A parallel integrated learning technique of improved particle swarm optimization and BP neural network and its application.

Swarm intelligence algorithm has attracted a lot of interest since its development, which has been proven to be effective in many application areas. In this study, an enhanced integrated learning technique of improved particle swarm optimization and BPNN (Back Propagation Neural Network) is proposed. First, the theory of good point sets is used to create a particle swarm with a uniform initial spatial distribution. So a good point set adaptive particle swarm optimization (GPSAPSO) algorithm was created by using a multi-population co-evolution approach and introducing a function that dynamically changes the inertia weights with the number of iterations. Sixteen benchmark functions were used to confirm the efficacy of the algorithm. Secondly, a parallel integrated approach combining the GPSAPSO algorithm and the BPNN was developed and utilized to build a water quality prediction model. Finally, four sets of cross-sectional data of the Huai River in Bengbu, Anhui Province, China, were used as simulation data for experiments. The experimental results show that the GPSAPSO-BPNN algorithm has obvious advantages compared with TTPSO-BPNN, NSABC-BPNN, IGSO-BPNN and CRBA-BPNN algorithms, which improves the accuracy of water quality prediction results and provides a scientific basis for water quality monitoring and management.

Deep Learning Based on Hierarchical Self-Attention for Finance Distress Prediction Incorporating Text.

To detect comprehensive clues and provide more accurate forecasting in the early stage of financial distress, in addition to financial indicators, digitalization of lengthy but indispensable textual disclosure, such as Management Discussion and Analysis (MD&A), has been emphasized by researchers. However, most studies divide the long text into words and count words to treat the text as word count vectors, bringing massive invalid information but ignoring meaningful contexts. Aiming to efficiently represent the text of large size, an end-to-end neural networks model based on hierarchical self-attention is proposed in this study after the state-of-the-art pretrained model is introduced for text embedding including contexts. The proposed model has two notable characteristics. First, the hierarchical self-attention only affords the essential content with high weights in word-level and sentence-level and automatically neglects lots of information that has no business with risk prediction, which is suitable for extracting effective parts of the large-scale text. Second, after fine-tuning, the word embedding adapts the specific contexts of samples and conveys the original text expression more accurately without excessive manual operations. Experiments confirm that the addition of text improves the accuracy of financial distress forecasting and the proposed model outperforms benchmark models better at AUC and F2-score. For visualization, the elements in the weight matrix of hierarchical self-attention act as scalers to estimate the importance of each word and sentence. In this way, the "red-flag" statement that implies financial risk is figured out and highlighted in the original text, providing effective references for decision-makers.

Towards the second generation of Boceprevir: Dithianes as an alternative P2 substituent for 2,2-dimethyl cycloproyl proline in HCV NS3 protease inhibitors.

Hepatitis C (HCV) infection is a global health crisis leading to chronic liver disease. In our efforts towards a second generation HCV NS3 serine protease inhibitor with improved profile, we have undertaken SAR studies in various regions of Boceprevir including P2. Herein, we report the synthesis and structure-activity relationship studies of inhibitors with (S)-1,4-dithia-7-azaspiro[4.4]nonane-8-carboxylic acid 2 as P2 substituent replacing the (1R,2S,5S)-6,6-dimethyl 3-azabicyclo[3.1.0]hexane-2-carboxylic acid. The systematic investigation led to the discovery of highly potent inhibitor 25 (K(i)( *)=7nM, EC(90)=30nM) with improved rat exposure of 2.56microM h.

Discovery of Narlaprevir (SCH 900518): A Potent, Second Generation HCV NS3 Serine Protease Inhibitor.

Boceprevir (SCH 503034), 1, a novel HCV NS3 serine protease inhibitor discovered in our laboratories, is currently undergoing phase III clinical trials. Detailed investigations toward a second generation protease inhibitor culminated in the discovery of narlaprevir (SCH 900518), 37, with improved potency (∼10-fold over 1), pharmacokinetic profile and physicochemical characteristics, currently in phase II human trials. Exploration of synthetic sequence for preparation of 37 resulted in a route that required no silica gel purification for the entire synthesis.

Toward the back-up of boceprevir (SCH 503034): discovery of new extended P4-capped ketoamide inhibitors of hepatitis C virus NS3 serine protease with improved potency and pharmacokinetic profiles.

Hepatitis C is the most prevalent liver disease. Viral hepatitis C (HCV), a small (+)-RNA virus, infects chronically an estimated 300 million people worldwide. Results of Phase I clinical studies with our first generation HCV inhibitor Boceprevir, SCH 503034 (1), presented at the 56th Annual Meeting of the American Association for the Study of Liver Diseases (AASLD) were encouraging, and thus, additional human clinical studies are underway. In view of the positive data from our first generation compound, further work aimed at optimizing its overall profile was undertaken. Herein, we report that extension of our earlier inhibitor to the P(4) pocket and optimization of the P(1)' capping led to the discovery of new ketoamide inhibitors of the HCV NS3 serine protease with improved in vitro potency. In addition to being potent inhibitors of HCV subgenomic RNA replication, some of the new P(4)-capped inhibitors were also found to have improved PK profile.

Discovery of (1R,5S)-N-[3-amino-1-(cyclobutylmethyl)-2,3-dioxopropyl]- 3-[2(S)-[[[(1,1-dimethylethyl)amino]carbonyl]amino]-3,3-dimethyl-1-oxobutyl]- 6,6-dimethyl-3-azabicyclo[3.1.0]hexan-2(S)-carboxamide (SCH 503034), a selective, potent, orally bioavailable hepatitis C virus NS3 protease inhibitor: a potential therapeutic agent for the treatment of hepatitis C infection.

Hepatitis C virus (HCV) infection is the major cause of chronic liver disease, leading to cirrhosis and hepatocellular carcinoma, which affects more than 170 million people worldwide. Currently the only therapeutic regimens are subcutaneous interferon-alpha or polyethylene glycol (PEG)-interferon-alpha alone or in combination with oral ribavirin. Although combination therapy is reasonably successful with the majority of genotypes, its efficacy against the predominant genotype (genotype 1) is moderate at best, with only about 40% of the patients showing sustained virological response. Herein, the SAR leading to the discovery of 70 (SCH 503034), a novel, potent, selective, orally bioavailable NS3 protease inhibitor that has been advanced to clinical trials in human beings for the treatment of hepatitis C viral infections is described. X-ray structure of inhibitor 70 complexed with the NS3 protease and biological data are also discussed.

Discovery of SCH446211 (SCH6): a new ketoamide inhibitor of the HCV NS3 serine protease and HCV subgenomic RNA replication.

Introduction of various modified prolines at P(2) and optimization of the P(1) side chain led to the discovery of SCH6 (24, Table 2), a potent ketoamide inhibitor of the HCV NS3 serine protease. In addition to excellent enzyme potency (K(i)*= 3.8 nM), 24 was also found to be a potent inhibitor of HCV subgenomic RNA replication with IC(50) and IC(90) of 40 and 100 nM, respectively. Recently, antiviral activity of 24 was demonstrated with inhibition of the full-length genotype 2a HCV genome. In addition, 24 was found to restore the responsiveness of the interferon regulatory factor 3 (IRF-3) in cells containing HCV RNA replicons.

Depeptidization efforts on P3-P2' alpha-ketoamide inhibitors of HCV NS3-4A serine protease: effect on HCV replicon activity.

Depeptidization efforts of the P(3)-P(2) region of P(3) capped alpha-ketoamide inhibitor of HCV NS3 serine protease 1 are reported. We clearly established that N-methylation of the P(2) nitrogen and modification of the P(2)' carboxylic acid terminus were essential for activity in the replicon assay.