Coder Social home page Coder Social logo

cellpi's Introduction

CellPi

Under development, not ready for a general use, seem to perform well on gold-standard datasets English description and license will be uploaded with the first release

The main idea of this pipeline is to take best-practice scRNA-seq data preprocessind tools and integrate them in a fully unsupervised pipeline "from GSE id to cluster's markers"

GSE_id->read counts step will be based on the mixture of https://github.com/hms-dbmi/dropEst and https://github.com/CGATOxford/UMI-tools

Инструкция:
1) Установить пакеты через installer.Rmd
2) Загрузить все необходимые функции из Counts2Exprs.Pmd
3) Загрузить данные ориентируясь на примеры из Load_data.Rmd
4) Запустить основной анализ по примерам из Simple_Analyse.md
5) Если функция seur_find_multiplication выдаёт NULL, значит разбить кластер на суб-кластеры не удалось

Аннотация исходной матрицы клеток должна иметь формат: <тип_клетки>.<номер_клетки> 
( "d7.122" "d0.484" "d2.39"  "d2.213")
Для расстановки номеров можно воспользоваться функцией types2names, 
пример использования которой можно найти в модуле Load_data.Rds в функции load_sce

Исходная аннотация клеток не используется при кластеризации но может быть полезна 
для оценки качества итогового разбиения

Переменная окружения "R_MAX_NUM_DLLS 255" может понадобиться при запуске в Windows, если возникает ошибка 
"превышение максимального числа загруженных библиотек"

cellpi's People

Contributors

testaibot avatar

Stargazers

 avatar

Watchers

 avatar

cellpi's Issues

[feature] Lvl-specific dropout correction

Problem: DE genes search on initial step of SAVER removes rear landmark genes, making impute step useless.

Idea to consider: seurat's DE genes binned search

Possible solution: we have no prior information about real landmark genes and full dropout correction is time-consuming, possible solution is to group genes by nZero percentage, making assumption, that zeroes are mainly real zeroes, rather dropout events

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.