction method called Literature Based Multi-Feature Fusion (LBMFF), which effectively integrated known drugs, diseases, side effects and target associations from public databases as well as literature semantic features. Specifically, a pre-training and fine-tuning BERT model was introduced to extract literature semantic information for similarity assessment. Then, we revealed drug and disease embeddings from the constructed fusion similarity matrix by a graph convolutional network with an attention mechanism. Results: LBMFF achieved superior performance in drug-disease association prediction with an AUC value of 0.8818 and an AUPR value of 0.5916. Discussion: LBMFF achieved relative improvements of 31.67% and 16.09%, respectively, over the second-best results, compared to single feature methods and seven existing state-of-the-art prediction methods on the same test datasets. Meanwhile, case studies have verified that LBMFF can discover new associations to accelerate drug development. The proposed benchmark dataset and source code are available at: https://github.com/kang-hongyu/LBMFF.

TWAS Atlas: a curated knowledgebase of transcriptome-wide association studies.

Transcriptome-wide association studies (TWASs), as a practical and prevalent approach for detecting the associations between genetically regulated genes and traits, are now leading to a better understanding of the complex mechanisms of genetic variants in regulating various diseases and traits. Despite the ever-increasing TWAS outputs, there is still a lack of databases curating massive public TWAS information and knowledge. To fill this gap, here we present TWAS Atlas (https://ngdc.cncb.ac.cn/twas/), an integrated knowledgebase of TWAS findings manually curated from extensive literature. In the current implementation, TWAS Atlas collects 401,266 high-quality human gene-trait associations from 200 publications, covering 22,247 genes and 257 traits across 135 tissue types. In particular, an interactive knowledge graph of the collected gene-trait associations is constructed together with single nucleotide polymorphism (SNP)-gene associations to build up comprehensive regulatory networks at multi-omics levels. In addition, TWAS Atlas, as a user-friendly web interface, efficiently enables users to browse, search and download all association information, relevant research metadata and annotation information of interest. Taken together, TWAS Atlas is of great value for promoting the utility and availability of TWAS results in explaining the complex genetic basis as well as providing new insights for human health and disease research.

Prediction and risk assessment of sepsis-associated encephalopathy in ICU based on interpretable machine learning.

Sepsis-associated encephalopathy (SAE) is a major complication of sepsis and is associated with high mortality and poor long-term prognosis. The purpose of this study is to develop interpretable machine learning models to predict the occurrence of SAE after ICU admission and implement the individual prediction and analysis. Patients with sepsis admitted to ICU were included. SAE was diagnosed as glasgow coma score (GCS) less than 15. Statistical analysis at baseline was performed between SAE and non-SAE. Six machine learning classifiers were employed to predict the occurrence of SAE, and the adjustment of model super parameters was performed by using Bayesian optimization method. Finally, the optimal algorithm was selected according to the prediction efficiency. In addition, professional physicians were invited to evaluate our model prediction results for further quantitative assessment of the model interpretability. The preliminary analysis of variance showed significant differences in the incidence of SAE among patients with pathogen infection. There were significant differences in physical indicators like respiratory rate, temperature, SpO2 and mean arterial pressure (P < 0.001). In addition, the laboratory results were also significantly different. The optimal classification model (XGBoost) indicated that the best risk factors (cut-off points) were creatinine (1.1 mg/dl), mean respiratory rate (18), pH (7.38), age (72), chlorine (101 mmol/L), sodium (138.5 k/ul), SAPSII score (23), platelet count (160), and phosphorus (2.4 and 5.0 mg/dL). The ranked features derived from the best model (AUC is 0.8837) were mechanical ventilation, duration of mechanical ventilation, phosphorus, SOFA score, and vasopressin usage. The SAE risk prediction model based on XGBoost created here can make very accurate predictions using simple indicators and support the visual explanation. The interpretable model was effectively evaluated by professional physicians and can help them predict the occurrence of SAE more intuitively.

In-Situ Sludge Reduction Performance and Mechanism in Sulfidogenic Anoxic-Oxic-Anoxic Membrane Bioreactors.

The excess sludge generated from the activated sludge process remains a big issue. Sustainable approaches that achieve in situ sludge reduction with satisfactory effluent quality deserve attention. This study explored the sludge reduction performance of sulfidogenic anoxic-oxic-anoxic (AOA) membrane bioreactors. The dynamics of the microbial community and metabolic pathways were further analyzed to elucidate the internal mechanism of sludge reduction. Compared with the conventional anoxic-oxic-oxic membrane bioreactor (MBRcontrol), AOAS150 (150 mg/L SO42- in the membrane tank) and AOAS300 (300 mg/L SO42- in the membrane tank) reduced biomass production by 40.39% and 47.45%, respectively. The sulfide reduced from sulfate could enhance the sludge decay rate and decrease sludge production. Extracellular polymeric substances (EPSs) destruction and aerobic lysis contributed to sludge reduction in AOA bioreactors. The relative abundance of Bacteroidetes (phylum), sulfate-reducing bacteria (SRB, genus), and Ignavibacterium (genus) increased in AOA bioreactors compared with MBRcontrol. Our metagenomic analysis indicated that the total enzyme-encoding genes involved in glycolysis, denitrification, and sulfate-reduction processes decreased over time in AOAS300 and were lower in AOAS300 than AOAS150 at the final stage of operation. The excess accumulation of sulfide in AOAS300 may inactive the functional bacteria, and sulfide inhibition induced sludge reduction.

In-Situ Sludge Reduction in Membrane-Controlled Anoxic-Oxic-Anoxic Bioreactor: Performance and Mechanism.

Conventional and advanced biological wastewater treatment systems generate excess sludge, which causes socio-economic and environmental issues. This study investigated the performance of membrane-controlled anoxic-oxic-anoxic (AOA) bioreactors for in-situ sludge reduction compared to the conventional anoxic-oxic-oxic membrane bioreactor (MBRcontrol). The membrane units in the AOA bioreactors were operated as anoxic reactors at lower sludge recirculation rates to achieve hydrolysis of extracellular polymeric substances (EPS) and extensive endogenous respiration. Compared to MBRcontrol, the AOA bioreactors operated with 90%, and 80% recirculation rates reduced the sludge growth up to 19% and 30%, respectively. Protein-like components were enriched in AOA bioreactors while fulvic-like components were dominant in MBRcontrol. The growth of Dechloromonas and Zoogloea genra was promoted in AOA bioreactors and thus sludge reduction was facilitated. Metagenomics analysis uncovered that AOA bioreactors exhibited higher proportions of key genes encoding enzymes involved in the glycolysis and denitrification processes, which contributed to the utilization of carbon sources and nitrogen consumption and thus sludge reduction.

Gravity-driven layered double hydroxide nanosheet membrane activated peroxymonosulfate system for micropollutant degradation.

For the first time in this study, CoAl-layered double hydroxide nanosheet membrane (LDHm) with abundant active sites was fabricated for peroxymonosulfate (PMS) activation with the mindset to catalytically degrade micropollutants. Depending on the catalyst loading, the developed LDHm can be driven under gravity at a permeate flux of approximately 80 L/m2 h and 210 L/m2 h at LDH loading of 0.80 mg/cm2 and 0.08 mg/cm2, respectively. Notably, the LDHm (0.63 mg) exhibited excellent PMS activation efficiency as indicated by 87.8% removal of the probe chemical (ranitidine) at 0.2 mM PMS, which was higher than that (37-44%) achieved by conventional LDH (5-20 mg)/PMS (0.2 mM) system. In addition to efficient degradation of several micropollutants, LDHm/PMS performance was not inhibited by variation in solution pH (4-8) as well as during long-term (29 h) continuous-flow operation. SO4•- and 1O2 were identified as the primary reactive species in the LDHm/PMS system, while both Co and Al participated in PMS activation. This study offers a simple strategy for efficient removal of several micropollutants with significantly reduced catalyst leaching, which could be applied sustainably in water treatment.

Building a Pharmacogenomics Knowledge Model Toward Precision Medicine: Case Study in Melanoma.

BACKGROUND: Many drugs do not work the same way for everyone owing to distinctions in their genes. Pharmacogenomics (PGx) aims to understand how genetic variants influence drug efficacy and toxicity. It is often considered one of the most actionable areas of the personalized medicine paradigm. However, little prior work has included in-depth explorations and descriptions of drug usage, dosage adjustment, and so on. OBJECTIVE: We present a pharmacogenomics knowledge model to discover the hidden relationships between PGx entities such as drugs, genes, and diseases, especially details in precise medication. METHODS: PGx open data such as DrugBank and RxNorm were integrated in this study, as well as drug labels published by the US Food and Drug Administration. We annotated 190 drug labels manually for entities and relationships. Based on the annotation results, we trained 3 different natural language processing models to complete entity recognition. Finally, the pharmacogenomics knowledge model was described in detail. RESULTS: In entity recognition tasks, the Bidirectional Encoder Representations from Transformers-conditional random field model achieved better performance with micro-F1 score of 85.12%. The pharmacogenomics knowledge model in our study included 5 semantic types: drug, gene, disease, precise medication (population, daily dose, dose form, frequency, etc), and adverse reaction. Meanwhile, 26 semantic relationships were defined in detail. Taking melanoma caused by a BRAF gene mutation into consideration, the pharmacogenomics knowledge model covered 7 related drugs and 4846 triples were established in this case. All the corpora, relationship definitions, and triples were made publically available. CONCLUSIONS: We highlighted the pharmacogenomics knowledge model as a scalable framework for clinicians and clinical pharmacists to adjust drug dosage according to patient-specific genetic variation, and for pharmaceutical researchers to develop new drugs. In the future, a series of other antitumor drugs and automatic relation extractions will be taken into consideration to further enhance our framework with more PGx linked data.

Mining and standardizing chinese consumer health terms.

BACKGROUND: Health professionals and consumers use different terms to express medical events or concerns, which makes the communication barriers between the professionals and consumers. This may lead to bias in the diagnosis or treatment due to the misunderstanding or incomplete understanding. To solve the issue, a consumer health vocabulary was developed to map the consumer-used health terms to professional-used medical terms. METHODS: In this study, we extracted Chinese consumer health terms from both online health forum and patient education monographs, and manually mapped them to medical terms used by professionals (terms in medical thesauri or in medical books). To ensure the above annotation quality, we developed annotation guidelines. RESULTS: We applied our method to extract consumer-used disease terms in endocrinology, cardiology, gastroenterology and dermatology. In this study, we identified 1349 medical mentions from 8436 questions posted in an online health forum and 1428 articles for patient education monographs. After manual annotation and review, we released 1036 Chinese consumer health terms with mapping to 480 medical terms. Four annotators worked on the manual annotation work following the Chinese consumer health term annotation guidelines. Their average inter-annotator agreement (IAA) score was 93.91% ensuring high consistency of the released terms. CONCLUSIONS: We extracted Chinese consumer health terms from online forum and patient education monographs, and mapped them to medical terms used by professionals. Manual annotation efforts have been made for term annotating and mapping. Our study may contribute to the Chinese consumer health vocabulary construction. In addition, our annotated corpus, both the contexts of consumer health terms and consumer-professional term mapping, would be a useful resource for automatic methodology development. The dataset of the Chinese consumer health terms (CHT) is publicly available at http://www.phoc.org.cn/cht/ .

Mining association rules between stroke risk factors based on the Apriori algorithm.

BACKGROUND: Stroke is a frequently-occurring disease and is a severe threat to human health. OBJECTIVE: We aimed to explore the associations between stroke risk factors. METHODS: Subjects who were aged 40 or above were requested to do surveys with a unified questionnaire as well as laboratory examinations. The Apriori algorithm was applied to find out the meaningful association rules. Selected association rules were divided into 8 groups by the number of former items. The rules with higher confidence degree in every group were viewed as the meaningful rules. RESULTS: The training set used in association analysis consists of a total of 985,325 samples, with 15,835 stroke patients (1.65%) and 941,490 without stroke (98.35%). Based on the threshold we set for the Apriori algorithm, eight meaningful association rules were obtained between stroke and its high risk factors. While between high risk factors, there are 25 meaningful association rules. CONCLUSIONS: Based on the Apriori algorithm, meaningful association rules between the high risk factors of stroke were found, proving a feasible way to reduce the risk of stroke with early intervention.

Facilitating Full-text Access to Biomedical Literature Using Open Access Resources.

Open access (OA) resources and local libraries often have their own literature databases, especially in the field of biomedicine. We have developed a method of linking a local library to a biomedical OA resource facilitating researchers' full-text article access. The method uses a model based on vector space to measure similarities between two articles in local library and OA resources. The method achieved an F-score of 99.61%. This method of article linkage and mapping between local library and OA resources is available for use. Through this work, we have improved the full-text access of the biomedical OA resources.

[Inhibitory effect of chondroitinase ABC on ephrin A4 expression after spinal cord injury in rats].

The aim of the study was to investigate the effect of chondroitinase ABC (ChABC) on ephrin A4 (EphA4) expression after spinal cord impairment (SCI) in rats. Adult female SD rats were randomly divided into three groups: ChABC group, normal saline (NS) group and sham group. In the ChABC and NS group, the SCI model was produced by the spinal cord hemisection. The rats in sham group received sham operation without the spinal hemisection. ChABC and NS groups were intrathecally injected with ChABC and normal saline, respectively. At different time points after SCI, injured region of spinal cord was taken out as sample. The levels of EphA4 expression were measured by immunofluorescence technique and Western blot. And the expressions of growth associated protein 43 (GAP-43) and glial fibrillary acidic protein (GFAP) were detected using double immunofluorescent staining. Immunofluorescent results showed that, compared with that in sham group, the EphA4 expression was significantly down-regulated on 1, 3 and 7 d after SCI, then up-regulated on 14 and 21 d after SCI in NS group. In ChABC group, the level of EphA4 expression was significantly less than that in the NS group during the whole time after SCI. Western blot showed an identical result to that of immunofluorescent staining. The double labeling results showed that on 3 d after SCI, the number of GFAP, glial cells marker, positive cells in NS group was lower than that in sham group, but higher than that in ChABC group. Moreover, GAP-43 was not detected in all three groups. These results suggest that ChABC can decrease the expression level of EphA4 and reduce the number of astrocytes after SCI, thus improving microenvironment of the injured region and promoting axonal growth and extension.

[Rotavirus surveillance data from Kunming Children's Hospital, 1998 - 2001].

OBJECTIVE: To study the epidemiological status on rotavirus diarrhea in Kunming to improve the rotavirus vaccine immunization program. METHODS: A hospital-based sentinel surveillance program for rotavirus was set up among children less than 5 years old with acute diarrhea in Kunming Children's Hospital. Clinical information and fecal specimens were collected and rotavirus were detected by polyacrylamide gel electrophoresis (PAGE) and/or enzyme linked immunosorbent assay (ELISA). Positive specimens were further serotyped or genotyped by ELISA and/or RT-PCR. RESULTS: During the three years of surveillance, 466 specimens were collected. Rotavirus were detected on 246 (52.8%) specimens. 97% of the rotavirus diarrhea cases occurred among children less than 2 years old. There was a peak of admissions for rotavirus diarrhea cases between October and December which accounted for 48% of all the rotavirus hospitalizations each year. Among 204 specimens with G serotyping, the predominant strain was serotype G1 (47.5%) followed by G2 (17.6%), G3 (15.7%), G9 (4.9%) and G4 (1.0%). Mixed infection (2.5%) were rare and 22 specimens (10.8%) remained non-typeable. P genotyping showed P[4], P[8] and P[6] were the most common strains, accounting for 29.3%, 27.6% and 13.8% respectively. P[4]G2 was the most common strain which accounted for 34.1% (14/41) followed by P[8]G1 (29.3%) and P[6]G9 (12.2%). Another 7 uncommon P-G combinations were also identified. CONCLUSION: Rotavirus was the major cause of acute diarrhea in Kunming. An effective rotavirus vaccine for prevention and control of rotavirus diarrhea should be developed.