409 lines
15 KiB
JSON
Executable File
409 lines
15 KiB
JSON
Executable File
{
|
||
"_comment": "自定义基因家族Pfam映射文件 - 此文件中的定义会覆盖内置映射",
|
||
"_version": "1.0",
|
||
"_last_updated": "2024-01-01",
|
||
|
||
"SPL": {
|
||
"pfam_ids": ["PF03110"],
|
||
"description": "SQUAMOSA promoter binding protein-like, SBP-box转录因子家族",
|
||
"category": "transcription_factor",
|
||
"aliases": ["SBP", "SBP-box", "SQUAMOSA", "SPL transcription factor"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 16,
|
||
"typical_count": "15-30 per genome",
|
||
"hmm_source": "Pfam",
|
||
"notes": "参与植物发育时相转变、花发育、叶片形态等"
|
||
},
|
||
|
||
"WRKY": {
|
||
"pfam_ids": ["PF03106"],
|
||
"description": "WRKY DNA-binding domain, 植物特有转录因子,参与胁迫响应和发育",
|
||
"category": "transcription_factor",
|
||
"aliases": ["WRKY transcription factor"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 74,
|
||
"typical_count": "70-130 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["Group I", "Group II", "Group III"],
|
||
"notes": "以保守的WRKYGQK序列命名,参与病原防御、衰老、发育等"
|
||
},
|
||
|
||
"MYB": {
|
||
"pfam_ids": ["PF00249", "PF13921"],
|
||
"description": "MYB DNA-binding domain, 大型转录因子家族",
|
||
"category": "transcription_factor",
|
||
"aliases": ["MYB transcription factor", "R2R3-MYB", "MYB-related"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 197,
|
||
"typical_count": "100-250 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["1R-MYB", "R2R3-MYB", "3R-MYB", "4R-MYB"],
|
||
"notes": "R2R3-MYB是植物中最大的亚家族,参与代谢、发育、胁迫响应"
|
||
},
|
||
|
||
"bHLH": {
|
||
"pfam_ids": ["PF00010"],
|
||
"description": "Basic helix-loop-helix domain, 参与光信号、激素响应和发育",
|
||
"category": "transcription_factor",
|
||
"aliases": ["basic helix-loop-helix", "HLH"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 162,
|
||
"typical_count": "150-200 per genome",
|
||
"hmm_source": "Pfam"
|
||
},
|
||
|
||
"NAC": {
|
||
"pfam_ids": ["PF02365"],
|
||
"description": "NAC domain (NAM, ATAF, CUC), 植物特有转录因子",
|
||
"category": "transcription_factor",
|
||
"aliases": ["NAM", "ATAF", "CUC", "NAC transcription factor"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 117,
|
||
"typical_count": "100-180 per genome",
|
||
"hmm_source": "Pfam",
|
||
"notes": "参与发育、衰老、胁迫响应、次生壁合成等"
|
||
},
|
||
|
||
"AP2_ERF": {
|
||
"pfam_ids": ["PF00847"],
|
||
"description": "AP2/ERF domain, 乙烯响应因子超家族",
|
||
"category": "transcription_factor",
|
||
"aliases": ["AP2", "ERF", "DREB", "CBF", "AP2/EREBP"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 147,
|
||
"typical_count": "120-200 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["AP2", "ERF", "DREB", "RAV", "Soloist"],
|
||
"notes": "DREB/CBF亚家族参与冷胁迫响应"
|
||
},
|
||
|
||
"NBS-LRR": {
|
||
"pfam_ids": ["PF00931", "PF13855"],
|
||
"description": "NBS-LRR抗病基因家族,植物先天免疫核心组分",
|
||
"category": "resistance",
|
||
"aliases": ["NLR", "R gene", "NB-LRR", "NBS", "R protein"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 178,
|
||
"typical_count": "100-500 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["TNL", "CNL", "RNL"],
|
||
"notes": "TNL含TIR结构域,CNL含CC结构域,数量在物种间差异大"
|
||
},
|
||
|
||
"MADS-box": {
|
||
"pfam_ids": ["PF00319", "PF01486"],
|
||
"description": "MADS-box转录因子,花发育ABC模型核心因子",
|
||
"category": "transcription_factor",
|
||
"aliases": ["MADS", "MIKC", "MADS-box transcription factor"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 107,
|
||
"typical_count": "70-150 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["Type I", "Type II (MIKC)"],
|
||
"notes": "MIKC型包含M、I、K、C四个结构域"
|
||
},
|
||
|
||
"HD-ZIP": {
|
||
"pfam_ids": ["PF00046", "PF02183"],
|
||
"description": "Homeodomain-leucine zipper, 参与发育模式建成",
|
||
"category": "transcription_factor",
|
||
"aliases": ["Homeodomain", "HD-Zip", "HOX"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 48,
|
||
"typical_count": "40-60 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["HD-ZIP I", "HD-ZIP II", "HD-ZIP III", "HD-ZIP IV"]
|
||
},
|
||
|
||
"GRAS": {
|
||
"pfam_ids": ["PF03514"],
|
||
"description": "GRAS domain转录因子,参与GA信号和发育",
|
||
"category": "transcription_factor",
|
||
"aliases": ["DELLA", "SCR", "SHR", "GRAS family"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 33,
|
||
"typical_count": "30-60 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["DELLA", "SCR", "SHR", "PAT1", "HAM", "LISCL", "SCL3"],
|
||
"notes": "DELLA蛋白是GA信号的负调控因子"
|
||
},
|
||
|
||
"bZIP": {
|
||
"pfam_ids": ["PF00170", "PF07716"],
|
||
"description": "Basic leucine zipper转录因子,参与ABA信号和胁迫响应",
|
||
"category": "transcription_factor",
|
||
"aliases": ["basic leucine zipper", "bZIP transcription factor"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 78,
|
||
"typical_count": "70-130 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["Group A", "Group B", "Group C", "Group D", "Group E", "Group F", "Group G", "Group H", "Group I", "Group S"]
|
||
},
|
||
|
||
"TCP": {
|
||
"pfam_ids": ["PF03634"],
|
||
"description": "TCP domain转录因子,参与细胞增殖和器官形态",
|
||
"category": "transcription_factor",
|
||
"aliases": ["TCP transcription factor", "TB1", "CYC", "PCF"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 24,
|
||
"typical_count": "20-30 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["Class I (PCF)", "Class II (CIN, CYC/TB1)"]
|
||
},
|
||
|
||
"ARF": {
|
||
"pfam_ids": ["PF06507", "PF02362"],
|
||
"description": "Auxin Response Factor, 生长素响应因子",
|
||
"category": "transcription_factor",
|
||
"aliases": ["Auxin response factor", "ARF transcription factor"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 23,
|
||
"typical_count": "20-40 per genome",
|
||
"hmm_source": "Pfam",
|
||
"notes": "与Aux/IAA蛋白互作调控生长素响应基因"
|
||
},
|
||
|
||
"HSF": {
|
||
"pfam_ids": ["PF00447"],
|
||
"description": "Heat shock transcription factor, 热激转录因子",
|
||
"category": "transcription_factor",
|
||
"aliases": ["Heat shock factor", "HSF transcription factor"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 21,
|
||
"typical_count": "20-30 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["Class A", "Class B", "Class C"]
|
||
},
|
||
|
||
"Dof": {
|
||
"pfam_ids": ["PF02701"],
|
||
"description": "Dof (DNA binding with one finger) 转录因子",
|
||
"category": "transcription_factor",
|
||
"aliases": ["Dof transcription factor", "Dof zinc finger"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 36,
|
||
"typical_count": "30-50 per genome",
|
||
"hmm_source": "Pfam"
|
||
},
|
||
|
||
"C2H2_ZF": {
|
||
"pfam_ids": ["PF00096", "PF13912"],
|
||
"description": "C2H2型锌指蛋白,经典锌指转录因子",
|
||
"category": "transcription_factor",
|
||
"aliases": ["C2H2", "C2H2 zinc finger", "Zinc finger", "ZFP"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 211,
|
||
"typical_count": "150-300 per genome",
|
||
"hmm_source": "Pfam"
|
||
},
|
||
|
||
"GATA": {
|
||
"pfam_ids": ["PF00320"],
|
||
"description": "GATA型锌指转录因子,参与氮代谢和光响应",
|
||
"category": "transcription_factor",
|
||
"aliases": ["GATA zinc finger", "GATA transcription factor"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 30,
|
||
"typical_count": "25-40 per genome",
|
||
"hmm_source": "Pfam"
|
||
},
|
||
|
||
"Trihelix": {
|
||
"pfam_ids": ["PF13837", "PF10545"],
|
||
"description": "Trihelix (GT因子) 转录因子",
|
||
"category": "transcription_factor",
|
||
"aliases": ["GT factor", "GT element binding protein"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 30,
|
||
"typical_count": "25-40 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["GT-1", "GT-2", "GTγ", "SH4", "SIP1"]
|
||
},
|
||
|
||
"LRR-RLK": {
|
||
"pfam_ids": ["PF00560", "PF00069", "PF07714"],
|
||
"description": "LRR受体激酶,植物最大的受体激酶家族",
|
||
"category": "kinase",
|
||
"aliases": ["LRR receptor kinase", "LRR-RK", "Leucine-rich repeat receptor kinase"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 235,
|
||
"typical_count": "200-400 per genome",
|
||
"hmm_source": "Pfam",
|
||
"notes": "包括CLV1、BAK1、FLS2等重要受体"
|
||
},
|
||
|
||
"MAPK": {
|
||
"pfam_ids": ["PF00069"],
|
||
"description": "Mitogen-activated protein kinase, 丝裂原活化蛋白激酶",
|
||
"category": "kinase",
|
||
"aliases": ["MPK", "MAP kinase"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 20,
|
||
"typical_count": "15-25 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["Group A", "Group B", "Group C", "Group D"]
|
||
},
|
||
|
||
"CDPK": {
|
||
"pfam_ids": ["PF00069", "PF13499", "PF00036"],
|
||
"description": "Calcium-dependent protein kinase, 钙依赖蛋白激酶",
|
||
"category": "kinase",
|
||
"aliases": ["CPK", "Calcium-dependent kinase"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 34,
|
||
"typical_count": "25-40 per genome",
|
||
"hmm_source": "Pfam",
|
||
"notes": "含有EF-hand钙结合结构域"
|
||
},
|
||
|
||
"SnRK": {
|
||
"pfam_ids": ["PF00069", "PF00571"],
|
||
"description": "SNF1-related protein kinase, 蔗糖非发酵相关激酶",
|
||
"category": "kinase",
|
||
"aliases": ["SnRK1", "SnRK2", "SnRK3", "CIPK"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 38,
|
||
"typical_count": "35-50 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["SnRK1", "SnRK2", "SnRK3/CIPK"],
|
||
"notes": "SnRK2参与ABA信号,SnRK3/CIPK与CBL互作"
|
||
},
|
||
|
||
"WAK": {
|
||
"pfam_ids": ["PF00069", "PF13947", "PF08488"],
|
||
"description": "Wall-associated kinase, 细胞壁相关激酶",
|
||
"category": "kinase",
|
||
"aliases": ["Wall-associated receptor kinase", "WAKL"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 26,
|
||
"typical_count": "20-100 per genome",
|
||
"hmm_source": "Pfam"
|
||
},
|
||
|
||
"Aquaporin": {
|
||
"pfam_ids": ["PF00230"],
|
||
"description": "水通道蛋白/主要内在蛋白家族",
|
||
"category": "other",
|
||
"aliases": ["MIP", "PIP", "TIP", "NIP", "SIP", "XIP", "Major intrinsic protein"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 35,
|
||
"typical_count": "30-70 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["PIP", "TIP", "NIP", "SIP", "XIP"],
|
||
"notes": "PIP定位质膜,TIP定位液泡膜"
|
||
},
|
||
|
||
"HSP70": {
|
||
"pfam_ids": ["PF00012"],
|
||
"description": "Heat shock protein 70, 分子伴侣",
|
||
"category": "other",
|
||
"aliases": ["HSP70", "DnaK", "BiP", "Heat shock 70"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 18,
|
||
"typical_count": "15-25 per genome",
|
||
"hmm_source": "Pfam"
|
||
},
|
||
|
||
"HSP90": {
|
||
"pfam_ids": ["PF00183", "PF02518"],
|
||
"description": "Heat shock protein 90, 分子伴侣",
|
||
"category": "other",
|
||
"aliases": ["HSP90", "Heat shock 90"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 7,
|
||
"typical_count": "5-10 per genome",
|
||
"hmm_source": "Pfam"
|
||
},
|
||
|
||
"sHSP": {
|
||
"pfam_ids": ["PF00011"],
|
||
"description": "Small heat shock protein, 小分子热激蛋白",
|
||
"category": "other",
|
||
"aliases": ["HSP20", "small HSP", "alpha-crystallin"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 19,
|
||
"typical_count": "15-30 per genome",
|
||
"hmm_source": "Pfam"
|
||
},
|
||
|
||
"LEA": {
|
||
"pfam_ids": ["PF03760", "PF03168", "PF02987", "PF00257", "PF04927", "PF00477"],
|
||
"description": "Late embryogenesis abundant protein, 胚胎发育晚期丰富蛋白",
|
||
"category": "other",
|
||
"aliases": ["LEA protein", "Dehydrin"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 51,
|
||
"typical_count": "40-100 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["LEA_1", "LEA_2", "LEA_3", "LEA_4", "LEA_5", "Dehydrin"],
|
||
"notes": "参与干旱、低温等非生物胁迫响应"
|
||
},
|
||
|
||
"GST": {
|
||
"pfam_ids": ["PF02798", "PF00043", "PF13417", "PF13410"],
|
||
"description": "Glutathione S-transferase, 谷胱甘肽S-转移酶",
|
||
"category": "other",
|
||
"aliases": ["Glutathione transferase"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 55,
|
||
"typical_count": "50-100 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["Phi", "Tau", "Theta", "Zeta", "Lambda", "DHAR", "EF1Bγ"],
|
||
"notes": "参与解毒、次生代谢、胁迫响应"
|
||
},
|
||
|
||
"Cytochrome_P450": {
|
||
"pfam_ids": ["PF00067"],
|
||
"description": "Cytochrome P450, 细胞色素P450单加氧酶",
|
||
"category": "other",
|
||
"aliases": ["CYP", "P450", "Cytochrome P450 monooxygenase"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 272,
|
||
"typical_count": "200-500 per genome",
|
||
"hmm_source": "Pfam",
|
||
"notes": "植物中最大的酶家族之一,参与次生代谢"
|
||
},
|
||
|
||
"ABC_transporter": {
|
||
"pfam_ids": ["PF00005", "PF00664", "PF01061"],
|
||
"description": "ABC transporter, ATP结合盒转运蛋白",
|
||
"category": "other",
|
||
"aliases": ["ABC transporter", "ATP-binding cassette"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 130,
|
||
"typical_count": "100-200 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["ABCA", "ABCB", "ABCC", "ABCD", "ABCE", "ABCF", "ABCG", "ABCI"]
|
||
},
|
||
|
||
"Expansin": {
|
||
"pfam_ids": ["PF03330", "PF01357"],
|
||
"description": "Expansin, 扩展蛋白,参与细胞壁松弛",
|
||
"category": "other",
|
||
"aliases": ["EXPA", "EXPB", "EXLA", "EXLB"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 36,
|
||
"typical_count": "30-60 per genome",
|
||
"hmm_source": "Pfam",
|
||
"subfamilies": ["α-expansin (EXPA)", "β-expansin (EXPB)", "expansin-like A (EXLA)", "expansin-like B (EXLB)"]
|
||
},
|
||
|
||
"Peroxidase": {
|
||
"pfam_ids": ["PF00141"],
|
||
"description": "Class III peroxidase, 过氧化物酶",
|
||
"category": "other",
|
||
"aliases": ["POD", "PRX", "POX", "Class III peroxidase"],
|
||
"reference_species": "Arabidopsis thaliana",
|
||
"reference_count": 73,
|
||
"typical_count": "70-150 per genome",
|
||
"hmm_source": "Pfam",
|
||
"notes": "参与木质素合成、ROS代谢、防御响应"
|
||
},
|
||
|
||
"Laccase": {
|
||
"pfam_ids": ["PF00394", "PF07731", "PF07732"],
|
||
"description": "Laccase, 漆酶,参与木质素聚合",
|
||
"category": "other",
|
||
"aliases": ["LAC", "Laccase/Diphenol oxidase"],
|