{"id":"W2952156265","doi":"10.1371/journal.pcbi.1005755","title":"Unmet needs for analyzing biological big data: A survey of 704 NSF principal investigators","year":2017,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":157,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Principal (computer security); Workflow; Data science; Data management; Big data; Data archive; Computer science; Publication; Work (physics); Political science; Engineering; Data mining; Database","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07644267,0.0005244141,0.0007980802,0.006701692,0.003438403,0.006510392,0.003346751,0.002113033,0.00753408],"category_scores_gemma":[0.1251251,0.0009723169,0.0009875953,0.01057073,0.002384074,0.007408563,0.01098141,0.004297706,0.001935206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003466028,"about_ca_system_score_gemma":0.02076781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006028706,"about_ca_topic_score_gemma":0.008262681,"domain_scores_codex":[0.9676031,0.008986332,0.003759098,0.002201467,0.01429857,0.003151462],"domain_scores_gemma":[0.8302042,0.05440701,0.01758925,0.009080571,0.04894186,0.03977703],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004177227,0.0002640808,0.197397,0.00211049,0.0002029019,0.0004460799,0.004559541,0.0003866255,0.001051241,0.01295543,0.279622,0.5005867],"study_design_scores_gemma":[0.0001701182,0.0002774007,0.2040345,0.004364468,0.0002378978,0.001539654,0.018188,0.001517334,0.001298756,0.02102282,0.7471544,0.000194733],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2187879,0.09330659,0.01719914,0.6153055,0.004239072,0.0005629786,0.006386137,0.001517013,0.04269573],"genre_scores_gemma":[0.5996094,0.1575273,0.04991249,0.154973,0.006700532,0.001803105,0.01753676,0.001143081,0.01079434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9235573,"threshold_uncertainty_score":0.4042723,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2060724053949253,"score_gpt":0.3698108616315151,"score_spread":0.1637384562365898,"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."}}