Combinatorial Chemistry & High Throughput Screening

Rathnam Chaguturu 
iDDPartners, 3 Edith Court
Princeton Junction
NJ 08550


In Silico Prediction of Chemical Toxicity Profile Using Local Lazy Learning

Author(s): Jing Lu, Pin Zhang, Xiao-Wen Zou, Xiao-Qiang Zhao, Ke-Guang Cheng, Yi-Lei Zhao, Yi Bi, Ming-Yue Zheng, Xiao-Min Luo.


Background: Chemical toxicity is an important reason for late-stage failure in drug R&D. However, it is time-consuming and expensive to identify the multiple toxicities of compounds using the traditional experiments. Thus, it is attractive to build an accurate prediction model for the toxicity profile of compounds.

Materials and Methods: In this study, we carried out a research on six types of toxicities: (I) Acute Toxicity; (II) Mutagenicity; (III) Tumorigenicity; (IV) Skin and Eye Irritation; (V) Reproductive Effects; (VI) Multiple Dose Effects, using local lazy learning (LLL) method for multi-label learning. 17,120 compounds were split into the training set and the test set as a ratio of 4:1 by using the Kennard-Stone algorithm. Four types of properties, including molecular fingerprints (ECFP_4 and FCFP_4), descriptors, and chemical-chemical-interactions, were adopted for model building.

Results: The model ‘ECFP_4+LLL’ yielded the best performance for the test set, while balanced accuracy (BACC) reached 0.692, 0.691, 0.666, 0.680, 0.631, 0.599 for six types of toxicities, respectively. Furthermore, some essential toxicophores for six types of toxicities were identified by using the Laplacian-modified Bayesian model.

Conclusion: The accurate prediction model and the chemical toxicophores can provide some guidance for designing drugs with low toxicity.

Keywords: Toxicity profile, Local lazy learning, ECFP_4, Laplacian-modified Bayesian.

Order Reprints Order Eprints Rights & PermissionsPrintExport

Article Details

Year: 2017
Page: [346 - 353]
Pages: 8
DOI: 10.2174/1386207320666170217151826
Price: $58