Move unused workflow logic to deprecated scripts

nextstrain · Jan 24, 2025 · 7bd4daa · 7bd4daa
1 parent 3b5e2d0
commit 7bd4daa
Show file tree

Hide file tree

Showing 3 changed files with 85 additions and 76 deletions.
diff --git a/scripts/deprecated/calculate_delta_frequency.py b/scripts/deprecated/calculate_delta_frequency.py
@@ -1,6 +1,51 @@
-"""Calculate the change in frequency for clades over time (aka the delta frequency or dfreq).
+"""
+
+Calculate the change in frequency for clades over time (aka the delta frequency or dfreq).
 Design discussion is located on GitHub at https://github.com/nextstrain/ncov/pull/595
+
+--------------------------------------------------------------
+
+This analysis was removed from the workflow on 2025-01-23
+This used frequencies of strains in the tree to estimate logistic growth rates
+However, analyses at nextstrain.org/sars-cov-2/forecasts use all the available
+sequence data and provide a more sophisticated estimate of growth rate accounting
+for competition between circulating viruses. These updated results are available
+in the `mlr_lineage_fitness` analysis
+
+rule logistic_growth:
+    input:
+        tree="results/{build_name}/tree.nwk",
+        frequencies="results/{build_name}/tip-frequencies.json",
+    output:
+        node_data="results/{build_name}/logistic_growth.json"
+    benchmark:
+        "benchmarks/logistic_growth_{build_name}.txt"
+    conda:
+        config["conda_environment"]
+    log:
+        "logs/logistic_growth_{build_name}.txt"
+    params:
+        method="logistic",
+        attribute_name = "logistic_growth",
+        delta_pivots=config["logistic_growth"]["delta_pivots"],
+        min_tips=config["logistic_growth"]["min_tips"],
+        min_frequency=config["logistic_growth"]["min_frequency"],
+        max_frequency=config["logistic_growth"]["max_frequency"],
+    resources:
+        mem_mb=256
+    shell:
+        python3 scripts/calculate_delta_frequency.py \
+            --tree {input.tree} \
+            --frequencies {input.frequencies} \
+            --method {params.method} \
+            --delta-pivots {params.delta_pivots} \
+            --min-tips {params.min_tips} \
+            --min-frequency {params.min_frequency} \
+            --max-frequency {params.max_frequency} \
+            --attribute-name {params.attribute_name} \
+            --output {output.node_data} 2>&1 | tee {log}
 """
+
 import argparse
 from augur.frequency_estimators import logit_transform
 from augur.utils import annotate_parents_for_tree, read_node_data, read_tree, write_json

diff --git a/scripts/deprecated/parse_mutational_fitness_tsv_into_distance_map.py b/scripts/deprecated/parse_mutational_fitness_tsv_into_distance_map.py
@@ -11,7 +11,46 @@
 Updated model outputs are available at https://github.com/bkotzen/sars-cov2-modeling following:
 
 https://raw.githubusercontent.com/bkotzen/sars-cov2-modeling/main/2024-07-22/PyR0/mutations.tsv
+
+--------------------------------------------------------------
+
+This analysis was removed from the workflow on 2025-01-23
+This was drawn from results at https://github.com/bkotzen/sars-cov2-modeling
+But this repo hasn't been updated since 2024-07-22
+If these results become updated more frequently, we should restore this analysis
+
+This was used in the workflow following:
+
+rule mutational_fitness:
+    input:
+        tree = "results/{build_name}/tree.nwk",
+        alignments = lambda w: rules.translate.output.translations,
+        distance_map = config["files"]["mutational_fitness_distance_map"]
+    output:
+        node_data = "results/{build_name}/mutational_fitness.json"
+    benchmark:
+        "benchmarks/mutational_fitness_{build_name}.txt"
+    log:
+        "logs/mutational_fitness_{build_name}.txt"
+    params:
+        genes = ' '.join(config.get('genes', ['S'])),
+        compare_to = "root",
+        attribute_name = "mutational_fitness"
+    conda:
+        config["conda_environment"],
+    resources:
+        mem_mb=2000
+    shell:
+        augur distance \
+            --tree {input.tree} \
+            --alignment {input.alignments} \
+            --gene-names {params.genes} \
+            --compare-to {params.compare_to} \
+            --attribute-name {params.attribute_name} \
+            --map {input.distance_map} \
+            --output {output} 2>&1 | tee {log}
 """
+
 import argparse
 import pandas as pd
 import json

diff --git a/workflow/snakemake_rules/main_workflow.smk b/workflow/snakemake_rules/main_workflow.smk
@@ -1103,81 +1103,6 @@ rule tip_frequencies:
             --proportion-wide {params.proportion_wide} \
             --output {output.tip_frequencies_json} 2>&1 | tee {log}
         """
-# This analysis is deprecated as of 2025-01-23
-# This uses frequencies of strains in the tree to estimate logistic growth rates
-# However, analyses at nextstrain.org/sars-cov-2/forecasts use all the available
-# sequence data and provide a more sophisticated estimate of growth rate accounting
-# for competition between circulating viruses. This updated results are available
-# in the `mlr_lineage_fitness` analysis
-# rule logistic_growth:
-#     input:
-#         tree="results/{build_name}/tree.nwk",
-#         frequencies="results/{build_name}/tip-frequencies.json",
-#     output:
-#         node_data="results/{build_name}/logistic_growth.json"
-#     benchmark:
-#         "benchmarks/logistic_growth_{build_name}.txt"
-#     conda:
-#         config["conda_environment"]
-#     log:
-#         "logs/logistic_growth_{build_name}.txt"
-#     params:
-#         method="logistic",
-#         attribute_name = "logistic_growth",
-#         delta_pivots=config["logistic_growth"]["delta_pivots"],
-#         min_tips=config["logistic_growth"]["min_tips"],
-#         min_frequency=config["logistic_growth"]["min_frequency"],
-#         max_frequency=config["logistic_growth"]["max_frequency"],
-#     resources:
-#         mem_mb=256
-#     shell:
-#         r"""
-#         python3 scripts/calculate_delta_frequency.py \
-#             --tree {input.tree} \
-#             --frequencies {input.frequencies} \
-#             --method {params.method} \
-#             --delta-pivots {params.delta_pivots} \
-#             --min-tips {params.min_tips} \
-#             --min-frequency {params.min_frequency} \
-#             --max-frequency {params.max_frequency} \
-#             --attribute-name {params.attribute_name} \
-#             --output {output.node_data} 2>&1 | tee {log}
-#         """
-
-# This analysis is deprecated as of 2025-01-23
-# This was drawn from results at https://github.com/bkotzen/sars-cov2-modeling
-# But this analysis hasn't been updated since 2024-07-22
-# If these results become updated more frequently, we should restore this analysis
-# rule mutational_fitness:
-#     input:
-#         tree = "results/{build_name}/tree.nwk",
-#         alignments = lambda w: rules.translate.output.translations,
-#         distance_map = config["files"]["mutational_fitness_distance_map"]
-#     output:
-#         node_data = "results/{build_name}/mutational_fitness.json"
-#     benchmark:
-#         "benchmarks/mutational_fitness_{build_name}.txt"
-#     log:
-#         "logs/mutational_fitness_{build_name}.txt"
-#     params:
-#         genes = ' '.join(config.get('genes', ['S'])),
-#         compare_to = "root",
-#         attribute_name = "mutational_fitness"
-#     conda:
-#         config["conda_environment"],
-#     resources:
-#         mem_mb=2000
-#     shell:
-#         r"""
-#         augur distance \
-#             --tree {input.tree} \
-#             --alignment {input.alignments} \
-#             --gene-names {params.genes} \
-#             --compare-to {params.compare_to} \
-#             --attribute-name {params.attribute_name} \
-#             --map {input.distance_map} \
-#             --output {output} 2>&1 | tee {log}
-#         """
 
 rule mlr_lineage_fitness:
     input: