Aligning　protein　sequences　using　a　score　matrix　has　became　a　routine　but　valuable　method　in　modem　biological　research.　However,　alignment　in　the　＇twilight　zone＇　remains　an　open　issue.　It　is　feasible　and　necessary　to　construct　a　new　score　matrix　as　more　protein　structures　are　resolved.　Three　structural　class-specific　score　matrices　(all-alpha,　all-beta　and　alpha/beta)　were　constructed　based　on　the　structure　alignment　of　low　identity　proteins　of　the　corresponding　structural　classes.　The　class-specific　score　matrices　were　significantly　better　than　a　structure-derived　matrix　(HSDM)　and　three　other　generalized　matrices　(BLOSUM30,　BLOSUM60　and　Gonnet250)　in　alignment　performance　tests.　The　optimized　gap　penalties　presented　here　also　promote　alignment　performance.　The　results　indicate　that　different　protein　classes　have　distinct　amino　acid　substitution　patterns,　and　an　amino　acid　score　matrix　should　be　constructed　based　on　different　structural　classes.　The　class-specific　score　matrices　could　also　be　used　in　profile　construction　to　improve　homology　detection.