Was going through this paper, among multiple things that i did not understand, I came across this part:

Each amino acid residue of a single window was encoded into a unitary bit string of length 20, where a bit was set (value = 1) if its position in the string corresponds to the position of the amino acid residue and zero otherwise

Did not understand this line. Someone please explain what position they are talking about


The paper's description is poor, but they seem to be describing an encoding where each of 20 possible amino acids are associated with a position within a string of 20 bits, e.g. alanine with offset 0, cysteine with offset 1, etc. With that representation, one amino acid residue within a window is encoded by a string of 20 bits, 19 of them being 0 and the other a 1; the single 1 bit occurring in the place corresponding to the residue.

This interpretation is supported by the paper's citation of Qian N, Sejnowski TJ (1998) "Predicting the secondary structure of globular proteins using neural network models." J Mol Biol 202: 865–884. Qian's paper says:

Each group has 21 units, each unit representing 1 of the amino acids (or spacer). For a local encoding of the input sequence, 1 and only 1 input unit in each group, corresponding to the appropriate amino acid at each position, is given a value 1, and the rest are set to 0.

| improve this answer | |
  • 2
    $\begingroup$ +1 good answer although do not agree with "The paper's description is poor" part. The sentence quoted in the OP's question seems confusing but reading the entire paragraph in the paper puts things into context nicely. $\endgroup$ – ddiez Aug 12 '15 at 13:20
  • $\begingroup$ @ddiez, I did not mean to imply the paper was poor (or the surrounding paragraph), but that the quoted sentence did a poor job of describing the representation, which was essentially the sentence's only job. The surrounding paragraph I don't think makes up for that, although it does provide necessary context. The problem is that nowhere does it convey that there is a defined bit position within the bit string for each kind of amino acid. It says "corresponds to the position of the amino acid residue" where it would be better ... $\endgroup$ – mgkrebbs Aug 12 '15 at 22:57
  • $\begingroup$ (cont'd) if it said something like "is the one defined for that type of amino acid". Once one understands the bit-for-residue-type representation, one might be able read the sentence as communicating something like that, but if one has not yet thought of that approach, the sentence does not put the idea across well (IMO). $\endgroup$ – mgkrebbs Aug 12 '15 at 22:57

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.