Semantic text mining in early drug discovery for type 2 diabetes.

BACKGROUND: Surveying the scientific literature is an important part of early drug discovery; and with the ever-increasing amount of biomedical publications it is imperative to focus on the most interesting articles. Here we present a project that highlights new understanding (e.g. recently discovered modes of action) and identifies potential drug targets, via a novel, data-driven text mining approach to score type 2 diabetes (T2D) relevance. We focused on monitoring trends and jumps in T2D relevance to help us be timely informed of important breakthroughs. METHODS: We extracted over 7 million n-grams from PubMed abstracts and then clustered around 240,000 linked to T2D into almost 50,000 T2D relevant 'semantic concepts'. To score papers, we weighted the concepts based on co-mentioning with core T2D proteins. A protein's T2D relevance was determined by combining the scores of the papers mentioning it in the five preceding years. Each week all proteins were ranked according to their T2D relevance. Furthermore, the historical distribution of changes in rank from one week to the next was used to calculate the significance of a change in rank by T2D relevance for each protein. RESULTS: We show that T2D relevant papers, even those not mentioning T2D explicitly, were prioritised by relevant semantic concepts. Well known T2D proteins were therefore enriched among the top scoring proteins. Our 'high jumpers' identified important past developments in the apprehension of how certain key proteins relate to T2D, indicating that our method will make us aware of future breakthroughs. In summary, this project facilitated keeping up with current T2D research by repeatedly providing short lists of potential novel targets into our early drug discovery pipeline.

Conflicting associations between dietary patterns and changes of anthropometric traits across subgroups of middle-aged women and men.

BACKGROUND: Individuals respond differently to dietary intake leading to different associations between diet and traits. Most studies have investigated large cohorts without subgrouping them. OBJECTIVE: The purpose was to identify non-uniform associations between diets and anthropometric traits that appeared to be in conflict with one another across subgroups. DESIGN: We used a cohort comprising 43,790 women and men, the Danish Diet, Cancer and Health study, which includes a baseline examination at age 50-64 years and a follow-up about 5 years later. The baseline examination involved anthropometrics, body fat percentage, a food frequency questionnaire and information on lifestyle. From the questionnaire data we computed association rules between the intake of food groups and changes in waist circumference and body weight. Using association rule mining on subgroups and gender-specific cohorts, we identified non-uniform associations. The two gender-specific cohorts were stratified into subgroups using a non-linear, self-organizing map based method. RESULTS: We found 22 and 7 cases of conflicting rules in 8 participant subgroups for different anthropometric traits in women and men, respectively. For example, in a subgroup of women moderate waist loss was associated with a dietary pattern characterized by low intake in both cabbages and wine, in conflict with the association trends of both dietary factors in the female cohort. The finding of more conflicting rules in women suggests that inter-individual differences in response to dietary intake are stronger in women than in men. CONCLUSIONS: This combined stratification and association discovery approach revealed epidemiological relationships between dietary factors and changes in anthropometric traits in subgroups that take food group interactions into account. Conflicting rules adds an additional layer of complexity that should be integrated into the study of these relationships, for example in relation to genotypes.

ChemProt-3.0: a global chemical biology diseases mapping.

ChemProt is a publicly available compilation of chemical-protein-disease annotation resources that enables the study of systems pharmacology for a small molecule across multiple layers of complexity from molecular to clinical levels. In this third version, ChemProt has been updated to more than 1.7 million compounds with 7.8 million bioactivity measurements for 19,504 proteins. Here, we report the implementation of global pharmacological heatmap, supporting a user-friendly navigation of chemogenomics space. This facilitates the visualization and selection of chemicals that share similar structural properties. In addition, the user has the possibility to search by compound, target, pathway, disease and clinical effect. Genetic variations associated to target proteins were integrated, making it possible to plan pharmacogenetic studies and to suggest human response variability to drug. Finally, Quantitative Structure-Activity Relationship models for 850 proteins having sufficient data were implemented, enabling secondary pharmacological profiling predictions from molecular structure. Database URL: http://potentia.cbs.dtu.dk/ChemProt/.