Mobility and sequence diversity of the Hok bacterial toxin family

This archive contains the bioinformatics analyses used in:Mobility and sequence diversity of the Hok bacterial toxin family Each subdirectory contains:1. Jupyter notebooks for specific analysis steps.2. README files describing the purpose and outputs of each analysis.3. Input and output files generated by the notebooks. ------------------------------------------------------------ DIRECTORY STRUCTURE Escalera-Maurer_2026├── bac_classification_fig3│ ├── 240404_bac_refseq_Ass_reports.txt│ ├── assembly_refseq_chromosomes_uniques.csv│ ├── bac_classification.ipynb│ ├── bac_classification_plasmid_VS_chromosome.ipynb│ ├── boxenplot_PvC_count_per_Genus.svg│ ├── Fig3A_raw_data.csv│ ├── f__Vibrionaceae_pept.fasta│ ├── gtdbtk.bac120.decorated.tree-taxonomy│ ├── hits_per_enter_genus.svg│ ├── percent_hits_per_fam_PvC.svg│ ├── raw_data_fig3C.csv│ ├── README_bac_classification_plasmid_VS_chromosome.txt│ └── README_bac_classification.txt├── bac_phylo_tree_fig1D│ ├── bar_annot_hok_numbers_Chr.txt│ ├── bar_annot_hok_numbers_Plasmid.txt│ ├── Enterobacteriaceae.tree.itol│ ├── README_tree_analysis.txt│ └── tree_analysis.ipynb├── clean_clusters│ ├── 250212_n45428_final_with_NCBI_annot.csv│ ├── 250320_clean_for_clust.fasta│ ├── 250320_hoks_trimmed_gt10.csv│ ├── 250320_SD_CDS_annot.csv│ ├── 250320_unique_pred_orf_aln.fasta│ ├── 250320_unique_pred_orf.fasta│ ├── 250320_unique_pred_orf_new_aln.fasta│ ├── 250320_unique_pred_orf_new.fasta│ ├── 250326_final_n45074_hok_homologs.csv│ ├── 250326_reclustered.csv│ ├── 250611_final_n45057_hok_homologs.csv│ ├── 4489375.clans│ ├── clean_reclustered_table.ipynb│ ├── clus60│ │ ├── _all_seqs.fasta│ │ ├── _cluster.tsv│ │ └── _rep_seq.fasta│ ├── clus80│ │ ├── _all_seqs.fasta│ │ ├── _cluster.tsv│ │ └── _rep_seq.fasta│ ├── clus90│ │ ├── _all_seqs.fasta│ │ ├── _cluster.tsv│ │ └── _rep_seq.fasta│ ├── hok_reannotation_script_CDS_SD_annot.py│ ├── missing_T1TAdb_to_add.csv│ ├── README_clean_reclustered_table│ ├── README_recluster│ ├── recluster.ipynb│ ├── representatives.csv│ ├── selected_clans.fasta│ ├── T1TAdb.csv│ └── trimal_removed.fasta├── clus60_analysis_refseq_fig1C│ ├── 250326_fake_clus60_tree_for_plotting.txt│ ├── clus_analysis_refseq.ipynb│ ├── itol_annotation_location_60cluster.txt│ ├── itol_annotation_methodology_clus60.txt│ ├── itol_annotation_unique_log_count_per_60cluster.txt│ ├── location_percent.txt│ ├── methods_marks.txt│ ├── mixed_clus100.svg│ ├── README_clus_analysis_refseq.txt│ └── unique_log_counts.txt├── clus60_analysis_refseq_PR_VR_figS7A│ ├── 250707_fake_clus60_tree_refseq_VR_PR.txt│ ├── clus100_PvC.svg│ ├── clus_analysis_refseq_PR_VR.ipynb│ ├── itol_annotation_location_60cluster.txt│ ├── itol_annotation_methodology_clus60.txt│ ├── itol_annotation_unique_log_count_per_60cluster.txt│ ├── location_percent.txt│ ├── methods_marks.txt│ ├── mixed_clus100.svg│ ├── README_clus_analysis_refseq_VR_PR.txt│ ├── search_methods_counts_clean.svg│ └── unique_log_counts.txt├── clus60_by_search│ └── upset.ipynb├── curated_T1TAs.fasta├── defense_fig4│ ├── chromsome_lengths.csv│ ├── chromsome_lengths_refseq.csv│ ├── chromsome_lengths_symE.csv│ ├── Hok_<20K_from_DS_Chr_only_genomes_with_ds.svg│ ├── hoks_defense_genomes_with_DS.ipynb│ ├── protein_pos_to_coord_unique.txt│ ├── README_hoks_defense_genomes_with_DS│ ├── README_symE_defense│ ├── searched_seq_summary_bak.txt│ ├── SymE_<20K_from_DS_chr.svg│ ├── symE_defense.ipynb│ ├── symE_mmseqs_hits.csv│ └── translated_gembase_all_defense_finder_systems.tsv├── genomes│ ├── assembly_summary_complete_genomes.txt│ ├── download_fastas.sh│ ├── fastas│ └── README├── HGT_Fig7_FigS8│ ├── README_shared_by_genus_clus100│ ├── shared_by_genus_clus100.ipynb│ ├── shared_clust_heatmap_loci_count_PvCvV_percent_by_clus60.svg│ ├── upset_counts_per_Chr_Pl_pro_phage_shared_inter-Genus_clus100.svg│ └── upset_counts_per_Chr_Pl_pro_phage_total_clus100.svg├── islets_fig1B│ ├── Fig3B_raw_data.csv│ ├── hok_islets_chr_pl_genus.svg│ ├── hok_islets.svg│ ├── hoks_near_hoks.ipynb│ └── README_islets.txt├── NCBI_locus_annotations│ ├── fetch_annotations.py│ └── get_NCBI_annot.ipynb├── peptide_annotation│ ├── direct_not_found_translate.fasta│ ├── direct_search_not_found.fasta│ ├── fetch_locus.py│ ├── hok_loci_coord.csv│ ├── hok_loci_nuc.csv│ ├── hok_peptide_predict_EC.csv│ ├── mmseqs_aln_unique.fasta│ ├── mmseqs_CMsearch_blast_hok_searches.csv│ ├── nucleotide_sequences.fasta│ ├── pairwise_alignment.py│ ├── peptide_annotation.ipynb│ ├── peptides_exact_coincidence.txt│ ├── README│ ├── search_pep_100.py│ └── seq_translate_3rf.fasta├── PR_Fig6│ ├── fig6A_raw.csv│ ├── Fig6B_raw_data.csv│ ├── hist_count_vs_length_hist_entero_conjugative.svg│ ├── hits_per_fam_in_pl.svg│ ├── hits_per_Genus_in_pl.svg│ ├── IMG_PR_pasmidScope_proteins_complete_entero.csv│ ├── IMGPR_plasmid_data.tsv│ ├── IMG-PR.plasmid_list.download.tsv│ ├── README_search_stats│ └── search_stats.ipynb├── README.md├── self_search_fig1B│ ├── all2all_pident_hist.svg│ ├── hok_queries│ │ ├── IMG_VR_PR_refseq_pept.fasta│ │ ├── prot│ │ ├── prot.dbtype│ │ ├── prot_h│ │ ├── prot_h.dbtype│ │ ├── prot_h.index│ │ ├── prot.index│ │ ├── prot.lookup│ │ └── prot.source│ ├── IMG_VR_PR_refseq_pept.fasta│ ├── README_self_search.txt│ ├── results│ │ ├── aln│ │ ├── aln.dbtype│ │ ├── aln.index│ │ └── aln.m8│ └── self_search.ipynb├── T1TAdb_input│ ├── curated_Hok.fasta│ └── hok.faa├── tm_prediction│ ├── clean_pept_for_logo_aln.fasta│ ├── deeptmhmm│ │ ├── biolib-input-files│ │ │ └── clean_pept_for_logo.fasta│ │ ├── clean_pept_for_logo.fasta│ │ ├── deeptmhmm_results.md│ │ ├── predicted_topologies.3line│ │ └── TMRs.gff3│ ├── logos.ipynb│ ├── profile.hmm│ ├── TMHMM result.pdf│ └── trimmed_aln_for_logo.fasta├── upset_logo_statistics_figs1ADE│ ├── aa_logo_less_than_10_unique_clus60.svg│ ├── aa_logo_n1264.svg│ ├── clean_pept_for_logo_aln.fasta│ ├── clean_pept_for_logo.fasta│ ├── logos-Copy1.ipynb│ ├── logos.ipynb│ ├── nt_aa_logo_C16.svg│ ├── nt_aa_logo_C31.svg│ ├── nt_aa_logo_C48.svg│ ├── nt_aa_logo_n1264.svg│ ├── nt_aa_logo_T18.svg│ ├── nt_aa_logo_Y31.svg│ ├── nt_aa_logo_Y48.svg│ ├── README_logos│ ├── README_stats│ ├── README_upset.txt│ ├── stats.ipynb│ ├── upset.ipynb│ └── upset.svg└── VR_Fig5 ├── 220920_bac_refseq_Ass_reports.txt ├── chromsome_lengths_symE.csv ├── Fig5A_raw_data.csv ├── hits_per_entero_genus_in_pro-phages.svg ├── IMG_all_Bac.tsv ├── IMGVR_all_Sequence_information-high_confidence.tsv ├── map_virus_in_refseq.ipynb ├── percent_Hok_In_prophages.svg ├── percent_in_prophages_Fig5B_Hok.ipynb ├── percent_in_prophages_Fig5B_symE.ipynb ├── percent_symE_In_prophages.svg ├── README_map_virus_in_refseq ├── README_percent_in_prophages_Fig5B_Hok ├── README_percent_in_prophages_Fig5B_symE ├── README_search_stats_Fig5A ├── refseq_prophages_coordinates_accession.csv ├── refseq_prophages_coordinates_accession_in_symE_chr.csv └── search_stats_Fig5A.ipynb