MAGIC
Data Imputer
An algorithm for denoising high-dimensional biological data by learning the manifold structure of the data using graph imputation
MAGIC (Markov Affinity-based Graph Imputation of Cells), is a method for imputing missing values restoring structure of large biological datasets.
345 stars
22 watching
97 forks
Language: Jupyter Notebook
last commit: about 2 months ago
Linked from 1 awesome list
seandavi/awesome-single-cellRelated projects:
| Repository | Description | Stars |
|---|---|---|
 xinychen/transdim | Develops machine learning models to handle incomplete transportation data and make accurate predictions | 1,216 |
 philkr/magic_init | This code provides an initialization method for convolutional neural networks based on data-dependent parameters. | 138 |
| krishnaswamylab/phate | A tool for visualizing high-dimensional biological data using a novel dimensionality reduction method | 475 |
 zwang-lab/g2s3 | An imputation method that applies graph signal processing to extract gene structure from scRNA-seq data and recover true expression levels by borrowing information from adjacent genes. | 3 |
 bimsbbioinfo/netsmooth | Improves single cell RNA-seq data by smoothing out noise using prior information from gene interaction networks | 27 |
 indigits/sparse-plex | A collection of algorithms and techniques for exploiting sparse data representations to solve various problems in signal processing and machine learning. | 98 |
 h3abionet/chipimputation | An imputation workflow tool for genomics data analysis | 20 |
 mims-harvard/decagon | An open-source software project implementing a graph convolutional neural network algorithm to predict side effects of drug combinations in pharmacology. | 449 |
 jiupinjia/neural-magic-eye | Training an image processing neural network to recover depth and content from autostereograms | 72 |
 benedekrozemberczki/tene | A sparsity-aware implementation of a deep learning algorithm for graph embedding with text information. | 73 |
 dialnd/imbalanced-algorithms | A collection of algorithms and implementations for handling imbalanced data in machine learning | 235 |
 yuqifan1117/hallucidoctor | This project provides tools and frameworks to mitigate hallucinatory toxicity in visual instruction data, allowing researchers to fine-tune MLLM models on specific datasets. | 41 |
 xjtushujun/meta-weight-net | An implementation of a meta-learning algorithm to improve sample weighting in classification tasks with noisy labels. | 281 |
| benedekrozemberczki/bane | A software implementation of a graph embedding algorithm | 86 |
 ekmett/bound | Combinators for manipulating locally-nameless generalized de Bruijn terms | 122 |