Comment seven. I’m not absolutely sure if this subject is ideal for this computational biology centric journal. Maybe, this operate is extra ideal for publishing in journals like BMC. Response. We are thankful for this suggestion and we suppose this kind of operate is effectively suited for this journal. Quality of written English. Acceptable Comment 1. The authors designed many classifi cation models making use of an exhaustive set of chemical fingerprints for discriminating approved medicines from ex perimental medication and created these designs out there by way of a net server. Before years, a lot of newly accepted drug molecules are breaking the broadly accepted rule of five for drug likeness, this bettering and updating approaches for calculating drug likeness is an significant issue. How ever, I dont understand why authors designed designs that discriminate accredited medicines from experimental medication. Experimental medicines are molecules that are beneath investigation.
Staying experimental will not meet the com pound is just not drug like, so any model that supplier RAD001 discriminates approved from experimental does not have any value. The exhaustive technique could be important if designs have been de veloped to discriminate drug like, harmless compounds from probably toxic, non drug like compounds. Response. We absolutely agreed with all the reviewer comment. Whilst, scientific studies happen to be executed previously with focused towards the discrimination of drug like mol ecules from non drug like ones. But most of these had been based mostly over the use of commercial dataset like MDDR, CMC as drug like and ACD as non drug like dataset. Hence, availability within the dataset would be the major concern. In contrast, our method is an try to discriminate two closely re lated drug like molecules.
This can be an advance stage in drug design practice given that in spite of the in vitro drug VX222 VCH222 like properties, many medicines failed in clinical trial, As a result, it is actually crucial to discriminate these two lessons of molecules. That is the sole dataset that may be avai lable for public use and will be a wonderful asset for deve lopment of public domain servers. Top quality of written English. Not ideal for publication unless of course extensively edited Response. We are thankful to the reviewer for this comment. During the revised version, we have experimented with our very best to improve quality of English in revised version of manuscript. Hopefully, the revised model is going to be suit able for publication. Response for the Reviewers remarks just after revision Reviewer amount one. Dr Robert Murphy The authors didn’t reply adequately to my concern about overfitting. By using the results from cross vali dation to make decisions, the expected accuracy from the process so configured is no longer the cross validation accuracy for that configuration. Simply including additional cross validation trials will not ad dress the difficulty.