genomewalker

Get the data from figshare

convert the DB into fasta

mkdir agnostos-comp cd agnostos-comp

mkdir one_step two_step

tar xvfz mg_gtdb_20190502.tar.gz ln -s mg_gtdb_db_20190502.dbtype mg_gtdb_db_20190502_h.dbtype

genomewalker

Sub AuthorTec_ReplaceAuthorName()

Const MacroName = "AuthorTec™ Replace Author Name"

'In XML formatted Word documents (docx, dotx, docm, dotm), this

'macro changes a specified author name on comments and tracked

'revisions. It runs on both Windows and Mac versions of Microsoft Word

genomewalker

name: anvio-7.1
channels:
  - conda-forge
  - bioconda
  - defaults
dependencies:
  - python=3.6
  - anvio=7
  - diamond=0.9.14
  - pip

genomewalker

easy-taxonomy e77760e07c3167ef94f937365175d68b.assm.combined.fasta DB/uniref50-tax/UniRef50 e77760e07c3167ef94f937365175d68b.UniRef50 /dev/shm/tmp/contig-taxonomy/e77760e07c3167ef94f937365175d68b.tax.UniRef50 --tax-lineage 2 --majority 0.5 --vote-mode 1 --lca-mode 3 --orf-filter 1 --lca-ranks superkingdom,phylum,class,order,family,genus --threads 32 

MMseqs Version:                        	5daca424b162cc5fdf0b9cd151aebed86975cbf6
ORF filter                             	1
ORF filter e-value                     	100
ORF filter sensitivity                 	2
LCA mode                               	3
Majority threshold                     	0.5
Vote mode                              	1
LCA ranks                              	superkingdom,phylum,class,order,family,genus

genomewalker

For the C program:

# Igraph C-library
wget https://igraph.org/nightly/get/c/igraph-0.7.1.tar.gz
tar xvfz igraph-0.7.1.tar.gz
cd igraph-0.7.1
./configure --prefix="${PREFIX}"/igraph/0.7.1
make -j 8
make check

genomewalker

1.2G    ./agnostosDB_dbf02445-20200519_environmental.tar.gz
104G    ./agnostosDB_dbf02445-20200519_hh-suite-db.tar.gz
21G     ./agnostosDB_dbf02445-20200519_mmseqs-cluseqdb.tar.gz
11G     ./agnostosDB_dbf02445-20200519_mmseqs-profiles.tar.gz
3.9G    ./agnostosDB_dbf02445-20200519_original-data.tar.gz
279M    ./agnostosDB_dbf02445-20200519_phylogenetic.tar.gz
111M    ./cluDB_name_origin_size.tsv.gz
312M    ./cluster_category_summary_stats.tsv.gz
30M     ./cluster_communities.tsv.gz
141M    ./cluster_db_size_categ_origin.tsv.gz

genomewalker

# From 
cut -f3 permafrost_pathway_orthologs.txt | grep -v ortho | while read ko; do make ${ko}.kegg.faa; done
for i in *kegg.faa; do NAM=$(basename $i .kegg.faa); hmmalign ../profiles/$NAM.hmm $NAM.kegg.faa | awk -vN=$NAM '{if (NR == 2){print "#=GF ID"N"\n#=GF AC   "N}else{print $0}}' ; done > alns.stck
mmseqs convertmsa faa/alns.stck ko_msa_db
mmseqs msa2profile ko_msa_db permafrost_ko_profiles --match-mode 1

# KO
seqkit replace --ignore-case --kv-file <(awk '{print $2"\t"$1}' ko_genes.list) --pattern "(.+)" --replacement "{kv}" <(seqkit replace -p "\s.+" test) > ko_seq.faa
awk '/^>/{split($1,a,":")}{print >> a[2]".fa"}' ../ko_seq.faa
~/opt/uproc-1.2.0/uproc-makedb model ko_seq.faa koDB

genomewalker

library(tidyverse)
library(DESeq2)
library(phyloseq)
library(taxonomizr)

# Read metadata
metadata <- read_csv("data/metadata_v10.csv", )
names(metadata) <- c("label", "age_ka_bp", "age_type",  "site_abrev", "region", "dating_lab_id",
                     "C14_age", "OSL_age", "age_errors", "group1", "lat", "lon")

genomewalker

library(tidyverse)
library(ggtree)
library(ape)
library(readxl)
library(viridis)

# Get tree data
tree_data <- read_xlsx(path = "clade_table_with_region.xlsx") %>%
  rename(label = ID) %>%
  mutate(group = case_when(age >= 50000 ~ "50+",

genomewalker

Let's install linuxbrew and pyenv

sh -c "$(curl -fsSL https://raw.githubusercontent.com/Linuxbrew/install/master/install.sh)"
brew install pyenv pyenv-virtualenv pyenv-which-ext
pyenv install miniconda3-latest
pyenv global miniconda3-latest

then we need to add into .bash_profile