Table 5.

An example for constructing string features

Input and processed documents and condidate string features	Details
Input document	The Three Human Syntrophin Genes Are Expressed in Diverse Tissues, Have Distinct Chromosomal Locations, and Each Bind to Dystrophin and Its Relatives
Processed document	the three human syntrophin genes are expressed in diverse tissues have distinct chromosomal locations and each bind to dystrophin and its relatives
Candidate string features	the thr
	he thre
	e three
	three h
	hree hu
	ree hum
	ee huma
	e human
	...

The length of substring is fixed to 7. The example document only has one sentence (the title of the document of PMID:8576247). A seven-character window moves along the sequential text. All characters are converted to lower case. Only alphabetical letters and the space character are processed. Punctuation is converted to the space character.