tldrdailynews.com logo
Tag

Bioinformatics

All articles tagged with #bioinformatics

New Deep Learning Method VIMA Identifies Disease-Specific Spatial Patterns in Tissues
science-and-technology2 days ago

New Deep Learning Method VIMA Identifies Disease-Specific Spatial Patterns in Tissues

Researchers have introduced VIMA, a new computational method that uses deep learning to analyze spatial molecular data in tissues. By creating numerical 'fingerprints' for small tissue patches, VIMA identifies disease-associated structures without requiring manual cell segmentation or discrete clustering. Tested on rheumatoid arthritis, ulcerative colitis, and dementia datasets, the tool successfully recapitulated known biology and revealed new spatial features, outperforming existing methods in detecting case-control differences.

via Nature|
#bioinformatics#diagnostics#machine-learning
From papers to interactive AI agents: a framework for reproducible, queryable science
technology23 days ago

From papers to interactive AI agents: a framework for reproducible, queryable science

A new framework called Paper2Agent converts scientific papers into autonomous AI agents by packaging a paper’s manuscript, data, code and workflows into a Model Context Protocol (MCP) server and linking it to chat agents; case studies with AlphaGenome, Scanpy, and TISSUE show agents reproduce results and handle novel, user-asked analyses, lowering barriers to adoption and enabling collaborative AI co-scientists.

via Nature|
#ai-agents#bioinformatics#model-context-protocol
Malva: a Google-like RNA search across millions of cells in seconds
health1 month ago

Malva: a Google-like RNA search across millions of cells in seconds

Malva is a Google‑like RNA search engine that indexes over 140 TB of public single‑cell and spatial transcriptomics data, enabling rapid, sequence‑based queries across millions of cells without downloading raw data or using a reference genome; it can reveal mutations, RNA isoforms, pathogens and more in seconds to minutes, potentially accelerating cancer and infection research, though it currently requires exact 24‑nucleotide matches and ongoing validation.

via The Brighter Side of News|
#bioinformatics#cell-atlas#health
AlphaFold Opens a Free Global Library of Protein Shapes
science2 months ago

AlphaFold Opens a Free Global Library of Protein Shapes

AI-powered AlphaFold2 transformed protein folding by predicting 3D structures from sequence in minutes, leading to a public database with roughly 214 million predicted protein structures available for free. Most entries are highly accurate or confidently useful, but about a fifth have low confidence and users should filter by pLDDT. The data is CC-BY-4.0 licensed and widely used, enabling rapid research while raising questions about openness for future commercial tools and the handling of multiple conformations and disordered regions. Ongoing updates include isoforms and alignments; methods like AF-Cluster have had mixed results in extracting alternative conformations.

via Space Daily|
#alphafold#bioinformatics#deepmind
AlphaFold’s database adds protein pairs to map how molecules work together
technology6 months ago

AlphaFold’s database adds protein pairs to map how molecules work together

AlphaFold’s database now includes 1.7 million predicted homodimer protein complexes, expanding its 200 million monomer structures to show how two copies of the same protein interact. The complex predictions were produced by a international consortium and are freely accessible via EMBL-EBI, broadening the resource’s biological and medical relevance across 20 studied species.

via Nature|
#alphafold#bioinformatics#homodimer
Evo 2: An Open-Source AI for Genome-Scale Prediction and Design Across Life
science7 months ago

Evo 2: An Open-Source AI for Genome-Scale Prediction and Design Across Life

Evo 2 is a large, open biological foundation model trained on 9 trillion base pairs across all life, with a 1‑million‑token context, available in 7B and 40B sizes. It predicts mutational effects on DNA, RNA and proteins without task-specific fine-tuning, can generate genome-scale sequences and chromatin-accessibility designs, and supports exon–intron annotation and variant-effect prediction across diverse species. The model and data (OpenGenome2) are fully open-source, with training/inference code and tools (Evo Designer, Evo Mech Interp), plus safety safeguards such as virus-data exclusions to mitigate misuse.

via Nature|
#artificial-intelligence#bioinformatics#genome-design
Evo: The AI Revolutionizing Genetic Prediction and Design
science-and-technology1 year ago

Evo: The AI Revolutionizing Genetic Prediction and Design

Scientists have developed Evo, a machine learning model that predicts the effects of genetic mutations and generates new DNA sequences with high accuracy. Unlike traditional large language models, Evo is trained on microbial genomes, using base pairs as "words" to analyze genetic patterns. While Evo shows promise in understanding DNA and RNA functions, it currently lacks the ability to predict human genetic mutations. The researchers emphasize the importance of ethical guidelines to prevent misuse as the technology advances.

via Livescience.com|
#ai#bioinformatics#dna