Learning from Multiple Classifier Systems: Perspectives for Improving Decision Making of QSAR Models in Medicinal Chemistry.

Quantitative Structure - Activity Relationship (QSAR) modeling has been widely used in medicinal chemistry and computational toxicology for many years. Today, as the amount of chemicals is increasing dramatically, QSAR methods have become pivotal for the purpose of handling the data, identifying a decision, and gathering useful information from data processing. The advances in this field have paved a way for numerous alternative approaches that require deep mathematics in order to enhance the learning capability of QSAR models. One of these directions is the use of Multiple Classifier Systems (MCSs) that potentially provide a means to exploit the advantages of manifold learning through decomposition frameworks, while improving generalization and predictive performance. In this paper, we presented MCS as a next generation of QSAR modeling techniques and discuss the chance to mining the vast number of models already published in the literature. We systematically revisited the theoretical frameworks of MCS as well as current advances in MCS application for QSAR practice. Furthermore, we illustrated our idea by describing ensemble approaches on modeling histone deacetylase (HDACs) inhibitors. We expect that our analysis would contribute to a better understanding about MCS application and its future perspectives for improving the decision making of QSAR models.

Whole genome analysis of a Vietnamese trio.

We here present the first whole genome analysis of an anonymous Kinh Vietnamese (KHV) trio whose genomes were deeply sequenced to 30-fold average coverage. The resulting short reads covered 99.91 percent of the human reference genome (GRCh37d5). We identified 4,719,412 SNPs and 827,385 short indels that satisfied the Mendelian inheritance law. Among them, 109,914 (2.3 percent) SNPs and 59,119 (7.1 percent) short indels were novel. We also detected 30,171 structural variants of which 27,604 (91.5 percent) were large indels. There were 6,681 large indels in the range 0.1-100 kbp occurring in the child genome that were also confirmed in either the father or mother genome. We compared these large indels against the DGV database and found that 1,499 (22.44 percent) were KHV specific. De novo assembly of high-quality unmapped reads yielded 789 contigs with the length greater than or equal to 300 bp. There were 235 contigs from the child genome of which 199 (84.7 percent) were significantly matched with at least one contig from the father or mother genome. Blasting these 199 contigs against other alternative human genomes revealed 4 novel contigs. The novel variants identified from our study demonstrated the necessity of conducting more genome-wide studies not only for Kinh but also for other ethnic groups in Vietnam.