{"id":"W4399117787","doi":"10.1093/bioinformatics/btae342","title":"Representations of lipid nanoparticles using large language models for transfection efficiency prediction","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Interference and Gene Delivery","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sanofi (Canada)","funders":"Sanofi","keywords":"Payload (computing); Transfection; Nanoparticle; Gene delivery; Computer science; Messenger RNA; Chemistry; Nanotechnology; Computational biology; Cell biology; Biochemistry; Biology; Materials science; Gene; Computer network","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":[0.001221397,0.001337911,0.0007875699,0.001137421,0.0003847114,0.001259408,0.001096026,0.001147864,0.003288293],"category_scores_gemma":[0.005208115,0.0004106267,0.001755369,0.0005990064,0.000425597,0.001171344,0.0008024969,0.001517066,0.00271279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001193418,"about_ca_system_score_gemma":0.001077215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004670535,"about_ca_topic_score_gemma":0.005073801,"domain_scores_codex":[0.9994249,0.000211196,0.00003843363,0.0001594148,0.0000984789,0.00006747552],"domain_scores_gemma":[0.9979665,0.001406701,0.0001238384,0.0001175025,0.000314286,0.00007112392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005988379,0.0004030277,0.005150347,0.0004059485,0.0001858,0.000314853,0.0001663352,0.7743424,0.02051436,0.0119282,0.01296791,0.173022],"study_design_scores_gemma":[0.000008332568,0.00002213653,0.00009554662,0.000006271657,0.000009268175,0.00001419919,0.000007502563,0.9934142,0.001711701,0.004165567,0.0005387319,0.000006499487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08094772,0.0008010317,0.899934,0.0009446326,0.0001562468,0.0001390268,0.003544369,0.01103128,0.002501741],"genre_scores_gemma":[0.6570758,0.0007220444,0.3188245,0.0006804714,0.0001581822,0.0007756607,0.01517913,0.001265103,0.005319096],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004670535,"threshold_uncertainty_score":0.01100045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01932988650558984,"score_gpt":0.2876306062438401,"score_spread":0.2683007197382503,"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."}}