From 909023b2e470f9ff3eb936991cca6e0e6a8e5bd9 Mon Sep 17 00:00:00 2001 From: MrTomRod Date: Wed, 11 May 2022 18:59:40 +0200 Subject: [PATCH] update to 0.0.3: - fix escaping of tabs through command line - improve README.md --- Notes.md | 38 +++++++++++++++++++++++++++++++++ README.md | 4 ++++ media/ScoaryWorkflow.drawio.svg | 4 ++++ pyproject.toml | 2 +- 4 files changed, 47 insertions(+), 1 deletion(-) create mode 100644 Notes.md create mode 100644 media/ScoaryWorkflow.drawio.svg diff --git a/Notes.md b/Notes.md new file mode 100644 index 0000000..8e3bcc1 --- /dev/null +++ b/Notes.md @@ -0,0 +1,38 @@ +# How to publish + +## Pypi + +Create update: + +1) Change version number in [pyproject.toml](pyproject.toml) +2) Create new package and upload: + +```bash +# build: will create files in dist/ +poetry build +# test: install .whl file +pip install dist/scoary_2-*-py3-none-any.whl +# upload +poetry publish +``` + +## Docker / Podman + +If you use docker, simply replace each `podman` with `docker`. + +```shell +podman build --tag troder/scoary-2 . +``` + +Publish docker image: + +```shell +# podman login docker.io --get-login +# podman login docker.io +podman tag troder/scoary-2 troder/scoary-2: +podman push troder/scoary-2: + +# update tag 'latest' +podman tag troder/scoary-2 troder/scoary-2:latest +podman push troder/scoary-2:latest +``` diff --git a/README.md b/README.md index ed26100..f996285 100644 --- a/README.md +++ b/README.md @@ -57,6 +57,10 @@ docker run \ /bin/bash ``` +# Overview of the algorithm + +![algorithm flowchart](media/ScoaryWorkflow.drawio.svg) + # Todo: - [X] Binarize traits during multiprocessing diff --git a/media/ScoaryWorkflow.drawio.svg b/media/ScoaryWorkflow.drawio.svg new file mode 100644 index 0000000..4a82bdf --- /dev/null +++ b/media/ScoaryWorkflow.drawio.svg @@ -0,0 +1,4 @@ + + + +calculate_confidence_intervalTrait data
Binary traits
Binary traits
Numeric traits
Numeric traitsGene data
Binary matrix
(Roary)
Binary matrix(Roary)
Gene matrix
(Orthofinder)
Gene matrix...
VCF
format
VCF...
Trait matrix
(boolean)
Trait matrix...
Gene matrix
(boolean)
Gene matrix...
load_traits
load_traits
load_genes
load_genes
pair_picking
pair_picking
for each
trait
for each...init_result_dfindex: genesadd col: contingency tableadd col: specificityadd col: sensitivityPhylogeny data(optional)
Newick file
Newick file
Tree object
(ScoaryTree class)
Tree object...
parse_newick
parse_newick
ScoaryTree.prune
ScoaryTree.prunecreate_test_dfindex: contingency tableadd col: Fisher-unique tablesadd col: Fisher's pvalue
add_odds_ratio
add_odds_ratio
perform_multiple_testing_correction
(initial filtration on Fisher's pvalue)
perform_multiple_testing_correction(...
merge test_df and result_df
(left outer join on contingency table)
merge test_df and result_df...
for each
gene
for eachgene
permute_trait
permute_trait
pair_picking
pair_picking
empirical pvalue
empirical pvaluecreate_summarycalculate dendrograminteractive output (html/js)
Speed up using...

faster algorithm

numba

caching

parallel
Speed up using......
Trait output
(tsv, html)
Trait output...
Summary
(html)
Summary...ScoaryTree \.from_presence_absencehemming distancesupgma algorithmsave_trait_resultinteractive output (html/js)Text is not SVG - cannot display \ No newline at end of file diff --git a/pyproject.toml b/pyproject.toml index d0b4e89..10d16aa 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "scoary-2" -version = "0.0.2" +version = "0.0.3" description = "Scoary 2: Associate genes with traits!" authors = ["MrTomRod "] license = "GPL3"