*********************************************************************************** This is the publicly released version of the Holland's dataset. The reference for this dataset is: T. Holalnd, S. Veretnik, I.N. Shindyalov, and P.E. Bourne. A benchmark for domain assignment from protein 3-dimensional structure and its application. J. Mol. Bio. 361:562-590, 2006. The dataset is used in Dr. Jianlin Cheng's paper: J. Cheng. DOMAC: An Accurate, Hybrid Protein Domain Prediction Server. Nucleic Acids Research. In press, 2007. Note: The index of the first residue of some proteins does not start from 1. So when you use this domain defintion with the dataset created by Cheng 2007, you need to adjust the indices of the domain definition. If the index of the first residue is i, the position of a domain boundary should be subtracted by i - 1. ************************************************************************************ 1fha_ 1 (5-184) 1csga 1 (5-124) 1rcb_ 1 (1-129) 1utg_ 1 (1-70) 4icb_ 1 (0-75) 1myt_ 1 (5-153) 1mrra 1 (1-340) 4cp4_ 1 (10-414) 1wrpr 1 (4-105) 1c5a_ 1 (1-66) 1mup_ 1 (5-161) 2por_ 1 (1-301) 6ebxa 1 (1-62) 1hcc_ 1 (1-59) 1bds_ 1 (1-43) 1btc_ 1 (5-495) 1cad_ 1 (1-53) 1huma 1 (1-69) 1bova 1 (1-69) 1hiva 1 (1-99) 1byh_ 1 (1-214) 1tnra 1 (28-171) 2pcdm 1 (301-536) 2madl 1 (7-130) 1mdaa 1 (3-105) 1ttba 1 (1-127) 1vfab 1 (1-116) 4htci 1 (1-65) 5nn9_ 1 (82-468) 1fxia 1 (1-96) 2msba 1 (109-220) 1caj_ 1 (3-261) 1fbaa 1 (0-363) 1xima 1 (3-394) 3teci 1 (8-70) 1gps_ 1 (1-47) 1chc_ 1 (1-68) 1gdc_ 1 (1-72) 1eaf_ 1 (395-637) 1cgii 1 (1-56) 1aps_ 1 (1-98) 1fdn_ 1 (1-55) 1aba_ 1 (1-87) 3chy_ 1 (2-129) 1ula_ 1 (1-289) 5p21_ 1 (1-166) 2fcr_ 1 (1-173) 1ovb_ 1 (94-248) 1rvea 1 (2-245) 1dnka 1 (1-260) 2ech_ 1 (1-49) 1fc2c 1 (124-167) 4pti_ 1 (1-58) 2pf2 1 (64-145) 1au7a 2 (5-76)(103-159) 1aua_ 2 (4-86)(87-299) 6paxa 2 (2-69)(70-118) 2cgpa 2 (138-206)(9-137) 1qnta 2 (86-176)(6-85) 1boa_ 2 (372-450)(164-371; 451-474) 1b4aa 2 (9-67)(79-148) 1crxa 2 (20-130)(132-331) 1ffua 2 (81-156)(3-76) 1bc5a 2 (16-90)(91-284) 1qlab 2 (107-125; 137-239)(1-106) 1eza_ 2 (21-146)(3-20; 147-249) 1ytfd 2 (5-57)(58-119) 1grj_ 2 (2-75)(76-158) 1gdd_ 2 (62-180)(9-61; 181-354) 1vola 2 (113-209)(210-315) 1qmda 2 (1-250)(251-370) 5eau_ 2 (21-60; 221-547)(61-220) 3hdha 2 (211-297)(12-207) 1ffh_ 2 (2-90)(91-281) 1dg3a 2 (284-583)(6-283) 1cuna 2 (7-109)(110-211) 1mrob 2 (2-44; 192-443)(45-191) 1eqfa 2 (1359-1370; 1496-1625)(1371-1495) 1dvpa 2 (2-141)(154-219) 3tf4a 2 (1-454)(458-604) 1urk_ 2 (6-49)(50-135) 1vvc_ 2 (1-58)(59-118) 1fbl_ 2 (275-465)(100-273) 1sat_ 2 (4-17; 250-471)(18-249) 1yua_ 2 (65-122)(1-64) 1lcka 2 (63-121)(122-226) 1eif_ 2 (4-73)(74-133) 1c0ma 2 (216-269)(49-215) 2g3pa 2 (2-101; 206-215)(102-205) 1bkb_ 2 (4-74)(75-139) 1cne_ 2 (11-116)(117-269) 1qdna 2 (1-83)(84-201) 1e2va 2 (171-230)(1-170; 231-251) 1prtb 2 (90-199)(4-89) 1bbwa 2 (14-153)(161-498) 1dfqa 2 (875-1109)(1110-1315) 1prs_ 2 (1-88)(89-173) 1duya 2 (182-270)(1-181) 1qnia 2 (461-580)(10-460) 1qlfa 2 (182-272)(1-181) 1fmta 2 (209-313)(1-208) 1b24a 2 (7-101)(105-178) 1bp1_ 2 (12-191)(1-11; 192-456) 1qu6a 2 (1-85)(104-179) 1egaa 2 (189-294)(4-184) 1pcza 2 (5-15; 103-184)(16-102) 1qmha 2 (186-276)(5-182; 277-337) 1tbrs 2 (1-51)(52-103) 3sxla 2 (127-197)(206-260) 1qd1a 2 (182-326)(2-181) 1mla_ 2 (125-197)(3-124; 198-307) 1l9fa 2 (60-145; 219-321)(1-59; 149-218; 326-385) 1pdz_ 2 (127-433)(1-126) 1ddza 2 (84-139; 394-564)(140-307; 339-393) 1e1la 2 (6-44; 61-106; 332-460)(45-60; 107-331) 1gph2 2 (260-305; 328-379; 391-424)(1-259; 380-390; 425-460) 1jaw_ 2 (1-173)(174-439) 1civa 2 (40-192)(193-367) 1bpm_ 2 (1-165)(166-483) 1vdc_ 2 (117-244)(1-116; 245-315) 1ush_ 2 (26-362)(363-550) 1pspa 2 (1-59; 100-106)(60-99) 1whe_ 2 (47-86)(1-46) 1bi3a 3 (4-74)(75-140)(148-223) 1e39a 3 (1-99)(103-359; 506-568)(365-502) 1skye 3 (354-469)(1-82)(84-352) 1djza 3 (210-292)(626-756)(293-625) 2cbla 3 (176-264)(47-175)(265-350) 1cqxa 3 (1-150)(151-261)(262-403) 1hjp_ 3 (159-202)(67-158)(1-66) 1chua 3 (423-524)(2-243; 350-422)(244-349) 1ciy_ 3 (33-253)(254-265; 462-608)(266-461) 1dcea 3 (2-241; 353-429)(242-344)(431-566) 1igra 3 (224-299)(1-184)(300-478) 1d0gt 3 (62-101)(102-130)(21-61) 1ksia 3 (6-101)(102-197)(231-646) 1pkya 3 (70-168)(2-69; 169-335)(336-469) 1tuia 3 (311-404)(216-307)(9-213) 1kit_ 3 (25-81; 94-213)(354-540)(214-353; 541-781) 1iray 3 (201-311)(3-94)(95-200) 1bhga 3 (225-328)(22-224)(329-631) 1ctn_ 3 (24-130)(443-518)(131-442; 519-561) 1qm4a 3 (17-25; 153-253)(130-152; 291-395)(26-129; 254-290) 1aoga 3 (361-472)(166-286)(4-165; 287-360) 2shpa 3 (110-215)(2-109)(216-525) 1fohb 3 (81-107; 238-342; 398-452)(453-661)(1-79; 110-237; 343-388) 1a8y_ 3 (3-126)(127-228)(229-347) 1tdj_ 3 (65-156)(5-64; 157-319)(338-514) 1cs6a 4 (210-298)(7-104)(299-388)(105-209) 1qba_ 4 (28-169)(820-885)(336-819)(209-335) 1dgkn 4 (54-222; 446-463)(513-670; 894-913)(16-53; 223-445)(671-892; 481-512) 1wgta 4 (1-42)(43-85)(129-171)(86-128) 1fnma 5 (433-483)(303-400)(603-685)(484-602)(6-286) 1cwva 5 (503-595)(693-794)(596-692)(796-886)(887-986) 2glia 5 (168-197)(136-167)(198-228)(229-257)(103-135) 1bxrc 6 (403-555)(128-402)(678-935)(2-127)(556-676)(936-1073)