{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001148377,0.00005983713,0.00006028065,0.00005078825,0.00004584505,0.00002212273,0.00005213683,0.00005907805,0.000004969757],"category_scores_gemma":[0.00001785643,0.0000541095,0.00007517248,0.00008020707,0.00001990629,0.00002076914,0.00001448044,0.0000241482,0.000002397051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007537763,"about_ca_system_score_gemma":0.0000410394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006769942,"about_ca_topic_score_gemma":0.000005367569,"domain_scores_codex":[0.9995181,0.000007885045,0.0002161124,0.00008348667,0.00006538333,0.0001090075],"domain_scores_gemma":[0.9997692,0.000009072178,0.00002978054,0.0001181187,0.00005257032,0.00002133399],"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":[0.00003277363,0.00004451869,0.00005413893,0.0002316191,0.00004323114,2.241744e-7,0.001772935,0.008030534,0.9854004,0.0004353998,0.0007554256,0.00319885],"study_design_scores_gemma":[0.0001478571,0.0001630467,0.00001822194,0.00003422629,0.00002456529,0.000005385671,0.0007787088,0.5739243,0.4242543,0.00004990373,0.0005489692,0.00005050688],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6549594,0.0002796719,0.3439473,0.00001030648,0.0001755506,0.0001386802,0.0001548096,0.00001553509,0.0003187609],"genre_scores_gemma":[0.9965639,0.00007415644,0.003002617,0.0000205163,0.0001041408,0.00001294302,0.0001253005,0.000007370998,0.00008908749],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5658938,"threshold_uncertainty_score":0.2206521,"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."}}