{"id":"W4408766904","doi":"10.1101/2025.03.21.644400","title":"An Artificial Intelligence Model for Translating Natural Language into Functional de Novo Proteins","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computational biology; Computer science; Protein design; Chemistry; Cell biology; Biology; Protein structure; Biochemistry","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":[0.001105676,0.0006175325,0.0003235087,0.0005252473,0.0001860707,0.0007916355,0.001151262,0.0007066685,0.0035054],"category_scores_gemma":[0.003581332,0.000308611,0.0007652562,0.0003846359,0.0005778464,0.001239573,0.0004948673,0.001350424,0.000720816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009473577,"about_ca_system_score_gemma":0.0008577409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00251042,"about_ca_topic_score_gemma":0.002991546,"domain_scores_codex":[0.9996947,0.0001077527,0.00001941441,0.000100275,0.00004452495,0.00003326778],"domain_scores_gemma":[0.9983235,0.001253281,0.0001001839,0.00009984033,0.0001794326,0.00004371362],"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":[0.0001847166,0.0001262785,0.001560281,0.0001645039,0.00004520084,0.0001408011,0.0001274302,0.8980437,0.00585067,0.02487579,0.00275888,0.06612182],"study_design_scores_gemma":[0.000006768879,0.00001538139,0.00004009527,0.000003096776,0.000003107506,0.000006497411,0.000004187844,0.9921407,0.0005985131,0.006880016,0.0002998618,0.000001784198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1445448,0.0003291775,0.8430052,0.001418027,0.0001196064,0.0001526495,0.0009892891,0.003601342,0.005840008],"genre_scores_gemma":[0.7452952,0.0002433702,0.2468089,0.0005259053,0.0000617031,0.0003424919,0.001533057,0.0001837784,0.005005703],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0035054,"threshold_uncertainty_score":0.01172674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04115979233209858,"score_gpt":0.3191601309420454,"score_spread":0.2780003386099468,"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."}}