You might want to look at what is in OpenTox. Quoting from the home page: "The OpenTox Framework provides tools for the integration of data from various sources (public and confidential), for the generation and validation of computer models for toxic effects, libraries for the development and seamless integration of new algorithms, and scientifically sound validation routines. OpenTox is relevent for users from a variety of research areas:

• Toxicological and chemical experts (e.g. risk assessors, drug designers, researchers)

• computer model developers and algorithm developers

• non specialists requiring access to Predictive Toxicology models and data."

Also, PubMed has a very recent publication on 'In silico toxicology: computational methods for the prediction of chemical toxicity." An excerpt from the abstract: "We provide a comprehensive overview, explain, and compare the strengths and weaknesses of the existing modeling methods and algorithms for toxicity prediction with a particular (but not exclusive) emphasis on computational tools that can implement these methods and refer to expert systems that deploy the prediction models. Finally, we briefly review a number of new research directions in in silico toxicology and provide recommendations for designing in silico models."

Finally, another PubMed citation is one on "Comprehension of drug toxicity: software and databases." Quoting from the abstract: "This mini-review provides analysis of existing databases and software which are necessary for use of robust computational assessments and robust prediction of potential drug toxicities by means of in silico methods."

http://www.opentox.org/home/about

http://www.ncbi.nlm.nih.gov/pubmed/24480159

http://www.ncbi.nlm.nih.gov/pubmed/27066112

You can use the VEGA suite (http://www.vega-qsar.eu/) that is free

or the suite ACD (http://www.acdlabs.com/products/percepta/physchem_adme_tox/) that is commercial

VEGA suite is a good call. There is alo ADMETsar http://lmmd.ecust.edu.cn:8000/

Be careful with any tool that makes predictions based on structural alerts: http://pubs.rsc.org/en/Content/ArticleLanding/2016/GC/C6GC01492E#!divAbstract