{"id":"W4414594447","doi":"10.1038/s42004-025-01683-z","title":"MolGraph-xLSTM as a graph-based dual-level xLSTM framework for enhanced molecular representation and interpretability","year":2025,"lang":"en","type":"article","venue":"Communications Chemistry","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; University of Manitoba; Western University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Interpretability; Representation (politics); Graph; Regression; Molecular descriptor; Feature (linguistics); Cheminformatics; Pattern recognition (psychology); Feature extraction","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004685144,0.0001799035,0.0002118724,0.0001021582,0.0002722464,0.0001784038,0.001602224,0.0001317855,0.000007973365],"category_scores_gemma":[0.001516603,0.0002103603,0.0001563469,0.0008845495,0.0002874927,0.0002183241,0.0008905514,0.00028396,0.000002131029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000717466,"about_ca_system_score_gemma":0.000263534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001602507,"about_ca_topic_score_gemma":0.000002992663,"domain_scores_codex":[0.99849,0.0002153435,0.000382267,0.0005365391,0.0001803056,0.0001954987],"domain_scores_gemma":[0.9937995,0.002511836,0.0001518386,0.00315329,0.0003029433,0.00008058015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001100458,0.0007317449,0.0006451171,0.0005389845,0.0002661876,0.000002817586,0.001287755,0.008449646,0.2460618,0.6799484,0.0004062831,0.06155125],"study_design_scores_gemma":[0.0003556943,0.00001296412,0.001044875,0.000137489,0.0000277489,0.000003122313,0.00008309975,0.09775861,0.3003623,0.5996986,0.0003104272,0.0002051018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05789081,0.0007156189,0.9325976,0.004894768,0.00008363733,0.0003745884,0.00002351646,0.0001368824,0.003282524],"genre_scores_gemma":[0.5648153,0.00002048191,0.4344119,0.0003780508,0.000005667507,0.0002596352,0.00004632631,0.000006768648,0.00005584784],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5069246,"threshold_uncertainty_score":0.8578243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03727308334263623,"score_gpt":0.3886884362909387,"score_spread":0.3514153529483025,"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."}}