Tests of the Specification and Predictive Accuracy of Nonnested Models of Inflation

Background: Enhancing a compound’s biological activity is the central task for lead optimization in small molecules drug discovery. However, it is laborious to perform many iterative rounds of compound synthesis and bioactivity tests. To address the issue, it is highly demanding to develop high quality in silico bioactivity prediction approaches, to prioritize such more active compound derivatives and reduce the trial-and-error process. Methods: Two kinds of bioactivity prediction models based on a large-scale structure-activity relationship (SAR) database were constructed. The first one is based on the similarity of substituents and realized by matched molecular pair analysis, including SA, SA_BR, SR, and SR_BR. The second one is based on SAR transferability and realized by matched molecular series analysis, including Single MMS pair, Full MMS series, and Multi single MMS pairs. Moreover, we also defined the application domain of models by using the distance-based threshold. Results: Among seven individual models, Multi single MMS pairs bioactivity prediction model showed the best performance (R2 = 0.828, MAE = 0.406, RMSE = 0.591), and the baseline model (SA) produced the most lower prediction accuracy (R2 = 0.798, MAE = 0.446, RMSE = 0.637). The predictive accuracy could further be improved by consensus modeling (R2 = 0.842, MAE = 0.397 and RMSE = 0.563). Conclusion: An accurate prediction model for bioactivity was built with a consensus method, which was superior to all individual models. Our model should be a valuable tool for lead optimization.

Download Full-text

Improving bioclimatic envelop modeling for Lichens through remote sensing based substratum correction: A study over Indian Himalaya

Cryptogam Biodiversity and Assessment ◽

10.21756/cab.v1i2.6655 ◽

2016 ◽

Vol 1 (2) ◽

Author(s):

C. P. Singh ◽

R. Bajpai ◽

R. P. Singh ◽

D. K. Upreti

Keyword(s):

Remote Sensing ◽

Predictive Accuracy ◽

Geographic Area ◽

Jammu And Kashmir ◽

Indian Himalaya ◽

Novel Approach ◽

Digital Elevation ◽

Average Probability ◽

Niche Area ◽

Elevation Model

In alpine Himalaya, the niche map of lichens and its characteristics is a gap area. A novel approach of improving the bioclimatic envelop through use of remote sensing inputs was employed. The 19 bioclimatic indices and digital elevation model were used for training niche models through occurrence records of 33 lichen species across Indian Himalaya. Substratum correction was carried out using LU/LC data. About 45% of the total geographic area studied is found to be very conducive (with niche probability > 70%) for the growth of lichens with predictive accuracy of 91% ascertained through cross-validation. Jammu and Kashmir is having highest niche area (36.02%); however, average probability niche score is highest in Uttarakhand (81.08). Area between 27o - 28o N latitude is having highest area however average probability score is highest in 30o - 31o N. Overall maximum niche area (35.50 %) is found in the regions dominated by alpine meadow, alpine grasslands and parts of cold deserts. The potential use lies in reporting yet to be explored lichens in the Indian Himalaya.

Download Full-text