In reference to the patent: US5933819

I think this is not patentable, but does need protection.

Without knowing the details, applying a neural network algorithm to a problem is not even an idea, it is common course of the art. IF, authors made some modification to the NNA, it may deserve patenting, but not if any researcher in the same area will find the same modification - because it is obviously needed to adapt the algorithm to the problem.

I think this case should be treated like a Trade Secret if applied commercially, otherwise should be considered general research and made public.

I found the patent by simply searching for peptide NN. Does this mean I should not even TRY to apply the algorithm to the problem but instead should start paying rights to these authors if I use it commercially?

Cases like this one deserve a PRIZE in lieu of rights, but not a restrictive patent.


It has been stated already that this patent has lapsed, which is correct (see for example the google page, espacenet, USPTO). So it is now part of the public domain and if there is no other protection for this (yes, this could happen, should not though), everyone may use it.

Claim 1 states:

  1. A computer-implemented method for identifying relative binding motifs of peptide-like molecules, comprising the steps of: (a) training a computer-implemented artificial neural network (ANN) with input data characterizing a set of training peptide-like molecules, each of known sequence and binding affinity; (b) applying to the ANN input data characterizing at least one test peptide-like molecule, each of known sequence but unknown binding affinity; (c) analyzing each applied test peptide-like molecule using the ANN to generate a prediction of a relative binding affinity for each test peptide-like molecule, and outputting such prediction.

This is a really broad claim but only for peptide-like molecules, I am not sure why this would be abandoned, but maybe the market was too small. A claim like this would not get granted today (I'm sure), as it is obvious for everyone skilled in the art. But the patent is from 1997 (and maybe claims earlier priority, I didn't check). This was roughly 20 years ago, so maybe at that time, this was not obvious.


Pay it no mind since this patent is lapsed. You have freedom to practice any of its claims.

  • It would help to include some additional information here. How did you find that it was lapsed? Is there anything in the patent that may make it less broad than was originally suggested in the question? Not too much information is necessary, but since this question is about the scope of a granted patent (i.e. the answer isn't "yes, this is broad, and it probably won't be granted"), including some more information may help with the next similar patent the user, or another, finds. – Matthew Haugen Jul 18 '16 at 6:37

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.