{"id":"W4388975238","doi":"10.3389/fmicb.2023.1217750","title":"Predicting environmental stressor levels with machine learning: a comparison between amplicon sequencing, metagenomics, and total RNA sequencing based on taxonomically assigned data","year":2023,"lang":"en","type":"article","venue":"Frontiers in Microbiology","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Canada First Research Excellence Fund; Deutsche Forschungsgemeinschaft; Biodiversa+","keywords":"Metagenomics; Amplicon sequencing; Amplicon; Biology; Context (archaeology); Deep sequencing; Massive parallel sequencing; Machine learning; Computational biology; Artificial intelligence; DNA sequencing; Computer science; Genetics; 16S ribosomal RNA; Genome; Polymerase chain reaction; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009932783,0.001611202,0.001116484,0.003253862,0.0003504842,0.001707698,0.0009530849,0.001149632,0.0004162883],"category_scores_gemma":[0.01106255,0.0003855226,0.001279864,0.00188268,0.000598087,0.001699585,0.000875012,0.0008772689,0.0002193383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007633847,"about_ca_system_score_gemma":0.0006614616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001372047,"about_ca_topic_score_gemma":0.001660766,"domain_scores_codex":[0.9959747,0.002077264,0.0002968569,0.0007482083,0.0007826039,0.0001204111],"domain_scores_gemma":[0.9911629,0.006721698,0.00072367,0.000476511,0.0007408878,0.0001743404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002908453,0.001101898,0.2044629,0.001448873,0.003247376,0.0001813311,0.0004100627,0.201184,0.02988512,0.001313236,0.0009267568,0.55293],"study_design_scores_gemma":[0.00008689972,0.001999454,0.07349773,0.0003329477,0.0004486045,0.0001749188,0.0002453808,0.9004933,0.01690993,0.004028874,0.001666695,0.0001152966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7871734,0.01621058,0.1905191,0.001228546,0.0001536328,0.0002404401,0.0007856751,0.0007652123,0.002923464],"genre_scores_gemma":[0.8639756,0.003428271,0.1307842,0.000272872,0.0001066816,0.0001317737,0.0009392265,0.00008997985,0.0002714305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009932783,"threshold_uncertainty_score":0.05253023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04356600572186626,"score_gpt":0.2424770770692571,"score_spread":0.1989110713473909,"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."}}