Library

A new deep learning model called AESTETIK successfully integrates spatial, RNA, and morphology data from spatial transcriptomics to improve tissue clustering and analysis.

Researchers developed a biochip system called ENDO-Genome that attaches to standard endoscopes to safely extract and map RNA directly from living human internal organs without causing bleeding.

Researchers created a comprehensive single-cell spatial map of human skin across 15 body sites, revealing how specific cellular neighborhoods maintain skin health and are disrupted in disease.

Researchers developed a microscopy-based method to measure the survival of specific cell types in mixed neuroblastoma samples, allowing for more accurate testing of cancer drugs.

This review explores how machine learning and deep learning are being used to improve the early diagnosis and treatment of mental health disorders while highlighting the ethical and technical challenges involved.

Meta2DB is a newly developed, highly curated database of microbiome data and metadata designed to help train machine learning models for predicting human health conditions.

Researchers developed two new modeling approaches that use microbial genetic data to accurately simulate how groundwater bacteria remove nitrogen pollution.

This paper introduces computational methods from genomics and systems biology to build diverse and efficient clinical benchmarks for evaluating artificial intelligence.

Researchers developed ROCKET, a tool that combines AlphaFold2's predictive power with experimental data to automatically build accurate protein structures, even from low-resolution or noisy datasets.

Researchers developed StarFunc, a new tool that successfully combines deep learning with multiple types of template data, including structural similarity, to more accurately predict what proteins do.

The Single-Cell Pediatric Cancer Atlas Portal provides researchers with a large, uniformly processed collection of single-cell RNA sequencing data from various childhood tumors.

BioMaster is a new multi-agent artificial intelligence system that automates complex, multi-step bioinformatics workflows with high accuracy and efficiency.