In silico prediction of chemical toxicity profile using local lazy learning.

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. 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, the prediction ability of the 'ECFP_4+LLL' model was tested and verified by two external sets. Finally, some essential toxicophores for six types of toxicities were identified by using the Laplacian-modified Bayesian model. We wish that the accurate prediction model and the chemical toxicophores can provide some guidance for designing drugs with lower toxicity. PMID: 28215144 [PubMed - as supplied by publisher]
Source: Combinatorial Chemistry and High Throughput Screening - Category: Chemistry Authors: Tags: Comb Chem High Throughput Screen Source Type: research