{"success":true,"data":{"author":"Google Research (Sanderson et al., ProteInfer)","bucketAccessType":"public","bucketListable":true,"bucketName":"brain-genomics-public","bucketPrefix":"research/proteins/proteinfer","category":"Proteomics","cloudProvider":"gcp","createdAt":"2026-11-17T14:12:20.560Z","description":"Training and evaluation data for ProteInfer, the convolutional networks that predict protein function directly from amino acid sequence (Sanderson et al., ProteInfer, deep networks for protein functional inference, eLife). Sequences come from Swiss-Prot, the manually curated part of UniProt, labeled with Enzyme Commission (EC) numbers and Gene Ontology (GO) terms, with parent terms added so the labels follow each hierarchy. Two splits are given: a random 80/20 split, and a clustered split by UniRef50 cluster membership so that test sequences have low similarity to training sequences. Each TFRecord example carries the UniProt accession, the sequence and its list of database cross-reference labels. Measured 2026-11-17: datasets/swissprot/ holds random/ and clustered/, plus price_annotations.tsv; sibling folders hold models/, blast_baseline/, interpro_baseline/, swissprot_inference_results/ and colab_support/. Read the records with TensorFlow tf.data. Built from UniProt data; the folder README licenses it CC BY 4.0. Cite Sanderson et al., eLife, and UniProt.","displayTitle":"ProteInfer Swiss-Prot Training Sets for EC Number and Gene Ontology Prediction (Random and Clustered Splits)","doi":"10.7554/eLife.80942","fuseMountBrowsable":true,"id":"6796d4bb-2b1b-587c-802d-0e5d0aaae99a","license":"CC-BY-4.0","licenseEvidenceUrl":"https://storage.googleapis.com/brain-genomics-public/research/proteins/proteinfer/README.md","objectCountEstimate":6,"probeStatus":"ok","referenceUrl":"https://doi.org/10.7554/eLife.80942","region":"us","schemaCard":{"accessHints":[{"language":"python-gcsfs","snippet":"import gcsfs\nfs = gcsfs.GCSFileSystem(token='anon')\nfs.ls('brain-genomics-public/research/proteins/proteinfer/', detail=False)[:10]"},{"language":"python-storage","snippet":"from google.cloud import storage\nclient = storage.Client.create_anonymous_client()\nlist(client.bucket('brain-genomics-public').list_blobs(prefix='research/proteins/proteinfer/', max_results=10))"}],"caveats":["Files are binary — use a domain-specific parser rather than text I/O."],"format":"binary","generatedAt":"2026-11-17T14:24:14.319Z","layout":{"example":"research/proteins/proteinfer/blast_baseline/blast_output/clustered/blast_out_dev.tsv","pattern":"{prefix}/{seg1}/{seg2}/{seg3}/{seg4}/{seg5}/{filename}"},"mountPath":"/mnt/gcs-archive/data","sampleHeaders":[{"bytes":"accession=\"Q0WJ82\"\taccession=\"Q82ZN5\"\t56.410\t390\t169\t1\t16\t405\t9\t397\t1.00e-142\t415\naccession=\"P21316\"\taccession=\"P21678\"\t69.231\t169\t52\t0\t1\t169\t1\t169\t1.21e-89\t260\naccession=\"P31559\"\taccession=\"Q9MS66\"\t66.667\t33\t11\t0\t1\t33\t1\t33\t5.65e-10\t48.9\naccession=\"Q8Z3A8\"\taccession=\"O31087\"\t74.834\t302\t74\t1\t1\t300\t1\t302\t4.72e-167\t467\naccession=\"Q8Z2Y6\"\taccession=\"Q88NX8\"\t72.892\t498\t129\t1\t3\t500\t7\t498\t0.0\t790\naccession=\"P63604\"\taccession=\"A8GAI2\"\t56.395\t172\t75\t0\t1\t172\t1\t172\t7.77e-66\t201\naccession=\"Q8Z8H3\"\taccession=\"P65208\"\t57","encoding":"utf8","key":"research/proteins/proteinfer/blast_baseline/blast_output/clustered/blast_out_dev.tsv","truncatedAt":512},{"bytes":"accession=\"A3MV32\"\taccession=\"A8MDP6\"\t60.000\t225\t84\t4\t3\t225\t4\t224\t9.54e-91\t268\naccession=\"B8CKI4\"\taccession=\"A4IR26\"\t33.654\t208\t129\t4\t14\t221\t8\t206\t1.61e-28\t109\naccession=\"B8CND5\"\taccession=\"A0KF23\"\t79.000\t100\t21\t0\t1\t100\t1\t100\t1.08e-51\t159\naccession=\"P66675\"\taccession=\"A4VV23\"\t50.794\t252\t123\t1\t4\t255\t3\t253\t1.01e-76\t234\naccession=\"P0A0B3\"\taccession=\"A7GU41\"\t65.149\t505\t174\t2\t12\t515\t10\t513\t0.0\t697\naccession=\"Q99R60\"\taccession=\"Q7VN48\"\t24.762\t105\t78\t1\t2\t105\t10\t114\t9.50e-07\t48.9\naccession=\"P0DG91\"\taccession=\"A4VZL","encoding":"utf8","key":"research/proteins/proteinfer/blast_baseline/blast_output/clustered/blast_out_test.tsv","truncatedAt":512}],"sampleObjects":["research/proteins/proteinfer/blast_baseline/blast_output/clustered/blast_out_dev.tsv","research/proteins/proteinfer/blast_baseline/blast_output/clustered/blast_out_test.tsv","research/proteins/proteinfer/blast_baseline/blast_output/random/blast_out_dev.tsv","research/proteins/proteinfer/blast_baseline/blast_output/random/blast_out_test.tsv"],"sidecars":[{"bytes":"# ProteInfer training datasets\n\nThis directory contains data used to train deep neural networks that predict\nprotein function, and was built for the ProteInfer project\n(http://proteinfer.github.io).\n\n## Attribution\n\nThis dataset was created with data from the UniProt consortium\n(http://uniprot.org).\n\n## License\n\nThese data are licensed under the CC 4.0 license\n(https://creativecommons.org/licenses/by/4.0/).\n","encoding":"utf8","key":"research/proteins/proteinfer/README.md","name":"README.md","size":411,"truncated":false}],"sourceObjectKey":"research/proteins/proteinfer/blast_baseline/blast_output/clustered/blast_out_dev.tsv","starterCell":"from google.cloud import storage\nclient = storage.Client.create_anonymous_client()\nbucket = client.bucket('brain-genomics-public')\nblob = bucket.blob('research/proteins/proteinfer/blast_baseline/blast_output/clustered/blast_out_dev.tsv')\nwith blob.open(\"rb\") as fh:\n    print(fh.read(64))","starterSamplePath":"blast_baseline/blast_output/clustered/blast_out_dev.tsv","totalObjects":"6 top-level prefixes"},"summary":"Training and evaluation data for ProteInfer, the convolutional networks that predict protein function directly from amino acid sequence (Sanderson et al., ProteInfer, deep…","title":"ProteInfer Swiss-Prot Training Sets for EC Number and Gene Ontology Prediction (Random and Clustered Splits)","updatedAt":"2026-11-17T20:13:55.906Z","visibility":"public","websiteUrl":"https://google-research.github.io/proteinfer/"}}