Text mining and portal development for gene-specific publications on Alzheimer's disease and other neurodegenerative diseases.

BACKGROUND: Tremendous research efforts have been made in the Alzheimer's disease (AD) field to understand the disease etiology, progression and discover treatments for AD. Many mechanistic hypotheses, therapeutic targets and treatment strategies have been proposed in the last few decades. Reviewing previous work and staying current on this ever-growing body of AD publications is an essential yet difficult task for AD researchers. METHODS: In this study, we designed and implemented a natural language processing (NLP) pipeline to extract gene-specific neurodegenerative disease (ND) -focused information from the PubMed database. The collected publication information was filtered and cleaned to construct AD-related gene-specific publication profiles. Six categories of AD-related information are extracted from the processed publication data: publication trend by year, dementia type occurrence, brain region occurrence, mouse model information, keywords occurrence, and co-occurring genes. A user-friendly web portal is then developed using Django framework to provide gene query functions and data visualizations for the generalized and summarized publication information. RESULTS: By implementing the NLP pipeline, we extracted gene-specific ND-related publication information from the abstracts of the publications in the PubMed database. The results are summarized and visualized through an interactive web query portal. Multiple visualization windows display the ND publication trends, mouse models used, dementia types, involved brain regions, keywords to major AD-related biological processes, and co-occurring genes. Direct links to PubMed sites are provided for all recorded publications on the query result page of the web portal. CONCLUSION: The resulting portal is a valuable tool and data source for quick querying and displaying AD publications tailored to users' interested research areas and gene targets, which is especially convenient for users without informatic mining skills. Our study will not only keep AD field researchers updated with the progress of AD research, assist them in conducting preliminary examinations efficiently, but also offers additional support for hypothesis generation and validation which will contribute significantly to the communication, dissemination, and progress of AD research.

Predicting pharmacotherapeutic outcomes for type 2 diabetes: An evaluation of three approaches to leveraging electronic health record data from multiple sources.

Electronic health record (EHR) data are increasingly used to develop prediction models to support clinical care, including the care of patients with common chronic conditions. A key challenge for individual healthcare systems in developing such models is that they may not be able to achieve the desired degree of robustness using only their own data. A potential solution-combining data from multiple sources-faces barriers such as the need for data normalization and concerns about sharing patient information across institutions. To address these challenges, we evaluated three alternative approaches to using EHR data from multiple healthcare systems in predicting the outcome of pharmacotherapy for type 2 diabetes mellitus(T2DM). Two of the three approaches, named Selecting Better (SB) and Weighted Average(WA), allowed the data to remain within institutional boundaries by using pre-built prediction models; the third, named Combining Data (CD), aggregated raw patient data into a single dataset. The prediction performance and prediction coverage of the resulting models were compared to single-institution models to help judge the relative value of adding external data and to determine the best method to generate optimal models for clinical decision support. The results showed that models using WA and CD achieved higher prediction performance than single-institution models for common treatment patterns. CD outperformed the other two approaches in prediction coverage, which we defined as the number of treatment patterns predicted with an Area Under Curve of 0.70 or more. We concluded that 1) WA is an effective option for improving prediction performance for common treatment patterns when data cannot be shared across institutional boundaries and 2) CD is the most effective approach when such sharing is possible, especially for increasing the range of treatment patterns that can be predicted to support clinical decision making.

Utilization of electronic health records for the assessment of adiponectin receptor autoantibodies during the progression of cardio-metabolic comorbidities.

BACKGROUND: Diabetes is a complex, multi-symptomatic disease whose complications drives increases in healthcare costs as the diabetes prevalence grows rapidly world-wide. Real-world electronic health records (EHRs) coupled with patient biospecimens, biological understanding, and technologies can characterize emerging diagnostic autoimmune markers resulting from proteomic discoveries. METHODS: Circulating autoantibodies for C-terminal fragments of adiponectin receptor 1 (IgG-CTF) were measured by immunoassay to establish the reference range using midpoint samples from 1862 participants in a 20-year observational study of type 2 diabetes and cardiovascular arterial disease (CVAD) conducted by the Fairbanks Institute. The White Blood Cell elastase activity in these patients was assessed using immunoassays for Bikunin and Uristatin. Participants were assigned to four cohorts (healthy, T2D, CV, CV+T2D) based on analysis of their EHRs and the diagnostic biomarkers values and patient status were assessed ten-years post-sample. RESULTS: The IgG-CTF reference range was determined to be 75-821 ng/mL and IgG-CTF out-of-range values did not predict cohort or comorbidity as determined from the EHRs at 10 years after sample collection nor did IgG-CTF demonstrate a significant risk for comorbidity or death. Many patients at sample collection time had other conditions (hypertension, hyperlipidemia, or other risk factors) of which only hypertension, Uristatin and Bikunin values correlated with increased risk of developing additional comorbidities (odds ratio 2.58-13.11, P<0.05). CONCLUSIONS: This study confirms that retrospective analysis of biorepositories coupled with EHRs can establish reference ranges for novel autoimmune diagnostic markers and provide insights into prediction of specific health outcomes and correlations to other markers.

A Novel Open Access Web Portal for Integrating Mechanistic and Toxicogenomic Study Results.

Applying toxicogenomics to improving the safety profile of drug candidates and crop protection molecules is most useful when it identifies relevant biological and mechanistic information that highlights risks and informs risk mitigation strategies. Pathway-based approaches, such as gene set enrichment analysis, integrate toxicogenomic data with known biological process and pathways. Network methods help define unknown biological processes and offer data reduction advantages. Integrating the 2 approaches would improve interpretation of toxicogenomic information. Barriers to the routine application of these methods in genome-wide transcriptomic studies include a need for "hands-on" computer programming experience, the selection of 1 or more analysis methods (eg pathway analysis methods), the sensitivity of results to algorithm parameters, and challenges in linking differential gene expression to variation in safety outcomes. To facilitate adoption and reproducibility of gene expression analysis in safety studies, we have developed Collaborative Toxicogeomics, an open-access integrated web portal using the Django web framework. The software, developed with the Python programming language, is modular, extensible and implements "best-practice" methods in computational biology. New study results are compared with over 4000 rodent liver experiments from Drug Matrix and open TG-GATEs. A unique feature of the software is the ability to integrate clinical chemistry and histopathology-derived outcomes with results from gene expression studies, leading to relevant mechanistic conclusions. We describe its application by analyzing the effects of several toxicants on liver gene expression and exemplify application to predicting toxicity study outcomes upon chronic treatment from expression changes in acute-duration studies.

Predicting the early risk of chronic kidney disease in patients with diabetes using real-world data.

Diagnostic procedures, therapeutic recommendations, and medical risk stratifications are based on dedicated, strictly controlled clinical trials. However, a plethora of real-world medical data exists, whereupon the increase in data volume comes at the expense of completeness, uniformity, and control. Here, a case-by-case comparison shows that the predictive power of our real world data-based model for diabetes-related chronic kidney disease outperforms published algorithms, which were derived from clinical study data.

Predicting onset of complications from diabetes: a graph based approach.

Diabetes is a significant health concern with more than 30 million Americans living with diabetes. Onset of diabetes increases the risk for various complications, including kidney disease, myocardial infractions, heart failure, stroke, retinopathy, and liver disease. In this paper, we study and predict the onset of these complications using a network-based approach by identifying fast and slow progressors. That is, given a patient's diagnosis of diabetes, we predict the likelihood of developing one or more of the possible complications, and which patients will develop complications quickly. This combination of "if a complication will be developed" with "how fast it will be developed" can aid the physician in developing better diabetes management program for a given patient.

Kinomics: characterizing the therapeutically validated kinase space.

The annotation and visualization of medicinally relevant kinase space revealed that kinase inhibitors in the clinic are, on average, of higher molecular weight and more lipophilic than all other clinically investigated drugs. Tyrosine kinases from the vascular endothelial growth factor and epidermal growth factor receptor families are the most pursued targets. Furthermore, oncological indications account for 75% of all kinase-related clinical interest. In addition, analysis of the similarity between kinase targets with respect to sequence, selectivity and structure has revealed that kinases with > or =60% sequence identity are most likely to be inhibited by the same classes of compounds and have similar ATP-binding sites. The identification of this threshold, together with the widely accepted representation of the sequence-based kinase space, is expanding our understanding of the clinical and structural space of the kinome.

Kinomics-structural biology and chemogenomics of kinase inhibitors and targets.

Classifying kinases based entirely on small molecule selectivity data is a new approach to drug discovery that allows scientists to understand relationships between targets. This approach combines the understanding of small molecules and targets, and thereby assists the researcher in finding new targets for existing molecules or understanding selectivity and polypharmacology of molecules in related targets. Currently, structural information is available for relatively few of the protein kinases encoded in the human genome (7% of the estimated 518); however, even the current knowledge base, when paired with structure-based design techniques, can assist in the identification and optimization of novel kinase inhibitors across the entire protein class. Chemogenomics attempts to combine genomic data, structural biological data, classical dendrograms, and selectivity data to explore, define, and classify the medicinally relevant kinase space. Exploitation of this information in the discovery of kinase inhibitors defines practical kinase chemogenomics (kinomics). In this paper, we review the available information on kinase targets and their inhibitors, and present the relationships between the various classification schema for kinase space. In particular, we present the first dendrogram of kinases based entirely on small molecule selectivity data. We find that the selectivity dendrogram differs from sequence-based clustering mostly in the higher-level groupings of the smaller clusters, and remains very comparable for closely homologous targets. Highly homologous kinases are, on average, inhibited comparably by small molecules. This observation, although intuitive, is very important to the process of target selection, as one would expect difficulty in achieving inhibitor selectivity for kinases that share high sequence identity.

Lessons in molecular recognition: the effects of ligand and protein flexibility on molecular docking accuracy.

The key to success for computational tools used in structure-based drug design is the ability to accurately place or "dock" a ligand in the binding pocket of the target of interest. In this report we examine the effect of several factors on docking accuracy, including ligand and protein flexibility. To examine ligand flexibility in an unbiased fashion, a test set of 41 ligand-protein cocomplex X-ray structures were assembled that represent a diversity of size, flexibility, and polarity with respect to the ligands. Four docking algorithms, DOCK, FlexX, GOLD, and CDOCKER, were applied to the test set, and the results were examined in terms of the ability to reproduce X-ray ligand positions within 2.0A heavy atom root-mean-square deviation. Overall, each method performed well (>50% accuracy) but for all methods it was found that docking accuracy decreased substantially for ligands with eight or more rotatable bonds. Only CDOCKER was able to accurately dock most of those ligands with eight or more rotatable bonds (71% accuracy rate). A second test set of structures was gathered to examine how protein flexibility influences docking accuracy. CDOCKER was applied to X-ray structures of trypsin, thrombin, and HIV-1-protease, using protein structures bound to several ligands and also the unbound (apo) form. Docking experiments of each ligand to one "average" structure and to the apo form were carried out, and the results were compared to docking each ligand back to its originating structure. The results show that docking accuracy falls off dramatically if one uses an average or apo structure. In fact, it is shown that the drop in docking accuracy mirrors the degree to which the protein moves upon ligand binding.

Characteristic physical properties and structural fragments of marketed oral drugs.

An increasingly competitive pharmaceutical market demands improvement in the efficiency and probability of drug candidate discovery. Usually these new drug candidates are targeted for oral administration, so a detailed understanding of the molecular-level properties that relate to optimal pharmacokinetics is a critical step toward improving the probability of selecting successful clinical candidates. Although the characteristics of druglike molecules have been previously discussed in the literature, the importance of this topic sustains a continued interest for additional perspective and further detailed statistical analyses. In this contribution, we approach the analysis from the perspective of profiling distinguishing features of orally administered drugs. We have compiled both structural and route-administration information for a total of 1729 marketed drugs to provide a solid basis for developing a new perspective on the characteristics of over 1000 orally administered drugs. The molecular properties and most commonly occurring structural elements are statistically analyzed to capture the differences between routes of administration, as well as between marketed drugs and SAR or clinical compounds. We find that, with respect to other routes of administration, oral drugs tend to be lighter and have fewer H-bond donors, acceptors, and rotatable bonds than drugs with other routes of administration. These differences are particularly pronounced when comparing the mean values for oral vs injectable drugs. We also demonstrate that the mean property values for oral drugs do not vary substantially with respect to launch date, suggesting that the range of acceptable oral properties is independent of synthetic complexity or targeted receptor. Finally, we note that, while these properties are descriptive of each class, they are not necessarily predictive of what class any particular drug will reside in, since there is significant overlap in the acceptable ranges found for each drug class.

Detailed analysis of grid-based molecular docking: A case study of CDOCKER-A CHARMm-based MD docking algorithm.

The influence of various factors on the accuracy of protein-ligand docking is examined. The factors investigated include the role of a grid representation of protein-ligand interactions, the initial ligand conformation and orientation, the sampling rate of the energy hyper-surface, and the final minimization. A representative docking method is used to study these factors, namely, CDOCKER, a molecular dynamics (MD) simulated-annealing-based algorithm. A major emphasis in these studies is to compare the relative performance and accuracy of various grid-based approximations to explicit all-atom force field calculations. In these docking studies, the protein is kept rigid while the ligands are treated as fully flexible and a final minimization step is used to refine the docked poses. A docking success rate of 74% is observed when an explicit all-atom representation of the protein (full force field) is used, while a lower accuracy of 66-76% is observed for grid-based methods. All docking experiments considered a 41-member protein-ligand validation set. A significant improvement in accuracy (76 vs. 66%) for the grid-based docking is achieved if the explicit all-atom force field is used in a final minimization step to refine the docking poses. Statistical analysis shows that even lower-accuracy grid-based energy representations can be effectively used when followed with full force field minimization. The results of these grid-based protocols are statistically indistinguishable from the detailed atomic dockings and provide up to a sixfold reduction in computation time. For the test case examined here, improving the docking accuracy did not necessarily enhance the ability to estimate binding affinities using the docked structures.