
Download from GISAID search

conda activate pangolin
pangolin 02_inputData/GISAID_NYCPHL_04_29/gisaid_hcov-19_2021_04_30_00.fasta -o 02_inputData/GISAID_NYCPHL_04_29 --max-ambig 75

epimuller-parse -iF 02_inputData/GISAID_NYCPHL_04_29/gisaid_hcov-19_2021_04_30_00.fasta -oM 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename.tsv -oF 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename.fasta -p 02_inputData/GISAID_NYCPHL_04_29/lineage_report.csv


mafft --6merpair --keeplength --addfragments 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename.fasta  01_refData/hu1.fasta > 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename_aln.fasta


[PATHTOIQTREE2]/iqtree-2.0.4-Linux/bin/iqtree2 -s 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename_aln.fasta -m GTR+F+G -fast -pre 02_inputData/GISAID_NYCPHL_04_29/IQtree2_April29_fast_GTRFG -T 4 


conda activate nextstrain
mkdir 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults
augur refine \
--tree 02_inputData/GISAID_NYCPHL_04_29/IQtree2_April29_fast_GTRFG.treefile \
--alignment 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename_aln.fasta \
--metadata 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename.tsv \
--output-tree 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults/tree.nwk \
--output-node-data 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults/branch_lengths.json \
--timetree \
--clock-rate 0.0008 \
--clock-std-dev 0.0004 \
--coalescent skyline \
--date-confidence \
--date-inference marginal \
--clock-filter-iqd 4 \
--no-covariance

augur ancestral \
--tree 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults/tree.nwk \
--alignment 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename_aln.fasta \
--output-node-data 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults/nt_muts.json \
--inference joint


augur translate \
--tree 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults/tree.nwk \
--ancestral-sequences 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults/nt_muts.json \
--reference-sequence  01_refData/Hu-1.gb \
--output-node-data 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults/aa_muts.json

conda activate datetime
epimuller -n 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults -m 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename.tsv -oDir 03_results_NYCPHL_April29 -oP 01_defaultAAList -min 50 -c 02_inputData/CITY_US-NY_NYC_outbreakinfo_epidemiology_data_2021-04-30.tsv



-----------------------------------------

conda activate nextstrain
augur traits \
--tree 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults/tree.nwk \
--metadata 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename.tsv \
--output-node-data 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults/traits.json \
--columns lineage

conda activate datetime
epimuller -n 02_inputData/GISAID_NYCPHL_04_29/02_nextstrainResults -m 02_inputData/GISAID_NYCPHL_04_29/gisaid_2021_04_30_00_rename.tsv -oDir 03_results_NYCPHL_April29 -oP 02_pangolin -min 100 -c 02_inputData/CITY_US-NY_NYC_outbreakinfo_epidemiology_data_2021-04-30.tsv --traitOfInterstFile traits.json --traitOfInterstKey lineage -lp Max