ATOMICAdoi:10.7910/DVN/4DUBJXHarvard Dataverse2025-04-021Fang, Ada; Zaixi Zhang; Andrew Zhou; Marinka Zitnik, 2025, "ATOMICA", https://doi.org/10.7910/DVN/4DUBJX, Harvard Dataverse, V1, UNF:6:5HKIlWTQwgwDI29MfVc/5Q== [fileUNF]ATOMICAdoi:10.7910/DVN/4DUBJXFang, AdaZaixi ZhangAndrew ZhouMarinka ZitnikHarvard DataverseFang, AdaFang, Ada2025-03-27ChemistryComputer and Information ScienceMedicine, Health and Life SciencesDatasets used in developing & evaluating ATOMICA.<a href="http://creativecommons.org/licenses/by/4.0">CC BY 4.0</a>ATOMICAScore_protein_small_molecule_results.tab569124text/tab-separated-valuesUNF:6:CgFPlCHL6R4A7UpNxTlPQA==ATOMICAScore for identification of amino acid blocks involved in intermolecular bonds.ADP_ids_sequence_30_split.tab3343882text/tab-separated-valuesUNF:6:LDK8HUM0sSAUVE5LyLMcZQ==30% sequence similarity split for ADP ligands on protein-small molecule complexesATP_ids_sequence_30_split.tab3318092text/tab-separated-valuesUNF:6:IcRGbZgxYwKdA6tCnYag2A==30% sequence similarity split for ATP ligands on protein-small molecule complexesCA_ids_sequence_30_split.tab2022732text/tab-separated-valuesUNF:6:KMAaUCWusRU7w419n53vkA==30% sequence similarity split for CA ligands on protein-ion complexesCIT_ids_sequence_30_split.tab3078072text/tab-separated-valuesUNF:6:mcfcqtIqd1YtfLuFlIQxeg==30% sequence similarity split for CIT ligands on protein-small molecule complexesCLA_ids_sequence_30_split.tab3091562text/tab-separated-valuesUNF:6:gmZqNjII8J4S9H8n0stiOg==30% sequence similarity split for CLA ligands on protein-small molecule complexesCO_ids_sequence_30_split.tab2021572text/tab-separated-valuesUNF:6:SWJEVMiBBW5lrmzFsOFdUQ==30% sequence similarity split for CO ligands on protein-ion complexesCU_ids_sequence_30_split.tab2007462text/tab-separated-valuesUNF:6:deP/TqmZcjtq5B4a+qQyQQ==30% sequence similarity split for CU ligands on protein-ion complexesdark_proteome_predictions.tab30654text/tab-separated-valuesUNF:6:esWxnh1+pVYCV86nAhVL7A==Predictions of ATOMICA-Ligand on dark proteome ion and small molecule binding sitesFAD_ids_sequence_30_split.tab3338662text/tab-separated-valuesUNF:6:2/hy9HcUiQJgi6uaRupi0g==30% sequence similarity split for FAD ligands on protein-small molecule complexesFE_ids_sequence_30_split.tab2018122text/tab-separated-valuesUNF:6:UOHdwrCxuymh8p9KMmKsPQ==30% sequence similarity split for FE ligands on protein-ion complexesGDP_ids_sequence_30_split.tab3190292text/tab-separated-valuesUNF:6:4Y4Yzf+EXHwlGlzJmA/2sQ==30% sequence similarity split for GDP ligands on protein-small molecule complexesGTP_ids_sequence_30_split.tab3154922text/tab-separated-valuesUNF:6:vbYOTn7VbUyDd9ms1DBD9g==30% sequence similarity split for GTP ligands on protein-small molecule complexesHEC_ids_sequence_30_split.tab2693202text/tab-separated-valuesUNF:6:cCegCG8MKhvVG1heMEgv2A==30% sequence similarity split for HEC ligands on protein-small molecule complexesHEM_ids_sequence_30_split.tab3334872text/tab-separated-valuesUNF:6:n3Xba22j9a+xMc84zCIflQ==30% sequence similarity split for HEM ligands on protein-small molecule complexesK_ids_sequence_30_split.tab2032602text/tab-separated-valuesUNF:6:C2L2+pA4uW9XjEHmeMHSzg==30% sequence similarity split for K ligands on protein-ion complexesMG_ids_sequence_30_split.tab2007992text/tab-separated-valuesUNF:6:57pxZCJpRCm//0MIgLroWg==30% sequence similarity split for MG ligands on protein-ion complexe complexesMN_ids_sequence_30_split.tab2037842text/tab-separated-valuesUNF:6:J2Iu1Tpo2vqwUCOjZIJI2A==30% sequence similarity split for MN ligands on protein-ion complexesNAD_ids_sequence_30_split.tab3100152text/tab-separated-valuesUNF:6:/qTQMj4j7+nJDNXPGMNQ8Q==30% sequence similarity split for NAD ligands on protein-small molecule complexesNAP_ids_sequence_30_split.tab3089832text/tab-separated-valuesUNF:6:doR2+I+invnVWFKu8Oal/Q==30% sequence similarity split for NAP ligands on protein-small molecule complexesNDP_ids_sequence_30_split.tab2887062text/tab-separated-valuesUNF:6:gYOjKlHbMP8WxSNL0O5znA==30% sequence similarity split for NDP ligands on protein-small molecule complexesZN_ids_sequence_30_split.tab2028062text/tab-separated-valuesUNF:6:vM5BKDQvTbtaVAgkE7/Hpw==30% sequence similarity split for ZN ligands on protein-ion complexesPDNA_ids.tab27502text/tab-separated-valuesUNF:6:fkbEYNjsww0D7xAp+bpM4g==Protein-DNA 30% sequence similarity splitPion_ids.tab745142text/tab-separated-valuesUNF:6:RmxcW4MpC8dDKJ5YhhetaQ==Protein-ion 30% sequence similarity splitPL_ids.tab1190172text/tab-separated-valuesUNF:6:NyV65rMg/9kna1s6w9peyA==Protein-small molecule 30% sequence similarity splitPpeptide_ids.tab84752text/tab-separated-valuesUNF:6:K34Ftjt7kdT5Z3ji6zZiWw==Protein-peptide 30% sequence similarity splitPP_ids.tab1245412text/tab-separated-valuesUNF:6:Hj9F0FLleU13zaO5vffu9g==Protein-protein 30% sequence similarity splitPRNA_ids.tab35112text/tab-separated-valuesUNF:6:Yz3HNEhVX8Z/vWiRfXNOxg==Protein-RNA 30% sequence similarity splitRNAL_ids.tab51852text/tab-separated-valuesUNF:6:C5VSg8nATMoeMgYItM6dqA==RNA-ligand 30% sequence similarity splititem_idUNF:6:dwB19c//Lbr0hYM3pZe4Xg==topk_Hydrogen Bonds1.44907952830725641.83605693199789372.05691.0.0.00.08.0UNF:6:g9EP/AqkCV4maI5DcZiouQ==topk_Hydrophobic Interactions0.07.01.14699859511583880.05691.00.70831136882797610.0.UNF:6:HH05yt1jR6UYZZrgy0C74Q==topk_pi-Stacking0.0.0.115094008082936715691.03.00.00.00.34509198099013855UNF:6:9w973QZUgIbS0kP9D/j1YQ==topk_Metal Complexes.5691.04.00.00.051836232648041170.366359641450566260.00.0UNF:6:lTjuZ7lj3nfd81mtd9qnWw==topk_Halogen Bonds.2.00.05691.00.00281145668599544270.059220206101675390.00.0UNF:6:3D6iQ95W2ZCmJPsTdNDvug==rand_Hydrogen Bonds1.230044060773690.0.7.01.01.37726234405201095691.00.0UNF:6:p5IftzzHhu4+dXqhbE7uQQ==rand_Hydrophobic Interactions0.06.00.4795290810050949.0.84162003143788880.05691.00.0UNF:6:8i+zY/OH/2yBXl9Fj6cNuQ==rand_pi-Stacking0.27939592634600650.00.00.072395009664382240.0.5691.02.0UNF:6:++NSU/4aAmUJVWc0TG8sXQ==rand_Metal Complexes4.00.00.00.0379546652609383.5691.00.27927907199317690.0UNF:6:U/3JosmVJ2NB3qQ44+ewXw==rand_Halogen Bonds0.049541943415636840.002460024600245975.0.00.01.05691.00.0UNF:6:xWLIZwggKUMwCCRm73ZciQ==topk_total1.45958181693972082.71410999824284140.00.05691.08.03.0.UNF:6:nnff82jHd9YikpkZ6+pqDw==rand_total0.05691.0.7.01.9696011245826740.01.25078119663458962.0UNF:6:zPlwWq3z0BTlcMqSNmYTDg==Hydrogen Bonds.0.05.8655772272008484.889574407585180.036.05.05691.0UNF:6:y5Sc7PqIHXrwkIOVbmPowA==pi-Stacking0.00.0.0.00.33632050606220328.05691.00.7557957144180683UNF:6:1X41ez6crXCW9X2qAypdyg==Hydrophobic Interactions2.35354067826392570.01.00.031.0.5691.03.6704940491824583UNF:6:OtX4UZO05HM2xQLaaz4w5w==Metal Complexes0.07.05691.00.55209305807851770.112985415568441630.0.0.0UNF:6:Cu0mTzuCHbFjPLJaJkUQUg==Halogen Bonds0.093502691176832910.00.00.00667720962923887.2.05691.00.0UNF:6:I1DqwxA14XKgh5AvmRrHKw==esm_Hydrogen Bonds.0.00.05691.01.4642396185097181.6972412581268681.07.0UNF:6:JIrXkmV+op0k08B0JuLr8g==esm_Hydrophobic Interactions.0.00.89983854533136136.05691.00.00.48374626603408890.0UNF:6:1d2EZ9AVffERkyC9TEMhIw==esm_pi-Stacking0.00.03.00.086452293094359565691.0.0.31356711561089430.0UNF:6:/YumVz7dk8p5QgALyC0b1g==esm_Metal Complexes0.0.0.52079892111233410.100685292567211260.07.00.05691.0UNF:6:bUf1aV/1rYK6EmxuwfnJow==esm_Halogen Bonds0.05691.00.00.04587500571503481.00.002108592514496593.0.0UNF:6:bJKfsO006szKxgT5UZH4xA==esm_total2.05691.00.01.4600068366101557.2.3702337023370248.00.0UNF:6:0Rd7lZ+uRcWcP09uDrZokQ==splitUNF:6:W2W3xPh9cuHUdgo+dc1UWA==idUNF:6:/p/X39axrWiOrs/p5dEnfw==splitUNF:6:Tm1qcsaQBG790iIYnWuRUw==idUNF:6:kb3IJP5HXQxoln2TF6sFYA==splitUNF:6:Mu6kx2PsddZW8RV4slvaiw==idUNF:6:yAt7z0RPkiUwzGRPlBMFCg==splitUNF:6:8TuvFADYF6o0YyyGSKSEGA==idUNF:6:6/RYcDZYWPTh9bGkrwVYXQ==splitUNF:6:uYaDR/iGL8uHo6YTqGQLCA==idUNF:6:9t8xqhVErRcAHRORFcp0rw==splitUNF:6:qgPBqy68NUtH+Ms5LlFpZg==idUNF:6:PiC4acDszQW+XlOH0QoUyA==splitUNF:6:nn3S1dwtrDMz7KJw/1mQsQ==idUNF:6:7HLnmyhtVD6aIIswlqrq4w==ligandUNF:6:LQTDESOSB1wxyvBf31DfYg==idUNF:6:D6t2WMLVb1dsFYft1PXvZg==mean0.0504651496666666740.90467162333333343065.00.00.78598920324100340.19249859314131040.9985229133333333.UNF:6:/1CDDYEbNLO73SbqoUEWdA==std0.00.04608470768954749.0.168271494353107843065.00.57416441565250991.2830682301940609E-40.18629739185168348UNF:6:4xEj6cvnZ55GROHU0szMHA==splitUNF:6:ix3lSyF+lj/U3F7gKIS8xw==idUNF:6:Z1L1zeNstKm7iJX06hmDQg==splitUNF:6:2KDwlh/okimRksKwXpCLcA==idUNF:6:7+I3oaGm0r2E0Ay9AhNwlg==splitUNF:6:82Wt247nR/DxAVgkSZpZtQ==idUNF:6:cFMhPXJxqqqhj+sbJzjViQ==splitUNF:6:w0nW2E8fdz6SOvOHAdNEHQ==idUNF:6:2BRMW/UXdRSvmENSAQA3+A==splitUNF:6:gAZ2J+HyD/Y2i/F63BNGPA==idUNF:6:OAZ5WFqc53wpXxFcv3rnpw==splitUNF:6:9OWry8peiJcp9l3YVBU2tw==idUNF:6:er4srlDjBGS/QWd1KNTipQ==splitUNF:6:dE6dJxD65aD7UvJ2J5NwMQ==idUNF:6:VEhJEdM1DuMqC2Kpq2If1A==splitUNF:6:0N24Ye1a4cOoCWbvEfeecQ==idUNF:6:OVa00G+9XzUHBnJrJ/Pu7Q==splitUNF:6:x+0JQRJSfU5UAgbkjr396w==idUNF:6:8Q7rkcWSfy3/aA7R9+sfBw==splitUNF:6:Ln6qdA5E3ECaohf0xE5CLw==idUNF:6:T23cuML00ycGUqL6DTLBBA==splitUNF:6:5Vb0sh62D/jfQ5rDxPKZvQ==idUNF:6:/ILwC5eRRhGM87TjJMT0WA==splitUNF:6:5VuGE2S9Lrwxuf8oXHzl1g==idUNF:6:xHomkJMlBJzpi5AugMBj/A==splitUNF:6:o5K657t/1S6uyBSaelWYRQ==idUNF:6:uPpUe3P595KNYUbRC9xwCA==splitUNF:6:8Tx9l4Fgk/lNGjAVkFOKPA==idUNF:6:jafllybnEYaVFex5JCfvGw==splitUNF:6:8NzJMGT/RCdljW5VHCEBBQ==idUNF:6:TmGgvuHqXRrMStm6+PS07A==splitUNF:6:3HEfy3ACfN11u04C2dR9Gg==idUNF:6:8uSPbDjqnLVjmEjatC0Kxg==splitUNF:6:SXiwSAydjHbG252+xNRebg==idUNF:6:uwgRgM1KtYp1iZWlVnQBXw==splitUNF:6:BSmEFJj5k+39CF5csw4PaA==idUNF:6:HOHpWbBYRsy3AqELyn9gaQ==splitUNF:6:r/KV+RjJV4wX+sn+3jpitw==idUNF:6:zCx8b950i0IwxFE4auXgnw==splitUNF:6:lug//4aoMVAzoB/7ZQS1DQ==idUNF:6:L/EUtWGDwQXpgvFsT45sCQ==annotated_dark_proteome_AF3_outputs.tar.gzAlphaFold3 structures and confidence scores of predicted dark proteome metal ion and small molecule complexesapplication/x-gzipis_dark_90_plddt_PeSTo_80_ion.jsonl.gzProcessed AFDB Cluster representative proteins (with pLDDT > 90) which have predicted small molecule binding sites (with PeSTo confidence > 80)application/x-gzipis_dark_90_plddt_PeSTo_80_small_molecule.jsonl.gzProcessed AFDB Cluster representative proteins (with pLDDT > 90) which have predicted ion binding sites (with PeSTo confidence > 80)application/x-gzipATOMICANet_ion.gmlATOMICANet-Ion for protein-ion interfaceomeapplication/gml+xmlATOMICANet_lipid.gmlATOMICANet-Lipid for protein-lipid interfaceomeapplication/gml+xmlATOMICANet_nucleic_acid.gmlATOMICANet-Nucleic-Acid for protein-nucleic acid interfaceomeapplication/gml+xmlATOMICANet_protein.gmlATOMICANet-Protein for protein-protein interfaceomeapplication/gml+xmlATOMICANet_small_molecule.gmlATOMICANet-Small-Molecule for protein-small molecule interfaceomeapplication/gml+xmlpesto_70_plddt_70_ion.jsonl.gzHuman proteome protein-ion interfaces from AlphaFold2 structures with pLDDT 70% cutoff and PeSTO 70 confidence cutoffapplication/x-gzippesto_70_plddt_70_lipid.jsonl.gzHuman proteome protein-lipid interfaces from AlphaFold2 structures with pLDDT 70% cutoff and PeSTO 70 confidence cutoffapplication/x-gzippesto_70_plddt_70_nucleic_acid.jsonl.gzHuman proteome protein-nucleic acid interfaces from AlphaFold2 structures with pLDDT 70% cutoff and PeSTO 70 confidence cutoffapplication/x-gzippesto_70_plddt_70_protein.jsonl.gzHuman proteome protein-protein interfaces from AlphaFold2 structures with pLDDT 70% cutoff and PeSTO 70 confidence cutoffapplication/x-gzippesto_70_plddt_70_small_molecule.jsonl.gzHuman proteome protein-small molecule interfaces from AlphaFold2 structures with pLDDT 70% cutoff and PeSTO 70 confidence cutoffapplication/x-gzipCSD.jsonl.gzCSD pre-training dataapplication/x-gzipCSD_ids.csvCSD molecule motif similarity splittext/csvPDNA.jsonl.gzProtein-DNA pre-training dataapplication/x-gzipPion.jsonl.gzProtein-ion pre-training dataapplication/x-gzipPL.jsonl.gzProtein-small molecule pre-training dataapplication/x-gzipPP.jsonl.gzProtein-protein pre-training dataapplication/x-gzipPpeptide.jsonl.gzProtein-peptide pre-training dataapplication/x-gzipPRNA.jsonl.gzProtein-RNA pre-training dataapplication/x-gzipRNAL.jsonl.gzRNA-ligand pre-training dataapplication/x-gzip