Skip to content

Fix df_mash_corr_dist silently overwritten with raw Mash distances #35

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dingyifei wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix df_mash_corr_dist silently overwritten with raw Mash distances #35

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
96 changes: 9 additions & 87 deletions examples/2b_mash_filtration_and_clustering.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,13 +197,7 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# scrubbed_strains = scrubbed_species_metadata.genome_id.astype('str')\n",
"\n",
"df_mash_square = df_mash_square.loc[scrubbed_strains, scrubbed_strains]\n",
"df_mash_corr = df_mash_corr.loc[scrubbed_strains, scrubbed_strains]\n",
"df_mash_corr_dist = df_mash_square.loc[scrubbed_strains, scrubbed_strains]"
]
"source": "# scrubbed_strains = scrubbed_species_metadata.genome_id.astype('str')\n\ndf_mash_square = df_mash_square.loc[scrubbed_strains, scrubbed_strains]\ndf_mash_corr = df_mash_corr.loc[scrubbed_strains, scrubbed_strains]\ndf_mash_corr_dist = df_mash_corr_dist.loc[scrubbed_strains, scrubbed_strains]"
},
{
"cell_type": "markdown",
Expand Down Expand Up @@ -263,17 +257,7 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"for repr_strain in repr_strains:\n",
" cond = df_mash_square.loc[repr_strain] < cutoff\n",
" good_strains = df_mash_square.loc[repr_strain][cond].index\n",
" \n",
" df_mash_square = df_mash_square.loc[good_strains, good_strains]\n",
" df_mash_corr = df_mash_corr.loc[good_strains, good_strains]\n",
" df_mash_corr_dist = df_mash_square.loc[good_strains, good_strains]\n",
" \n",
"df_mash_corr_dist.shape"
]
"source": "for repr_strain in repr_strains:\n cond = df_mash_square.loc[repr_strain] < cutoff\n good_strains = df_mash_square.loc[repr_strain][cond].index\n \n df_mash_square = df_mash_square.loc[good_strains, good_strains]\n df_mash_corr = df_mash_corr.loc[good_strains, good_strains]\n df_mash_corr_dist = df_mash_corr_dist.loc[good_strains, good_strains]\n \ndf_mash_corr_dist.shape"
},
{
"cell_type": "code",
Expand Down Expand Up @@ -303,20 +287,7 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"cond = scrubbed_species_summary.genome_status == 'Complete'\n",
"complete_seqs = set(scrubbed_species_summary[cond].genome_id)\n",
"complete_seqs = sorted(\n",
" complete_seqs.intersection(set(df_mash_square.index))\n",
")\n",
"\n",
"\n",
"df_mash_square_complete = df_mash_square.loc[complete_seqs, complete_seqs]\n",
"df_mash_corr_complete = df_mash_square.loc[complete_seqs, complete_seqs]\n",
"df_mash_corr_dist_complete = df_mash_square.loc[complete_seqs, complete_seqs]\n",
"\n",
"df_mash_corr_dist_complete.shape"
]
"source": "cond = scrubbed_species_summary.genome_status == 'Complete'\ncomplete_seqs = set(scrubbed_species_summary[cond].genome_id)\ncomplete_seqs = sorted(\n complete_seqs.intersection(set(df_mash_square.index))\n)\n\n\ndf_mash_square_complete = df_mash_square.loc[complete_seqs, complete_seqs]\ndf_mash_corr_complete = df_mash_corr.loc[complete_seqs, complete_seqs]\ndf_mash_corr_dist_complete = df_mash_corr_dist.loc[complete_seqs, complete_seqs]\n\ndf_mash_corr_dist_complete.shape"
},
{
"cell_type": "code",
Expand Down Expand Up @@ -435,19 +406,7 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"bad_genomes_list = []\n",
"\n",
"for genome in df_mash_square_complete.index:\n",
" cluster = clst.loc[genome, 'cluster']\n",
" if cluster in bad_clusters:\n",
" bad_genomes_list.append(genome)\n",
"\n",
"# Update filtration\n",
"df_mash_square_complete = remove_bad_strains(df_mash_square_complete, bad_genomes_list)\n",
"df_mash_corr_complete = remove_bad_strains(df_mash_square_complete, bad_genomes_list)\n",
"df_mash_corr_dist_complete = remove_bad_strains(df_mash_corr_dist_complete, bad_genomes_list)"
]
"source": "bad_genomes_list = []\n\nfor genome in df_mash_square_complete.index:\n cluster = clst.loc[genome, 'cluster']\n if cluster in bad_clusters:\n bad_genomes_list.append(genome)\n\n# Update filtration\ndf_mash_square_complete = remove_bad_strains(df_mash_square_complete, bad_genomes_list)\ndf_mash_corr_complete = remove_bad_strains(df_mash_corr_complete, bad_genomes_list)\ndf_mash_corr_dist_complete = remove_bad_strains(df_mash_corr_dist_complete, bad_genomes_list)"
},
{
"cell_type": "markdown",
Expand All @@ -461,44 +420,7 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"iteration = 1\n",
"prev = 0\n",
"curr = len(clst.cluster.unique())\n",
"\n",
"while(np.abs(prev - curr) > 0 ):\n",
" print(f'iteration {iteration}...{curr}')\n",
" \n",
" # Cluster\n",
" link, dist, clst = cluster_corr_dist(df_mash_corr_dist_complete, thresh=elbow_threshold)\n",
" \n",
" # Color each cluster\n",
" cm = matplotlib.colormaps.get_cmap('tab20')\n",
" clr = dict(zip(sorted(clst.cluster.unique()), cm.colors))\n",
" clst['color'] = clst.cluster.map(clr)\n",
" \n",
" # Increment\n",
" prev = curr\n",
" curr = len(clst.cluster.unique())\n",
" \n",
" # Define bad clusters\n",
" bad_clusters = clst.cluster.value_counts()[clst.cluster.value_counts() < small_clst_limit]\n",
" \n",
" # Remove bad genomes\n",
" bad_genomes_list = []\n",
" for genome in df_mash_square_complete.index:\n",
" cluster = clst.loc[genome, 'cluster']\n",
" if cluster in bad_clusters:\n",
" bad_genomes_list.append(genome)\n",
" \n",
" # Update filtration\n",
" df_mash_square_complete = remove_bad_strains(df_mash_square_complete, bad_genomes_list)\n",
" df_mash_corr_complete = remove_bad_strains(df_mash_square_complete, bad_genomes_list)\n",
" df_mash_corr_dist_complete = remove_bad_strains(df_mash_corr_dist_complete, bad_genomes_list)\n",
" \n",
" # Increment\n",
" iteration +=1"
]
"source": "iteration = 1\nprev = 0\ncurr = len(clst.cluster.unique())\n\nwhile(np.abs(prev - curr) > 0 ):\n print(f'iteration {iteration}...{curr}')\n \n # Cluster\n link, dist, clst = cluster_corr_dist(df_mash_corr_dist_complete, thresh=elbow_threshold)\n \n # Color each cluster\n cm = matplotlib.colormaps.get_cmap('tab20')\n clr = dict(zip(sorted(clst.cluster.unique()), cm.colors))\n clst['color'] = clst.cluster.map(clr)\n \n # Increment\n prev = curr\n curr = len(clst.cluster.unique())\n \n # Define bad clusters\n bad_clusters = clst.cluster.value_counts()[clst.cluster.value_counts() < small_clst_limit]\n \n # Remove bad genomes\n bad_genomes_list = []\n for genome in df_mash_square_complete.index:\n cluster = clst.loc[genome, 'cluster']\n if cluster in bad_clusters:\n bad_genomes_list.append(genome)\n \n # Update filtration\n df_mash_square_complete = remove_bad_strains(df_mash_square_complete, bad_genomes_list)\n df_mash_corr_complete = remove_bad_strains(df_mash_corr_complete, bad_genomes_list)\n df_mash_corr_dist_complete = remove_bad_strains(df_mash_corr_dist_complete, bad_genomes_list)\n \n # Increment\n iteration +=1"
},
{
"cell_type": "code",
Expand Down Expand Up @@ -647,9 +569,9 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python pyphylon",
"display_name": "pangenome",
"language": "python",
"name": "pyphylontesting"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
Expand All @@ -661,9 +583,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.8"
"version": "3.11.14"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
}