Improving virtual screening predictive accuracy of Human kallikrein 5 inhibitors using machine learning models.

The readily available high throughput screening (HTS) data from the PubChem database provides an opportunity for mining of small molecules in a variety of biological systems using machine learning techniques. From the thousands of available molecular descriptors developed to encode useful chemical information representing the characteristics of molecules, descriptor selection is an essential step in building an optimal quantitative structural-activity relationship (QSAR) model. For the development of a systematic descriptor selection strategy, we need the understanding of the relationship between: (i) the descriptor selection; (ii) the choice of the machine learning model; and (iii) the characteristics of the target bio-molecule. In this work, we employed the Signature descriptor to generate a dataset on the Human kallikrein 5 (hK 5) inhibition confirmatory assay data and compared multiple classification models including logistic regression, support vector machine, random forest and k-nearest neighbor. Under optimal conditions, the logistic regression model provided extremely high overall accuracy (98%) and precision (90%), with good sensitivity (65%) in the cross validation test. In testing the primary HTS screening data with more than 200K molecular structures, the logistic regression model exhibited the capability of eliminating more than 99.9% of the inactive structures. As part of our exploration of the descriptor-model-target relationship, the excellent predictive performance of the combination of the Signature descriptor and the logistic regression model on the assay data of the Human kallikrein 5 (hK 5) target suggested a feasible descriptor/model selection strategy on similar targets.

Universal neonatal hearing screening program in Shanghai, China: An inter-regional and international comparison.

OBJECTIVE: By comparing the Universal Neonatal Hearing Screening (UNHS) program as implemented in Shanghai and other regions in China and countries around the world, this study makes an assessment of the Shanghai model and summarizes the experiences implementing the UNHS program, so as to provide a valuable reference for other countries or regions to carry out UNHS more effectively. Since Shanghai is one of the most developed regions in China, we also examined the relationship between economic development and the UNHS starting year and coverage rate. METHODS: The study conducted a systematic review of published studies in Chinese and English on the program status of neonatal hearing screening to compare and analyze the implementation of the UNHS program in 20 cities or provinces in China and 24 regions or countries around the world. The literature search in Chinese was conducted in the three most authoritative publication databases, CNKI (China National Knowledge Infrastructure), WANFANGDATA, and CQVIP (http://www.cqvip.com/). We searched all publications in those databases with the keywords "neonatal hearing screening" (in Chinese) between 2005 and 2014. English literature was searched using the same keywords (in English). The publication database included Medline and Web of Science, and the search time period was 2000-2014. RESULTS: Shanghai was one of the first regions in China to implement UNHS, and its coverage rate was among the top regions by international comparison. The starting time of the UNHS program had no relationship with the Gross Domestic Product (GDP) per capita in the same year. Economic level serves as a threshold for carrying out UNHS but is not a linear contributor to the exact starting time of such a program. The screening coverage rate generally showed a rising trend with the increasing GDP per capita in China, but it had no relationship with the area's GDP per capita in selected regions and countries around the world. The system design of UNHS is the key factor influencing screening coverage. Policy makers, program administrators, and cost-sharing structures are important factors that influence the coverage rates of UNHS. CONCLUSION: When to carry out a UNHS program is determined by the willingness and preference of the local government, which is influenced by the area's social, political and cultural conditions. Mandatory hearing screening and minimal-cost to no-cost intervention are two pillars for a good coverage rate of UNHS. In terms of system design, decision-making, implementation, funding and the concrete implementation plan are all important factors affecting the implementation of the UNHS.

Amino acid derived quinazolines as Rock/PKA inhibitors.

SAR and lead optimization studies for Rock inhibitors based on amino acid-derived quinazolines are described. Studies demonstrated that these amino acid derived quinazolinones were mainly pan-Rock (I & II) inhibitors. While selectivity against other kinases could be achieved, selectivity for most of these compounds against PKA was not achieved. This is distinct from Rock inhibitors based on non-amino acid derived quinazolinones, where high selectivity against PKA could be obtained.(22) The inhibitors presented here in some cases possessed sub-nanomolar inhibition of Rock, nanomolar potency in ppMLC cell based assays, low to fair cytochrome P-450 inhibition, and good human microsomal stability.

Synthesis and biological evaluation of 4-quinazolinones as Rho kinase inhibitors.

Rho kinase (ROCK) is an attractive therapeutic target for various diseases including glaucoma, hypertension, and spinal cord injury. Herein, we report the development of a series of ROCK-II inhibitors based on 4-quinazolinone and quinazoline scaffolds. SAR studies at three positions of the quinazoline core led to the identification of analogs with high potency against ROCK-II and good selectivity over protein kinase A (PKA).

Tetrahydroisoquinoline derivatives as highly selective and potent Rho kinase inhibitors.

Rho kinase (ROCK) is a promising drug target for the treatment of many diseases including hypertension, multiple sclerosis, cancer, and glaucoma. The structure-activity relationships (SAR) around a series of tetrahydroisoquinolines were evaluated utilizing biochemical and cell-based assays to measure ROCK inhibition. These novel ROCK inhibitors possess high potency, high selectivity, and appropriate pharmacokinetic properties for glaucoma applications. The lead compound, 35, had subnanomolar potency in enzyme ROCK-II assays as well as excellent cell-based potency (IC(50) = 51 nM). In a kinase panel profiling, 35 had an off-target hit rate of only 1.6% against 442 kinases. Pharmacology studies showed that compound 35 was efficacious in reducing intraocular pressure (IOP) in rats with reasonably long duration of action. These results suggest that compound 35 may serve as a promising agent for further development in the treatment of glaucoma.

On the 6-exo atom transfer radical cyclization reactions of 3-butenyl 2-iodoalkanoates.

Bis(tributyltin)-initiated atom transfer cyclization reactions of 3-butenyl iodoalkanoates in the presence of BF3.OEt2 as the catalyst afforded the 6-exo cyclization products as a mixture of 3,4-cis- and trans-substituted tetrahydro-2H-pyran-2-ones in 53-71% yield with the major isomers being the cis ones. Ab initio calculations at the B3LYP/6-31G level on the transition states of the radical cyclization and on the cyclized products revealed that the reactions are kinetically controlled and the transition states for the 6-exo radical cyclization are in boat conformations. Moreover, the cis-oriented transition states are of lower energy than the corresponding trans-oriented ones, which are in excellent agreement with experimental results.