Feature subset size	# features present in both datasets	List of features present in both datasets
5	4 (80%)	salmonella, speci, shigella, campylobact
10	7 (70%)	speci, health, isol, group, salmonella, shigella, campylobact
15	12 (80%)	speci, indiana, campylobact, confirm, health, isol, group, suscept, typhi, salmonella, shigella, call
20	14 (70%)	chslb, speci, indiana, shigella, campylobact, confirm, health, isol, group, suscept, depart, salmonella, typhi, call
50	35 (70%)	sct, speci, non, due, isol, suscept, typhi, coli, report, chslb, call, indiana, cultur, confirm, diseas, issu, gener, azithromycin, sent, health, gastroenter, without, self, progress, depart, salmonella, stool, campylobact, enter, medic, test, final, group, shigella, tofmass
100	79 (79%)	perform, sct, present, speci, characterist, non, laboratori, due, isol, result, pathogen, infect, suscept, typhi, coli, identifi, report, chslb, serogroup, call, indiana, cultur, thi, lab, confirm, enzym, sourc, aerob, diseas, growth, issu, drug, gener, azithromycin, moder, maldi, specimen, sent, gastroenter, health, without, underli, serotyp, spectrometri, routin, self, toxin, numer, aeromona, follow, salmonella, progress, depart, stool, tofmass, ser, enter, campylobact, normal, develop, shiga, medic, patient, salsp, determin, test, mani, choic, mass, final, group, usual, see, board, date, shigella, access