nealgravindra Goto Github PK
Name: Neal G. Ravindra
Type: User
Bio: ML research scientist developing new methods to study biology / medicine + other things; #AI4science
Location: Bay Area
Name: Neal G. Ravindra
Type: User
Bio: ML research scientist developing new methods to study biology / medicine + other things; #AI4science
Location: Bay Area
Using biological priors (previously selected important features or "markers"), assign cell types to clusters based on differential discriminability of cell type markers
CONditional DENSity Embedding for unsupervised characterization of gene dynamics
CSI developed in the early days, published in https://www.annemergmed.com/article/S0196-0644(20)30588-6/fulltext
The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of drugs, learns interpretable embeddings, estimates dose-response curves, and provides uncertainty estimates.
How to diffuse a profile into a shared space for recommendations? Should we use supervised learning and feature attribution or variance metrics for perturbation profiles? How to evaluate this approach?
use of a permutation invariant network to encode probability distributions
3 month-ish thematic modules to keep up with new developments in other fields -- blogging, writing a textbook, implementing code from scratch
implementations of papers from scratch
GNN-based single-cell gene expression analysis
The Harmonized Pre-processing Toolkit for Dementia Bank
Playground for new computational implementations in order to appropriately tweak and transition to personal prj dev
Geometric Deep Learning Extension Library for PyTorch
need to read more papers gahhh
Code to reproduce results in Ravindra NG* & Sehanobish A* et al. 2020, "Disease State Prediction From Single-Cell Data Using Graph Attention Networks" to appear in ACM Proceedings. <https://arxiv.org/abs/2002.07128>
tutorial for Cell paper
copy of bo wang lab scGPT repo from 240604
neurodegeneration and single-cell omics
code for "Self-supervised edge features for improved Graph Neural Network training", <arxivlink>
Learning how life's languages are expressed
composite scores for indexed descriptions to target document(s)
Code to reproduce results of Tejwani L* and Ravindra NG* et al. 2020
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.