Comment 7. I am not positive if this topic is appropriate for this computational biology centric journal. Maybe, this function is a lot more ideal for publishing in journals like BMC. Response. We are thankful for this suggestion and we think this kind of perform is effectively suited for this journal. Good quality of written English. Acceptable Comment 1. The authors formulated numerous classifi cation models working with an exhaustive set of chemical fingerprints for discriminating authorized medication from ex perimental medicines and produced these designs readily available by means of a internet server. Prior to now years, many newly accepted drug molecules are breaking the widely accepted rule of five for drug likeness, this bettering and updating techniques for calculating drug likeness is definitely an essential difficulty. How ever, I dont have an understanding of why authors created designs that discriminate authorized medicines from experimental medicines. Experimental drugs are molecules which might be under investigation.
Remaining experimental won’t meet the com pound is not drug like, so any model that read this post here discriminates authorized from experimental isn’t going to have any value. The exhaustive technique would be useful if designs have been de veloped to discriminate drug like, harmless compounds from possibly toxic, non drug like compounds. Response. We thoroughly agreed with the reviewer comment. Even though, studies are already finished previously with centered in direction of the discrimination of drug like mol ecules from non drug like ones. But many of these had been primarily based to the use of industrial dataset like MDDR, CMC as drug like and ACD as non drug like dataset. Hence, availability of your dataset is definitely the leading challenge. In contrast, our technique is definitely an attempt to discriminate two closely re lated drug like molecules.
This will be an advance phase in drug layout process mainly because in spite of the in vitro drug PF-04691502 like properties, many medicines failed in clinical trial, As a result, its crucial to discriminate these two courses of molecules. This is often the only dataset that’s avai lable for public use and can be a great asset for deve lopment of public domain servers. High-quality of written English. Not suitable for publication unless of course extensively edited Response. We are thankful on the reviewer for this comment. During the revised model, we have experimented with our very best to enhance quality of English in revised version of manuscript. Hopefully, the revised version will likely be suit capable for publication. Response to your Reviewers comments after revision Reviewer quantity one. Dr Robert Murphy The authors didn’t respond adequately to my concern about overfitting. By using the outcomes from cross vali dation to make selections, the anticipated accuracy in the strategy so configured is no longer the cross validation accuracy for that configuration. Simply just incorporating extra cross validation trials won’t ad dress the challenge.