"sequence_id","alias","species","description","type"
"AT1G01250","No alias","Arabidopsis thaliana","Integrase-type DNA-binding superfamily protein","protein_coding"
"AT1G02630","No alias","Arabidopsis thaliana","Nucleoside transporter family protein","protein_coding"
"AT1G06990","No alias","Arabidopsis thaliana","GDSL-like Lipase/Acylhydrolase superfamily protein","protein_coding"
"AT1G07450","No alias","Arabidopsis thaliana","NAD(P)-binding Rossmann-fold superfamily protein","protein_coding"
"AT1G07485","No alias","Arabidopsis thaliana","unknown protein; FUNCTIONS IN: molecular_function unknown; INVOLVED IN: biological_process unknown; LOCATED IN: cellular_component unknown; EXPRESSED IN: shoot apex, embryo, leaf whorl, pedicel; EXPRESSED DURING: 4 anthesis, D bilateral stage; Has 5 Blast hits to 5 proteins in 3 species: Archae - 0; Bacteria - 0; Metazoa - 0; Fungi - 0; Plants - 5; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT1G07490","DVL9","Arabidopsis thaliana","ROTUNDIFOLIA like 3","protein_coding"
"AT1G10180","No alias","Arabidopsis thaliana","BEST Arabidopsis thaliana protein match is: exocyst complex component 84B (TAIR:AT5G49830.1); Has 132 Blast hits to 132 proteins in 25 species: Archae - 0; Bacteria - 0; Metazoa - 7; Fungi - 0; Plants - 117; Viruses - 0; Other Eukaryotes - 8 (source: NCBI BLink).","protein_coding"
"AT1G10460","GLP7","Arabidopsis thaliana","germin-like protein 7","protein_coding"
"AT1G11840","ATGLX1","Arabidopsis thaliana","glyoxalase I homolog","protein_coding"
"AT1G12130","No alias","Arabidopsis thaliana","Flavin-binding monooxygenase family protein","protein_coding"
"AT1G12860","SCRM2","Arabidopsis thaliana","basic helix-loop-helix (bHLH) DNA-binding superfamily protein","protein_coding"
"AT1G15760","No alias","Arabidopsis thaliana","Sterile alpha motif (SAM) domain-containing protein","protein_coding"
"AT1G20575","No alias","Arabidopsis thaliana","Nucleotide-diphospho-sugar transferases superfamily protein","protein_coding"
"AT1G21090","No alias","Arabidopsis thaliana","Cupredoxin superfamily protein","protein_coding"
"AT1G22160","No alias","Arabidopsis thaliana","Protein of unknown function (DUF581)","protein_coding"
"AT1G22790","No alias","Arabidopsis thaliana","unknown protein; FUNCTIONS IN: molecular_function unknown; INVOLVED IN: biological_process unknown; LOCATED IN: plasma membrane; EXPRESSED IN: 22 plant structures; EXPRESSED DURING: 13 growth stages; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT1G34010.1); Has 67 Blast hits to 67 proteins in 12 species: Archae - 0; Bacteria - 0; Metazoa - 0; Fungi - 0; Plants - 67; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT1G23000","No alias","Arabidopsis thaliana","Heavy metal transport/detoxification superfamily protein","protein_coding"
"AT1G24050","No alias","Arabidopsis thaliana","RNA-processing, Lsm domain","protein_coding"
"AT1G26560","BGLU40","Arabidopsis thaliana","beta glucosidase 40","protein_coding"
"AT1G27045","No alias","Arabidopsis thaliana","Homeobox-leucine zipper protein family","protein_coding"
"AT1G27360","SPL11","Arabidopsis thaliana","squamosa promoter-like 11","protein_coding"
"AT1G27450","ATAPT1","Arabidopsis thaliana","adenine phosphoribosyl transferase 1","protein_coding"
"AT1G28290","AGP31","Arabidopsis thaliana","arabinogalactan protein 31","protein_coding"
"AT1G29980","No alias","Arabidopsis thaliana","Protein of unknown function, DUF642","protein_coding"
"AT1G31490","No alias","Arabidopsis thaliana","HXXXD-type acyl-transferase family protein","protein_coding"
"AT1G46264","HSFB4","Arabidopsis thaliana","heat shock transcription factor  B4","protein_coding"
"AT1G49110","No alias","Arabidopsis thaliana","unknown protein; Has 5 Blast hits to 5 proteins in 2 species: Archae - 0; Bacteria - 0; Metazoa - 0; Fungi - 0; Plants - 5; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT1G51355","No alias","Arabidopsis thaliana","unknown protein; FUNCTIONS IN: molecular_function unknown; INVOLVED IN: biological_process unknown; LOCATED IN: chloroplast; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT3G20898.1); Has 52 Blast hits to 52 proteins in 9 species: Archae - 0; Bacteria - 0; Metazoa - 2; Fungi - 0; Plants - 50; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT1G56680","No alias","Arabidopsis thaliana","Chitinase family protein","protein_coding"
"AT1G57750","MAH1","Arabidopsis thaliana","cytochrome P450, family 96, subfamily A, polypeptide 15","protein_coding"
"AT1G64080","No alias","Arabidopsis thaliana","unknown protein; FUNCTIONS IN: molecular_function unknown; INVOLVED IN: biological_process unknown; LOCATED IN: plasma membrane; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT5G52870.1); Has 1546 Blast hits to 738 proteins in 176 species: Archae - 0; Bacteria - 143; Metazoa - 278; Fungi - 131; Plants - 95; Viruses - 4; Other Eukaryotes - 895 (source: NCBI BLink).","protein_coding"
"AT1G64130","No alias","Arabidopsis thaliana","Polyketide cyclase/dehydrase and lipid transport superfamily protein","protein_coding"
"AT1G65480","FT","Arabidopsis thaliana","PEBP (phosphatidylethanolamine-binding protein) family protein","protein_coding"
"AT1G67630","POLA2","Arabidopsis thaliana","DNA polymerase alpha 2","protein_coding"
"AT1G68430","No alias","Arabidopsis thaliana","unknown protein; FUNCTIONS IN: molecular_function unknown; INVOLVED IN: biological_process unknown; LOCATED IN: chloroplast; EXPRESSED IN: 21 plant structures; EXPRESSED DURING: 13 growth stages; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT1G66890.1); Has 35 Blast hits to 35 proteins in 6 species: Archae - 0; Bacteria - 0; Metazoa - 0; Fungi - 0; Plants - 35; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT1G70480","No alias","Arabidopsis thaliana","Domain of unknown function (DUF220)","protein_coding"
"AT1G71750","HGPT","Arabidopsis thaliana","Hypoxanthine-guanine phosphoribosyltransferase","protein_coding"
"AT1G72110","No alias","Arabidopsis thaliana","O-acyltransferase (WSD1-like) family protein","protein_coding"
"AT1G73380","No alias","Arabidopsis thaliana","unknown protein; CONTAINS InterPro DOMAIN/s: Protein of unknown function DUF1308 (InterPro:IPR010733); Has 162 Blast hits to 160 proteins in 67 species: Archae - 0; Bacteria - 2; Metazoa - 120; Fungi - 0; Plants - 34; Viruses - 0; Other Eukaryotes - 6 (source: NCBI BLink).","protein_coding"
"AT1G75580","No alias","Arabidopsis thaliana","SAUR-like auxin-responsive protein family","protein_coding"
"AT1G75670","No alias","Arabidopsis thaliana","DNA-directed RNA polymerases","protein_coding"
"AT1G75900","No alias","Arabidopsis thaliana","GDSL-like Lipase/Acylhydrolase superfamily protein","protein_coding"
"AT1G76060","EMB1793","Arabidopsis thaliana","LYR family of Fe/S cluster biogenesis protein","protein_coding"
"AT1G80050","APT2","Arabidopsis thaliana","adenine phosphoribosyl transferase 2","protein_coding"
"AT2G01220","No alias","Arabidopsis thaliana","Nucleotidylyl transferase superfamily protein","protein_coding"
"AT2G01420","ATPIN4","Arabidopsis thaliana","Auxin efflux carrier family protein","protein_coding"
"AT2G03505","No alias","Arabidopsis thaliana","Carbohydrate-binding X8 domain superfamily protein","protein_coding"
"AT2G04025","RGF3","Arabidopsis thaliana","root meristem growth factor 3 (RGF3); FUNCTIONS IN: molecular_function unknown; INVOLVED IN: regulation of root meristem growth, positive regulation of gene expression; LOCATED IN: endomembrane system; EXPRESSED IN: stem, root, carpel; EXPRESSED DURING: 4 anthesis; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT1G13620.1); Has 35333 Blast hits to 34131 proteins in 2444 species: Archae - 798; Bacteria - 22429; Metazoa - 974; Fungi - 991; Plants - 531; Viruses - 0; Other Eukaryotes - 9610 (source: NCBI BLink).","protein_coding"
"AT2G16600","ROC3","Arabidopsis thaliana","rotamase CYP 3","protein_coding"
"AT2G19410","No alias","Arabidopsis thaliana","U-box domain-containing protein kinase family protein","protein_coding"
"AT2G21050","LAX2","Arabidopsis thaliana","like AUXIN RESISTANT 2","protein_coding"
"AT2G21195","No alias","Arabidopsis thaliana","unknown protein; Has 28 Blast hits to 28 proteins in 11 species: Archae - 0; Bacteria - 0; Metazoa - 0; Fungi - 0; Plants - 28; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT2G21870","MGP1","Arabidopsis thaliana","copper ion binding;cobalt ion binding;zinc ion binding","protein_coding"
"AT2G23050","NPY4","Arabidopsis thaliana","Phototropic-responsive NPH3 family protein","protein_coding"
"AT2G24350","No alias","Arabidopsis thaliana","RNA binding (RRM/RBD/RNP motifs) family protein","protein_coding"
"AT2G24440","No alias","Arabidopsis thaliana","selenium binding","protein_coding"
"AT2G25270","No alias","Arabidopsis thaliana","unknown protein; LOCATED IN: plasma membrane; EXPRESSED IN: 18 plant structures; EXPRESSED DURING: 13 growth stages; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT2G12400.1); Has 35333 Blast hits to 34131 proteins in 2444 species: Archae - 798; Bacteria - 22429; Metazoa - 974; Fungi - 991; Plants - 531; Viruses - 0; Other Eukaryotes - 9610 (source: NCBI BLink).","protein_coding"
"AT2G27020","PAG1","Arabidopsis thaliana","20S proteasome alpha subunit G1","protein_coding"
"AT2G27240","No alias","Arabidopsis thaliana","Aluminium activated malate transporter family protein","protein_coding"
"AT2G28790","No alias","Arabidopsis thaliana","Pathogenesis-related thaumatin superfamily protein","protein_coding"
"AT2G30432","TCL1","Arabidopsis thaliana","Homeodomain-like superfamily protein","protein_coding"
"AT2G30860","GSTF9","Arabidopsis thaliana","glutathione S-transferase PHI 9","protein_coding"
"AT2G32100","OFP16","Arabidopsis thaliana","ovate family protein 16","protein_coding"
"AT2G32280","No alias","Arabidopsis thaliana","Protein of unknown function (DUF1218)","protein_coding"
"AT2G35320","ATEYA","Arabidopsis thaliana","EYES ABSENT homolog","protein_coding"
"AT2G38970","No alias","Arabidopsis thaliana","Zinc finger (C3HC4-type RING finger) family protein","protein_coding"
"AT2G41440","No alias","Arabidopsis thaliana","unknown protein; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT2G41470.1); Has 30201 Blast hits to 17322 proteins in 780 species: Archae - 12; Bacteria - 1396; Metazoa - 17338; Fungi - 3422; Plants - 5037; Viruses - 0; Other Eukaryotes - 2996 (source: NCBI BLink).","protein_coding"
"AT2G41990","No alias","Arabidopsis thaliana","CONTAINS InterPro DOMAIN/s: Late embryogenesis abundant protein, group 2 (InterPro:IPR004864); BEST Arabidopsis thaliana protein match is: Late embryogenesis abundant (LEA) hydroxyproline-rich glycoprotein family (TAIR:AT4G35170.1); Has 172 Blast hits to 168 proteins in 15 species: Archae - 0; Bacteria - 0; Metazoa - 0; Fungi - 0; Plants - 172; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT2G45720","No alias","Arabidopsis thaliana","ARM repeat superfamily protein","protein_coding"
"AT2G46850","No alias","Arabidopsis thaliana","Protein kinase superfamily protein","protein_coding"
"AT2G47690","No alias","Arabidopsis thaliana","NADH-ubiquinone oxidoreductase-related","protein_coding"
"AT3G01840","No alias","Arabidopsis thaliana","Protein kinase superfamily protein","protein_coding"
"AT3G05190","No alias","Arabidopsis thaliana","D-aminoacid aminotransferase-like PLP-dependent enzymes superfamily protein","protein_coding"
"AT3G05740","RECQI1","Arabidopsis thaliana","RECQ helicase l1","protein_coding"
"AT3G06840","No alias","Arabidopsis thaliana","unknown protein; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT5G49170.1); Has 33 Blast hits to 33 proteins in 9 species: Archae - 0; Bacteria - 0; Metazoa - 0; Fungi - 0; Plants - 33; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT3G10210","No alias","Arabidopsis thaliana","SEC14 cytosolic factor family protein / phosphoglyceride transfer family protein","protein_coding"
"AT3G11470","No alias","Arabidopsis thaliana","4'-phosphopantetheinyl transferase superfamily","protein_coding"
"AT3G11680","No alias","Arabidopsis thaliana","Aluminium activated malate transporter family protein","protein_coding"
"AT3G20390","No alias","Arabidopsis thaliana","endoribonuclease L-PSP family protein","protein_coding"
"AT3G20557","No alias","Arabidopsis thaliana","unknown protein; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT1G50930.1); Has 35333 Blast hits to 34131 proteins in 2444 species: Archae - 798; Bacteria - 22429; Metazoa - 974; Fungi - 991; Plants - 531; Viruses - 0; Other Eukaryotes - 9610 (source: NCBI BLink).","protein_coding"
"AT3G20840","PLT1","Arabidopsis thaliana","Integrase-type DNA-binding superfamily protein","protein_coding"
"AT3G20880","WIP4","Arabidopsis thaliana","WIP domain protein 4","protein_coding"
"AT3G23570","No alias","Arabidopsis thaliana","alpha/beta-Hydrolases superfamily protein","protein_coding"
"AT3G26120","TEL1","Arabidopsis thaliana","terminal EAR1-like 1","protein_coding"
"AT3G29300","No alias","Arabidopsis thaliana","unknown protein; FUNCTIONS IN: molecular_function unknown; INVOLVED IN: biological_process unknown; LOCATED IN: endomembrane system; EXPRESSED IN: 12 plant structures; EXPRESSED DURING: 6 growth stages; Has 451 Blast hits to 349 proteins in 91 species: Archae - 0; Bacteria - 85; Metazoa - 81; Fungi - 88; Plants - 18; Viruses - 1; Other Eukaryotes - 178 (source: NCBI BLink).","protein_coding"
"AT3G50340","No alias","Arabidopsis thaliana","unknown protein; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT5G67020.1); Has 128 Blast hits to 128 proteins in 39 species: Archae - 0; Bacteria - 46; Metazoa - 0; Fungi - 3; Plants - 76; Viruses - 0; Other Eukaryotes - 3 (source: NCBI BLink).","protein_coding"
"AT3G54970","No alias","Arabidopsis thaliana","D-aminoacid aminotransferase-like PLP-dependent enzymes superfamily protein","protein_coding"
"AT3G55550","No alias","Arabidopsis thaliana","Concanavalin A-like lectin protein kinase family protein","protein_coding"
"AT3G55710","No alias","Arabidopsis thaliana","UDP-Glycosyltransferase superfamily protein","protein_coding"
"AT3G57670","WIP2","Arabidopsis thaliana","C2H2-type zinc finger family protein","protein_coding"
"AT3G60650","No alias","Arabidopsis thaliana","unknown protein; Has 10 Blast hits to 10 proteins in 5 species: Archae - 0; Bacteria - 0; Metazoa - 0; Fungi - 0; Plants - 10; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT3G63240","No alias","Arabidopsis thaliana","DNAse I-like superfamily protein","protein_coding"
"AT4G00120","GT140","Arabidopsis thaliana","basic helix-loop-helix (bHLH) DNA-binding superfamily protein","protein_coding"
"AT4G08520","No alias","Arabidopsis thaliana","SNARE-like superfamily protein","protein_coding"
"AT4G10630","No alias","Arabidopsis thaliana","Glutaredoxin family protein","protein_coding"
"AT4G12440","APT4","Arabidopsis thaliana","adenine phosphoribosyl transferase 4","protein_coding"
"AT4G13950","RALFL31","Arabidopsis thaliana","ralf-like 31","protein_coding"
"AT4G16141","No alias","Arabidopsis thaliana","GATA type zinc finger transcription factor family protein","protein_coding"
"AT4G17760","No alias","Arabidopsis thaliana","damaged DNA binding;exodeoxyribonuclease IIIs","protein_coding"
"AT4G18310","No alias","Arabidopsis thaliana","unknown protein; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT4G18320.2); Has 1807 Blast hits to 1807 proteins in 277 species: Archae - 0; Bacteria - 0; Metazoa - 736; Fungi - 347; Plants - 385; Viruses - 0; Other Eukaryotes - 339 (source: NCBI BLink).","protein_coding"
"AT4G22570","APT3","Arabidopsis thaliana","adenine phosphoribosyl transferase 3","protein_coding"
"AT4G28330","No alias","Arabidopsis thaliana","unknown protein; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT4G28340.1); Has 48 Blast hits to 48 proteins in 10 species: Archae - 0; Bacteria - 0; Metazoa - 0; Fungi - 0; Plants - 48; Viruses - 0; Other Eukaryotes - 0 (source: NCBI BLink).","protein_coding"
"AT4G33480","No alias","Arabidopsis thaliana","unknown protein; FUNCTIONS IN: molecular_function unknown; INVOLVED IN: biological_process unknown; LOCATED IN: chloroplast; EXPRESSED IN: 22 plant structures; EXPRESSED DURING: 13 growth stages; CONTAINS InterPro DOMAIN/s: Protein of unknown function DUF3727 (InterPro:IPR022203); Has 348 Blast hits to 348 proteins in 78 species: Archae - 0; Bacteria - 101; Metazoa - 0; Fungi - 0; Plants - 183; Viruses - 0; Other Eukaryotes - 64 (source: NCBI BLink).","protein_coding"
"AT4G33790","G7","Arabidopsis thaliana","Jojoba acyl CoA reductase-related male sterility protein","protein_coding"
"AT4G37590","NPY5","Arabidopsis thaliana","Phototropic-responsive NPH3 family protein","protein_coding"
"AT5G01090","No alias","Arabidopsis thaliana","Concanavalin A-like lectin family protein","protein_coding"
"AT5G08260","scpl35","Arabidopsis thaliana","serine carboxypeptidase-like 35","protein_coding"
"AT5G09300","No alias","Arabidopsis thaliana","Thiamin diphosphate-binding fold (THDP-binding) superfamily protein","protein_coding"
"AT5G13290","SOL2","Arabidopsis thaliana","Protein kinase superfamily protein","protein_coding"
"AT5G23140","CLPP2","Arabidopsis thaliana","nuclear-encoded CLP protease P7","protein_coding"
"AT5G25390","SHN2","Arabidopsis thaliana","Integrase-type DNA-binding superfamily protein","protein_coding"
"AT5G26810","No alias","Arabidopsis thaliana","Pectin lyase-like superfamily protein","protein_coding"
"AT5G35590","PAA1","Arabidopsis thaliana","proteasome alpha subunit A1","protein_coding"
"AT5G37300","WSD1","Arabidopsis thaliana","O-acyltransferase (WSD1-like) family protein","protein_coding"
"AT5G37730","No alias","Arabidopsis thaliana","unknown protein; BEST Arabidopsis thaliana protein match is: unknown protein (TAIR:AT1G23150.1); Has 1807 Blast hits to 1807 proteins in 277 species: Archae - 0; Bacteria - 0; Metazoa - 736; Fungi - 347; Plants - 385; Viruses - 0; Other Eukaryotes - 339 (source: NCBI BLink).","protein_coding"
"AT5G37780","TCH1","Arabidopsis thaliana","calmodulin 1","protein_coding"
"AT5G39860","PRE1","Arabidopsis thaliana","basic helix-loop-helix (bHLH) DNA-binding family protein","protein_coding"
"AT5G43270","SPL2","Arabidopsis thaliana","squamosa promoter binding protein-like 2","protein_coding"
"AT5G47440","No alias","Arabidopsis thaliana","Plant protein of unknown function (DUF828) with plant pleckstrin homology-like region","protein_coding"
"AT5G49950","No alias","Arabidopsis thaliana","alpha/beta-Hydrolases superfamily protein","protein_coding"
"AT5G50790","SWEET10","Arabidopsis thaliana","Nodulin MtN3 family protein","protein_coding"
"AT5G53200","TRY","Arabidopsis thaliana","Homeodomain-like superfamily protein","protein_coding"
"AT5G53760","ATMLO11","Arabidopsis thaliana","Seven transmembrane MLO family protein","protein_coding"
"AT5G53990","No alias","Arabidopsis thaliana","UDP-Glycosyltransferase superfamily protein","protein_coding"
"AT5G56790","No alias","Arabidopsis thaliana","Protein kinase superfamily protein","protein_coding"
"AT5G57280","No alias","Arabidopsis thaliana","S-adenosyl-L-methionine-dependent methyltransferases superfamily protein","protein_coding"
"AT5G57800","CER3","Arabidopsis thaliana","Fatty acid hydroxylase superfamily","protein_coding"
"AT5G59320","LTP3","Arabidopsis thaliana","lipid transfer protein 3","protein_coding"
"AT5G59790","No alias","Arabidopsis thaliana","Domain of unknown function (DUF966)","protein_coding"
"AT5G60910","AGL8","Arabidopsis thaliana","AGAMOUS-like 8","protein_coding"
"AT5G61650","CYCP4;2","Arabidopsis thaliana","CYCLIN P4;2","protein_coding"
"AT5G62180","CXE20","Arabidopsis thaliana","carboxyesterase 20","protein_coding"
"AT5G62210","No alias","Arabidopsis thaliana","Embryo-specific protein 3, (ATS3)","protein_coding"
"AT5G65340","No alias","Arabidopsis thaliana","Protein of unknown function, DUF617","protein_coding"
"AT5G66560","No alias","Arabidopsis thaliana","Phototropic-responsive NPH3 family protein","protein_coding"
"AT5G66815","No alias","Arabidopsis thaliana","unknown protein; FUNCTIONS IN: molecular_function unknown; INVOLVED IN: biological_process unknown; LOCATED IN: endomembrane system; EXPRESSED IN: root; Has 30201 Blast hits to 17322 proteins in 780 species: Archae - 12; Bacteria - 1396; Metazoa - 17338; Fungi - 3422; Plants - 5037; Viruses - 0; Other Eukaryotes - 2996 (source: NCBI BLink).","protein_coding"
"AT5G67180","TOE3","Arabidopsis thaliana","target of early activation tagged (EAT) 3","protein_coding"