{"id":"W4365149100","doi":"10.26434/chemrxiv-2023-09wgb","title":"Analysis of nanopore data: classification strategies for an unbiased curation of single-molecule events from DNA nanostructures","year":2023,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Nanopore and Nanochannel Transport Studies","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nanopore; Event (particle physics); Computer science; Nanopore sequencing; Identification (biology); Computational biology; Nanotechnology; Data mining; Biological system; DNA sequencing; DNA; Biology; Materials science; Genetics; Physics","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":[0.002596885,0.0008912188,0.0008894611,0.002548549,0.0006880793,0.001571517,0.001397632,0.001208325,0.001703379],"category_scores_gemma":[0.006804734,0.0003644561,0.00070445,0.001412039,0.0008006975,0.001631632,0.00130952,0.001624153,0.001213686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007457781,"about_ca_system_score_gemma":0.0009824698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001228976,"about_ca_topic_score_gemma":0.002263143,"domain_scores_codex":[0.998635,0.0002269214,0.0001525364,0.0003839991,0.0004809414,0.0001206042],"domain_scores_gemma":[0.9951768,0.002003775,0.0006934594,0.00108861,0.0008490671,0.0001883761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000693629,0.0004171968,0.01204522,0.0007770965,0.0002251944,0.0004876618,0.0005815251,0.02639116,0.5615174,0.01430783,0.004780178,0.377776],"study_design_scores_gemma":[0.00002841836,0.0001505194,0.01160834,0.00008114816,0.00006564224,0.0004710715,0.000236506,0.522329,0.4209725,0.02813271,0.01581937,0.0001048494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03162683,0.0003181495,0.963999,0.000209807,0.00003355891,0.0001099303,0.0008595376,0.002278158,0.0005649694],"genre_scores_gemma":[0.1972069,0.0004858418,0.7968345,0.0002756247,0.00005867273,0.000432973,0.00288382,0.0005982599,0.001223342],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002596885,"threshold_uncertainty_score":0.0137338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1202722317328615,"score_gpt":0.3079173499597168,"score_spread":0.1876451182268553,"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."}}