Input data and cached results for, "MSA-based pLMs encode evolutionary distance but don't reliably exploit it"
Input data and cached results for, "MSA-based pLMs encode evolutionary distance but don't reliably exploit it"
Input Data - response_regulator_inputs: Raw Pfam alignments (PF00072, PF00196, PF00486, PF04397) and PDB representative sequences for responseregulator analysis- msa_difficulty: Pythia 2.0 MSA difficulty scores (msa_difficulty.csv)- casp15_input: CASP15 MSAs and target PDB structures (msas/, targets/) Intermediate Results - response_regulators_seq_weights: MSA Pairformer sequence weights for response regulator queries (inference_results.pt)- uniclust30_msas: Diversity-filtered MSAs from OpenProteinSet (1024 sequences each)- uniclust30_trees: FastTree phylogenies for each MSA (.fasttree.newick, .fasttree.log)- uniclust30_seq_weights: MSA Pairformer sequence weights for all UniClust30 MSAs (seq_weights.pt)- uniclust30_iqtrees: IQ-TREE phylogenies for 10 smallest MSAs (.iqtree.newick, .iqtree.log)- uniclust30_seq_weights_depth_200: Sequence weights for depth-200 filtered MSAs (seq_weights_depth_200.pt)- contact_prediction: Beta-carbon contact predictions with/without sequence weighting (cb_contacts.pt, cb_contacts_uniform.pt, pdbs/)- casp15_contact_prediction: Beta-carbon contact predictions for CASP15 targets (casp15_cb_contacts.pt,casp15_cb_contacts_uniform.pt)- layer_shuffling: Layer ablation study with shuffled sequence weights (single/, cumulative/) Pub Info - No need to manually download, the notebook pub will download necessary materials when executed - DOI: https://doi.org/10.57844/arcadia-ppdz-asaz - URL: https://arcadia-science.github.io/2025-phylogenetic-analysis-of-msa-pairformer
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!