{"id":"W4206903088","doi":"10.1101/2022.01.20.477098","title":"Image-centric compression of protein structures improves space savings","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lossless compression; Huffman coding; Computer science; Data compression; Image compression; Compression (physics); Compression ratio; Image file formats; Encoding (memory); Computational science; File size; Gas compressor; File format; Image (mathematics); Computer graphics (images); Algorithm; Theoretical computer science; Computer engineering; Computer vision; Image processing; Artificial intelligence; Database","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005728364,0.0006579799,0.0007669909,0.0004542129,0.0003566035,0.0004615376,0.003365553,0.0003622046,0.0001153213],"category_scores_gemma":[0.0001781194,0.0006305712,0.0002210419,0.0008833274,0.0001439231,0.0006384881,0.007427082,0.0011833,0.00001246791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002403498,"about_ca_system_score_gemma":0.000699122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001753314,"about_ca_topic_score_gemma":3.884993e-7,"domain_scores_codex":[0.9957558,0.0002809398,0.0007409885,0.001545273,0.001020924,0.0006560555],"domain_scores_gemma":[0.9950406,0.00008267488,0.001106313,0.003010766,0.0004658065,0.0002938723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002700069,0.000188559,0.0002573787,0.0005794435,0.00006349705,0.00005827979,0.000022483,0.00007285937,0.9930926,0.004655017,0.000942104,0.00004075831],"study_design_scores_gemma":[0.001470758,0.0002827902,0.06570171,0.001081324,0.0001002653,8.303294e-8,0.000008809749,0.04164755,0.8640587,0.0001570375,0.02329021,0.002200739],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7155705,0.004659709,0.2695266,0.0005877963,0.003947347,0.003502059,0.0007819992,0.001386574,0.00003739625],"genre_scores_gemma":[0.7305756,0.00009757817,0.26867,0.00007182579,0.0002454399,0.0002401877,0.000001019183,0.00008766058,0.00001071178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1290339,"threshold_uncertainty_score":0.9996145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009245792001998163,"score_gpt":0.2183854240670093,"score_spread":0.2091396320650112,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}