Skip to main content

Weekly news #15

·4 mins

News #


Science/Bioinformatics #

Entropy subspace separation-based clustering for noise reduction (ENCORE) of scRNA-seq data #

Song et al., Nucleic Acids Research (2021)

#clustering #entropy

Single-cell RNA sequencing enables us to characterize the cellular heterogeneity in single cell resolution with the help of cell type identification algorithms. However, the noise inherent in single-cell RNA-sequencing data severely disturbs the accuracy of cell clustering, marker identification and visualization. We propose that clustering based on feature density profiles can distinguish informative features from noise. We named such strategy as ā€˜entropy subspaceā€™ separation and designed a cell clustering algorithm called ENtropy subspace separation-based Clustering for nOise REduction (ENCORE) by integrating the ā€˜entropy subspaceā€™ separation strategy with a consensus clustering method. We demonstrate that ENCORE performs superiorly on cell clustering and generates high-resolution visualization across 12 standard datasets. More importantly, ENCORE enables identification of group markers with biological significance from a hard-to-separate dataset. With the advantages of effective feature selection, improved clustering, accurate marker identification and high-resolution visualization, we present ENCORE to the community as an important tool for scRNA-seq data analysis to study cellular heterogeneity and discover group markers.

SNT: a unifying toolbox for quantification of neuronal anatomy #

Arshadi et al., Nat Methods (2021)

#framework #neurons

SNT is an end-to-end framework for neuronal morphometry and whole-brain connectomics that supports tracing, proof-editing, visualization, quantification and modeling of neuroanatomy. With an open architecture, a large user base, community-based documentation, support for complex imagery and several model organisms, SNT is a flexible resource for the broad neuroscience community. SNT is both a desktop application and multi-language scripting library, and it is available through the Fiji distribution of ImageJ.

How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals #

Wu et al., Nat Med (2021)

#curated-dataset

A comprehensive overview of medical AI devices approved by the US Food and Drug Administration sheds new light on limitations of the evaluation process that can mask vulnerabilities of devices when they are deployed on patients.

Analyzing genomic data in families with deep learning #

#google #deep-variant

The Genomics team at Google Health is excited to share our latest expansion to DeepVariant - DeepTrio.

A three-dimensional virtual mouse generates synthetic training data for behavioral analysis #

BolaƱos et al., Nat Methods (2021)

#mouse #model #3d

We developed a three-dimensional (3D) synthetic animated mouse based on computed tomography scans that is actuated using animation and semirandom, joint-constrained movements to generate synthetic behavioral data with ground-truth label locations. Image-domain translation produced realistic synthetic videos used to train two-dimensional (2D) and 3D pose estimation models with accuracy similar to typical manual training datasets. The outputs from the 3D model-based pose estimation yielded better definition of behavioral clusters than 2D videos and may facilitate automated ethological classification.


Programming #

Learn Go in ~5mins #

This is inspired by A half-hour to learn Rust and Zig in 30 minutes.

Loading SQL data into Pandas without running out of memory #

How to load huge SQL database using pandas without breaking the system.


Tools #

breuleux/jurigged #

Hot reloading for Python.

Dr-Noob/cpufetch #

Simple yet fancy CPU architecture fetching tool.

ory/keto #

Open Source (Go) implementation of “Zanzibar: Google’s Consistent, Global Authorization System”. Ships gRPC, REST APIs, newSQL, and an easy and granular permission language. Supports ACL, RBAC, and other access models.


Guides and Tutorials #

Using PyTorch + NumPy? You’re making a mistake. #

Must read for AI projects

How to make an awesome Python package in 2021 #

Personal recommendation

pretzelhammer’s Rust blog šŸ¦€ #

Educational blog posts for Rust beginners

Screw it, Iā€™ll host it myself #

Self hosted guide with de-google setup.

Best practices for writing SQL queries #

Tips on how to write better SQL statements from Metabase.


Others #

Breaking GitHub Private Pages for $35k #

Neuroscientists discover a molecular mechanism that allows memories to form #

Modifications to chromosomes in ā€œengramā€ neurons control the encoding and retrieval of memories.

Can Blood from Young People Slow Aging? Silicon Valley Has Bet Billions It Will #

Long read about hacking aging.

Google is now writing low-level Android code in Rust #

Rust making its way to android code base.


Did you know? #

61 year old women suffers from rare urinary auto-brewery syndrome