search

nrnb / GoogleSummerOfCode

Main documentation site for NRNB GSoC project ideas and resources
114 stars 38 forks source link

Machine Learning support for constructing maps from scratch in Newt #231

Closed ugurdogrusoz closed 2 months ago

ugurdogrusoz commented 5 months ago

Background

Newt [1] is a Cytoscape.js [2] based, open source viewer and editor for pathways in Systems Biological Graphical Notation (SBGN) [3] and Simple Interaction Format (SIF). It's been built (with partial support from GSoC) around an editing library named ChiSE, which in turn was based on a viewer library named SBGNViz [4]. The tool uses a number of Cytoscape.js extensions built for various editing capabilities such as grid-guidelines, context-menus, and expand-collapse.

[1] H. Balci et al., "Newt: a comprehensive web-based tool for viewing, constructing, and analysing biological maps", Bioinformatics, 37(10), pp.1475-1477, 2021. [2] M. Franz et al. "Cytoscape. js 2023 update: a graph theory library for visualization and analysis.", Bioinformatics 39.1, btad031, 2023. [3] N. Le Novère et al., "The Systems Biology Graphical Notation", Nature Biotechnology, 27, pp. 735-741, 2009. [4] M. Sari et al., "SBGNViz: a tool for visualisation and complexity management of SBGN process description maps", PLoS ONE, 10(6), e0128985, 2015.

Goal

The goal of this project is to enable users to describe the interactions in a pathway textually rather than having to learn how to use Newt and its strict notation. Then an ML-based agent will interpret this text and produce the corresponding partial map. The user may or may not add the suggested partial map to the current drawing.

Difficulty Level: Hard

This project will require learning several repositories as well as some new ML components built for constructing pathways.

Size and Length of Project

Skills

Essential skills: JavaScript, HTML, CSS, Java Nice to have skills: Cytoscape.js and ML libraries

Public Repository

Newt GitHub repository ChiSE GitHub repository SBGNViz.js GitHub repository

Potential Mentors

Ugur Dogrusoz Adrien Rougny

vigasinii commented 4 months ago

Greetings Sir, @ugurdogrusoz, I'm Vigasini currently pursuing computer science and I am excited about the opportunity to contribute to this issue. To address these challenges, I plan to leverage my knowledge in JavaScript, HTML, CSS, and Java to develop a robust solution. I will explore existing ML libraries to train and deploy a model capable of understanding textual pathway descriptions. The integration with Newt will involve developing custom interfaces and APIs to facilitate communication between the ML agent and the platform. I look forward to the possibility of discussing how I can contribute to your team further.

khanspers commented 4 months ago

NRNB has been accepted as a mentoring organization for GSoC 2024. The contributor application period is March 18 – April 2. Here are some useful links:

GSoC contributor guide NRNB project proposal template Eligibility requirements Full program timeline

143divya commented 4 months ago

is this project still open?. because i want to work on this project

Ankita3503 commented 3 months ago

Hi @ugurdogrusoz . I am excited to contribute to your project . Can you please guide me how to leverage my knowledge in Cytoscape.js extensions . It will be very helpful in contributing the project before starting my work in this new tech.

Hoping to hear from you .

renu-123-pixel commented 2 months ago

i want to work on this issue . please assign me this issue.

khanspers commented 2 months ago

@Ankita3503 and @renu-123-pixel : FYI, the application period for GSoC is closed already and we are currently evaluating applicants.

khanspers commented 2 months ago

This is an active GSoC 2024 project. Closing this project idea as it is no longer available to other contributors.