J.B. Brown

Hypersensitivity reactions to anticancer agents: Data mining of the public version of the FDA adverse event reporting system, AERS

BackgroundPreviously, adverse event reports (AERs) submitted to the US Food and Drug Administration (FDA) database were reviewed to confirm platinum agent-associated hypersensitivity reactions. The present study was performed to confirm whether the database could suggest the hypersensitivity reactions caused by anticancer agents, paclitaxel, docetaxel, procarbazine, asparaginase, teniposide, and etoposide.MethodsAfter a revision of arbitrary drug names and the deletion of duplicated submissions, AERs involving candidate agents were analyzed. The National Cancer Institute Common Terminology Criteria for Adverse Events version 4.0 was applied to evaluate the susceptibility to hypersensitivity reactions, and standardized official pharmacovigilance tools were used for quantitative detection of signals, i.e., drug-associated adverse events, including the proportional reporting ratio, the reporting odds ratio, the information component given by a Bayesian confidence propagation neural network, and the empirical Bayes geometric mean.ResultsBased on 1,644,220 AERs from 2004 to 2009, the signals were detected for paclitaxel-associated mild, severe, and lethal hypersensitivity reactions, and docetaxel-associated lethal reactions. However, the total number of adverse events occurring with procarbazine, asparaginase, teniposide, or etoposide was not large enough to detect signals.ConclusionsThe FDAs adverse event reporting system, AERS, and the data mining methods used herein are useful for confirming drug-associated adverse events, but the number of co-occurrences is an important factor in signal detection.

COMPOUND ANALYSIS VIA GRAPH KERNELS INCORPORATING CHIRALITY

High accuracy is paramount when predicting biochemical characteristics using Quantitative Structural-Property Relationships (QSPRs). Although existing graph-theoretic kernel methods combined with machine learning techniques are efficient for QSPR model construction, they cannot distinguish topologically identical chiral compounds which often exhibit different biological characteristics. In this paper, we propose a new method that extends the recently developed tree pattern graph kernel to accommodate stereoisomers. We show that Support Vector Regression (SVR) with a chiral graph kernel is useful for target property prediction by demonstrating its application to a set of human vitamin D receptor ligands currently under consideration for their potential anti-cancer effects.

Computational chemogenomics: Is it more than inductive transfer?

High-throughput assays challenge us to extract knowledge from multi-ligand, multi-target activity data. In QSAR, weights are statically fitted to each ligand descriptor with respect to a single endpoint or target. However, computational chemogenomics (CG) has demonstrated benefits of learning from entire grids of data at once, rather than building target-specific QSARs. A possible reason for this is the emergence of inductive knowledge transfer (IT) between targets, providing statistical robustness to the model, with no assumption about the structure of the targets. Relevant protein descriptors in CG should allow one to learn how to dynamically adjust ligand attribute weights with respect to protein structure. Hence, models built through explicit learning (EL) by including protein information, while benefitting from IT enhancement, should provide additional predictive capability, notably for protein deorphanization. This interplay between IT and EL in CG modeling is not sufficiently studied. While IT is likely to occur irrespective of the injected target information, it is not clear whether and when boosting due to EL may occur. EL is only possible if protein description is appropriate to the target set under investigation. The key issue here is the search for evidence of genuine EL exceeding expectations based on pure IT. We explore the problem in the context of Support Vector Regression, using more than 9,400

Exome Sequencing Landscape Analysis in Ovarian Clear Cell Carcinoma Shed Light on Key Chromosomal Regions and Mutation Gene Networks

pK_i

Active learning for computational chemogenomics

pKi values of 31 GPCRs, where compound–protein interactions are represented by the concatenation of vectorial descriptions of compounds and proteins. This provides a unified framework to generate both IT-enhanced and potentially EL-enabled models, where the difference is toggled by supplied protein information. For EL-enabled models, protein information includes genuine protein descriptors such as typical sequence-based terms, but also the experimentally determined affinity cross-correlation fingerprints. These latter benchmark the expected behavior of a quasi-ideal descriptor capturing the actual functional protein-protein relatedness, and therefore thought to be the most likely to enable EL. EL- and IT-based methods were benchmarked alongside classical QSAR, with respect to cross-validation and deorphanization challenges. A rational method for projecting benchmarked methodologies into a strategy space is given, in the aims that the projection will provide directions for the types of molecule designs possible using a given methodology. While EL-enabled strategies outperform classical QSARs and favorably compare to similar published results, they are, in all respects evaluated herein, not strongly distinguished from IT-enhanced models. Moreover, EL-enabled strategies failed to prove superior in deorphanization challenges. Therefore, this paper raises caution that, contrary to common belief and intuitive expectation, the benefits of chemogenomics models over classical QSAR are quite possibly due less to the injection of protein-related information, and rather impacted more by the effect of inductive transfer, due to simultaneous learning from all of the modeled endpoints. These results show that the field of protein descriptor research needs further improvements to truly realize the expected benefit of EL.

Prediction of taxane and platinum sensitivity in ovarian cancer based on gene expression profiles.

Objective: The reports submitted to the US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) from 1997 to 2011 were reviewed to assess serious adverse events induced by the administration of antipsychotics to children. Methods: Following pre-processing of FAERS data by elimination of duplicated records as well as adjustments to standardize drug names, reports involving haloperidol, olanzapine, quetiapine, clozapine, ziprasidone, risperidone, and aripiprazole were analyzed in children (age 0-12). Signals in the data that signified a drug-associated adverse event were detected via quantitative data mining algorithms. The algorithms applied to this study include the empirical Bayes geometric mean, the reporting odds ratio, the proportional reporting ratio, and the information component of a Bayesian confidence propagation neural network. Neuroleptic malignant syndrome (NMS), QT prolongation, leukopenia, and suicide attempt were focused on as serious adverse events. Results: In regard to NMS, the signal scores for haloperidol and aripiprazole were greater than for other antipsychotics. Significant signals of the QT prolongation adverse event were detected only for ziprasidone and risperidone. With respect to leukopenia, the association with clozapine was noteworthy. In the case of suicide attempt, signals for haloperidol, olanzapine, quetiapine, risperidone, and aripiprazole were detected. Conclusions: It was suggested that there is a level of diversity in the strength of the association between various first- and second-generation antipsychotics with associated serious adverse events, which possibly lead to fatal outcomes. We recommend that research be continued in order to gather a large variety and quantity of related information, and that both available and newly reported data be placed in the context of multiple medical viewpoints in order to lead to improved levels of care.

Reliable pre-eclampsia pathways based on multiple independent microarray data sets

Previous studies have reported genome-wide mutation profile analyses in ovarian clear cell carcinomas (OCCCs). This study aims to identify specific novel molecular alterations by combined analyses of somatic mutation and copy number variation. We performed whole exome sequencing of 39 OCCC samples with 16 matching blood tissue samples. Four hundred twenty-six genes had recurrent somatic mutations. Among the 39 samples, ARID1A (62%) and PIK3CA (51%) were frequently mutated, as were genes such as KRAS (10%), PPP2R1A (10%), and PTEN (5%), that have been reported in previous OCCC studies. We also detected mutations in MLL3 (15%), ARID1B (10%), and PIK3R1 (8%), which are associations not previously reported. Gene interaction analysis and functional assessment revealed that mutated genes were clustered into groups pertaining to chromatin remodeling, cell proliferation, DNA repair and cell cycle checkpointing, and cytoskeletal organization. Copy number variation analysis identified frequent amplification in chr8q (64%), chr20q (54%), and chr17q (46%) loci as well as deletion in chr19p (41%), chr13q (28%), chr9q (21%), and chr18q (21%) loci. Integration of the analyses uncovered that frequently mutated or amplified/deleted genes were involved in the KRAS/phosphatidylinositol 3-kinase (82%) and MYC/retinoblastoma (75%) pathways as well as the critical chromatin remodeling complex switch/sucrose nonfermentable (85%). The individual and integrated analyses contribute details about the OCCC genomic landscape, which could lead to enhanced diagnostics and therapeutic options.

Chemical genomics approach for GPCR-ligand interaction prediction and extraction of ligand binding determinants.

With advancements in high‐throughput technologies and open availability of bioassay data, computational methods to generate models, that zoom out from a single protein with a focused ligand set to a larger and more comprehensive description of compound‐protein interactions and furthermore demonstrate subsequent translational validity in prospective experiments, are of prime importance. In this article, we discuss some of the new benefits and challenges of the emerging computational chemogenomics paradigm, particularly with respect to compound‐protein interaction. Examples of experimentally validated computational predictions and recent trends in molecular feature extraction are presented. In addition, analyses of cross‐family interactions are considered. We also discuss the expected role of computational chemogenomics in contributing to increasingly expansive network‐level modeling and screening projects.