GithubHelp home page GithubHelp logo

amatov / fragmentomicssubclinicaldisease Goto Github PK

View Code? Open in Web Editor NEW
0.0 1.0 0.0 305 KB

Home Page: https://www.researchgate.net/publication/374059465_Classification_of_Genome-Wide_cfDNA_Fragmentation_Patterns_with_Deep_Learning_2020_-_2021

R 87.37% TeX 3.55% Python 9.08%
breast-cancer gastric-cancer lung-cancer ovarian-cancer pancreatic-cancer bile-duct-cancer duodenal-cancer colon-adenoma colon-cancer deep-learning

fragmentomicssubclinicaldisease's Introduction

Utilization of cfDNA fragment size patterns ​for disease detection & classification ​based on low-coverage WGS data

Presentations and clinical applications on this project (Classification of Genome-Wide cfDNA Fragmentation Patterns with Deep Learning) are available here: http://dx.doi.org/10.13140/RG.2.2.34819.89121/1 (5 PDF files)

We consider the relative entropy between cohorts’ cfDNA fragment lengths and test two hypotheses.

  1. We can pinpoint particular lengths for which disease differs from healthy.

  2. We can identify distinct differences for colorectal (CRC) as well as other cancer types (ovarian, pancreatic, gastric, breast, lung cancer and cholangiocarcinoma).

Preliminary Kullback-Leibler divergence (PMC5812299) analysis of the Delfi (PMC6774252) data shows:

  1. Cancer vs healthy:
  • Healthy individuals and cancer patients exhibit differences for particular fragment lengths (classification of new clinical samples and early detection of disease).
  • We measure two to three peaks (see KLD_CRC_FRL.pdf) on the divergence histogram (identify the disease stage).
  1. Cancer vs cancer:
  • CRC patients and other cancers exhibit differences for particular fragment lengths (identify the tissue of origin).
  • At least 8% of the fragments belong to diverging populations (determine the degree of overlap between the regulation of different tumors).

The Delfi 2 / Endo II cohort consisted of samples from clinical trials NCT03637686, NCT03748680, NCT04084249

fragmentomicssubclinicaldisease's People

Contributors

amatov avatar

Watchers

 avatar

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.