{"id":"W4406708071","doi":"10.1101/2025.01.17.633498","title":"Recovering ecological interactions by mining non-target data from whole genome re-sequencing projects","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Natural Resources and Forestry","funders":"Helsinki Institute of Life Science, Helsingin Yliopisto; Helsingin Yliopisto","keywords":"Computational biology; Genome; DNA sequencing; Data science; Whole genome sequencing; Geography; Ecology; Biology; Computer science; Genetics; Gene","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004335878,0.001537408,0.001376058,0.004808545,0.0009876442,0.002330911,0.001315557,0.001570042,0.001641265],"category_scores_gemma":[0.009708165,0.0007564826,0.001710284,0.004331202,0.0006028929,0.001400105,0.001982288,0.001855841,0.002411203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004804779,"about_ca_system_score_gemma":0.0008792078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001567942,"about_ca_topic_score_gemma":0.003993721,"domain_scores_codex":[0.9963592,0.0008422593,0.0002908037,0.001659879,0.0006646838,0.0001832268],"domain_scores_gemma":[0.9928704,0.002582098,0.002035495,0.001400348,0.0007606845,0.0003508689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001057849,0.0006484795,0.3618335,0.007401106,0.006997053,0.003099267,0.002021122,0.02594169,0.3859121,0.007200757,0.02127605,0.1766111],"study_design_scores_gemma":[0.000221903,0.0007090539,0.580362,0.001208717,0.002364056,0.004048725,0.00255847,0.1443161,0.07846944,0.03146148,0.1539365,0.0003435709],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6154536,0.009839394,0.233583,0.001448331,0.0003264834,0.0004417998,0.1246893,0.006702343,0.007515652],"genre_scores_gemma":[0.5297478,0.002374282,0.2754002,0.0009940644,0.0001740629,0.0005586003,0.1870403,0.001572531,0.002138075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004808545,"threshold_uncertainty_score":0.02293062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03677414994120227,"score_gpt":0.2497298084791777,"score_spread":0.2129556585379754,"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."}}