{"feature_sets":[{"about":"Composition and physical properties of a DNA or RNA sequence","features":[{"name":"length","group":"size","unit":"bases","description":"Number of bases"},{"name":"molecular_weight","group":"size","unit":"Da","description":"Single-strand molecular weight: DNA Σ(313.21 A, 304.2 T, 289.18 C, 329.21 G) − 61.96; RNA Σ(329.21 A, 306.17 U, 305.18 C, 345.21 G) + 159.0","reference":"Thermo Fisher oligonucleotide formulas"},{"name":"is_rna","group":"size","unit":"flag","description":"1 when the sequence holds U and no T"},{"name":"frac_A","group":"composition","unit":"fraction","description":"Fraction of A"},{"name":"frac_C","group":"composition","unit":"fraction","description":"Fraction of C"},{"name":"frac_G","group":"composition","unit":"fraction","description":"Fraction of G"},{"name":"frac_T","group":"composition","unit":"fraction","description":"Fraction of T (or U in RNA)"},{"name":"frac_ambiguous","group":"composition","unit":"fraction","description":"Fraction of IUPAC ambiguity codes and N"},{"name":"gc_content","group":"composition","unit":"fraction","description":"(G + C) over unambiguous bases"},{"name":"gc_skew","group":"composition","description":"(G − C) / (G + C)","reference":"Lobry (1996) Mol Biol Evol 13:660"},{"name":"at_skew","group":"composition","description":"(A − T) / (A + T)"},{"name":"cpg_observed_expected","group":"composition","description":"CpG observed/expected: CpG·N / (C·G)","reference":"Gardiner-Garden & Frommer (1987) J Mol Biol 196:261"},{"name":"melting_temperature","group":"physics","unit":"°C","description":"Basic melting temperature: 2(A+T) + 4(G+C) below 14 bases, else 64.9 + 41(G + C − 16.4)/N","reference":"Wallace rule; Marmur & Doty"},{"name":"entropy_bits","group":"complexity","unit":"bits","description":"Shannon entropy of the base composition"},{"name":"di_AA","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide AA (T for U) among overlapping pairs"},{"name":"di_AC","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide AC (T for U) among overlapping pairs"},{"name":"di_AG","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide AG (T for U) among overlapping pairs"},{"name":"di_AT","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide AT (T for U) among overlapping pairs"},{"name":"di_CA","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide CA (T for U) among overlapping pairs"},{"name":"di_CC","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide CC (T for U) among overlapping pairs"},{"name":"di_CG","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide CG (T for U) among overlapping pairs"},{"name":"di_CT","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide CT (T for U) among overlapping pairs"},{"name":"di_GA","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide GA (T for U) among overlapping pairs"},{"name":"di_GC","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide GC (T for U) among overlapping pairs"},{"name":"di_GG","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide GG (T for U) among overlapping pairs"},{"name":"di_GT","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide GT (T for U) among overlapping pairs"},{"name":"di_TA","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide TA (T for U) among overlapping pairs"},{"name":"di_TC","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide TC (T for U) among overlapping pairs"},{"name":"di_TG","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide TG (T for U) among overlapping pairs"},{"name":"di_TT","group":"dinucleotides","unit":"fraction","description":"Frequency of the dinucleotide TT (T for U) among overlapping pairs"}],"kind":"nucleotide","name":"gl1x-nucleotide-1","prefix":"n_"}],"gl1f":{"default_scale_q":1000,"features_text":"the GL1F NFT features string: one feature name per line, in input order, as a model NFT stores its inputs","note":"a model trained on a dataset's feature columns takes them in the dataset's column order; quantize new inputs with the model's own scale_q","packing":"one little-endian int32 per input in feature order: the bytes the GL1F runtime's predict functions take","quantization":"q = clamp(round(x · scale_q)) to the int32 range, the GL1F Forest input rule (half rounds away from zero for positive x, toward +∞ as JavaScript's Math.round)"},"molnft_paths":{"0xd58b01f6c18086e5202cdc5d7ad3e41790360102:43":"/molnft/116D"},"record":{"accession":null,"collection_name":"MolNFT v2 / PDB Bank","contract_address":"0xd58b01f6c18086e5202cdc5d7ad3e41790360102","molecular_id":"116D","molnft_version":"v2","pdb_id":"116D","structure_available":true,"title":"CRYSTAL AND MOLECULAR STRUCTURE OF THE A-DNA DODECAMER D(CCGTACGTACGG): CHOICE OF FRAGMENT HELICAL AXIS","token_id":"43","url":"/molnft/116D"},"sequences":[{"ambiguous":0,"chain_id":null,"chains":[],"is_primary":true,"length":12,"notes":["DNA of 12 bases, 3,646.4 Da single strand","GC content 66.7%; GC skew 0.000, AT skew 0.000","Melting temperature ≈ 40.0 °C by the basic formula (salt and strand concentration not considered)","CpG observed/expected 2.25"],"sequence":"CCGTACGTACGG","sequence_key":"primary","sequence_keys":["primary"],"sequence_type":"nucleotide","set":"gl1x-nucleotide-1","sha256":"a3b7fc24d7a39ab986b0535b5c3504db24eb6a21552a669ba481d1197d3746bd","values":[12,3646.42,0,0.166667,0.333333,0.333333,0.166667,0,0.666667,0,0,2.25,40,1.918296,0,0.181818,0,0,0,0.090909,0.272727,0,0,0,0.090909,0.181818,0.181818,0,0,0]}],"sequences_truncated":false,"structure":{"chains":[],"entry_id":"116D","method":"X-RAY DIFFRACTION","predicted":false,"skipped":[{"chain_id":"A","kind":"dna","reason":"structure features describe protein chains"}],"status":"complete"}}