BOL: Related items

NVIDIA and Arc Institute Unveil Evo 2: A Breakthrough AI for DNA Design

BioStar — Fri, 21 Feb 2025 10:39:47 -0600

NVIDIA and the Arc Institute have introduced Evo 2, a groundbreaking AI model designed to understand, predict, and generate DNA sequences. This marks a major advancement in computational biology, offering scientists an unprecedented tool to decode the genetic blueprint of life and even design entirely new biological systems.

The Power of Evo 2: AI Meets DNA

Evo 2 is the largest AI model for biology ever created, trained on an astonishing 9.3 trillion DNA "letters" (nucleotides) carefully selected from genomes spanning the entire tree of life. This massive dataset ensures that Evo 2 can recognize patterns and relationships in genetic sequences at an unparalleled scale.

For the first time, scientists can design DNA with AI, moving beyond simple sequence analysis to active DNA generation. Evo 2 enables researchers to predict, modify, and even create entire genetic sequences, opening new possibilities in medicine, agriculture, and synthetic biology.

Decoding the Dark Genome

One of the biggest challenges in genetics is understanding the non-coding regions of DNA—vast stretches of the genome that do not code for proteins but play crucial roles in regulating gene expression. These regions control when and how genes are activated, influencing everything from development to disease.

Evo 2 is designed to decode these non-coding elements, helping researchers uncover their functions and use this knowledge to develop gene-based therapies, synthetic life forms, and precision agriculture solutions.

From Reading DNA to Writing It

To put Evo 2’s impact into perspective:

Previous AI models could "read" DNA like a book, analyzing genetic sequences and identifying patterns.
Evo 2 can "write" entirely new DNA, designing functional genes, chromosomes, and even full genomes from scratch.

This means scientists can now engineer biological systems with AI, designing new proteins, metabolic pathways, and genetic circuits to address real-world challenges.

A Step Toward Generative Biology

The Arc Institute describes Evo 2 as a major step toward "generative biology"—a revolutionary approach where AI is used to create novel biological structures rather than just analyzing existing ones. This could lead to breakthroughs such as:

New medicines: AI-generated enzymes and proteins tailored for targeted therapies.
Disease-resistant crops: Genetically optimized plants for higher yield and climate resilience.
Synthetic organisms: Custom-designed microbes for bioremediation, biofuel production, and industrial applications.

An Open-Source Revolution

Unlike many proprietary AI models, Evo 2 is open source, making its capabilities accessible to researchers worldwide. This democratization of AI-driven biology means that scientists from different disciplines can collaborate, experiment, and innovate, accelerating discoveries in genetic engineering and synthetic biology.

With Evo 2, the boundaries of what’s possible in DNA design, genetic engineering, and biological innovation are being redrawn. The future of life sciences is no longer just about understanding life’s code—it’s about writing it.

Genome Origami

Jitendra Narayan — Fri, 12 Dec 2014 22:48:17 -0600

There are several interesting factoid about our genomes, one of them is their folding. If we stretched out the DNA in a single cell, which is only a few millionths of an inch wide, it would span more than six feet. In other word, the size of six feet DNA fold themself to fit in a few millionths of an inch wide space. These DNA folding is a dynamic process that changes over time (!!). Researchers around the world have been trying to understand how DNA folds itself up so efficiently, and a recent post on the NIH Director’s Blog highlights new research illustrating how the human genome folds inside the cell’s nucleus, as well as how DNA folding affects gene regulation. The research team created this delightful video that demonstrates the principles involved using origami art.

http://bioinformaticsonline.com/videolist/watch/19555/a-3d-map-of-the-human-genome

Researchers have been working to determine how cells regulate gene expression for nearly as long as we’ve known about DNA. How, for example, do nerve cells know to turn off only nerve cell genes and turn off bone cell genes? DNA folding loops are part of the answer. This research team, which published their findings in a paper in Cell http://www.cell.com/cell/abstract/S0092-8674%2814%2901497-4 , found that the number of loops is much lower than expected. There are only 10,000 loops instead of the predicted millions, and they form on/off switches in DNA.

More at http://www.eurekalert.org/pub_releases/2014-12/ru-3mr121114.php

Reference http://www.cell.com/cell/abstract/S0092-8674%2814%2901497-4

TRRUST v2: an expanded reference database of human and mouse transcriptional regulatory interactions

Rahul Agarwal — Thu, 21 Dec 2017 17:01:44 -0600

TRRUST contains 8,444 and 6,552 TF-target regulatory relationships of 800 human TFs and 828 mouse TFs, respectively. They have been derived from 11,237 pubmed articles, which describe small-scale experimental studies of transcriptional regulations. To efficiently search for regulatory relationships from over 20 million pubmed articles, we used sentence-based text mining approach.

TRRUST database also provides information of mode of regulation (activation or repression). Currently 8,972 (59.8%) regulatory relationships are known for mode of regulation.

Search at : http://www.grnpedia.org/trrust/Network_search_form.php

Address of the bookmark: http://www.grnpedia.org/trrust/

destruct

Jitendra Prajapati — Mon, 29 Feb 2016 17:34:59 -0600

Destruct is a tool for joint prediction of rearrangement breakpoints from single or multiple tumour samples.

More at https://bitbucket.org/dranew/destruct

Address of the bookmark: https://bitbucket.org/dranew/destruct

SVfinder: Tool for detecting genomic rearrangement form DNA-seq data

Robert M Willioms — Thu, 14 Dec 2017 15:51:40 -0600

SVfinder provides genome-wide detection of structural variants from next generation paired-end sequencing reads.

Address of the bookmark: https://github.com/cauyrd/SVfinder

DNA is packaged in a chromosome experiment

Mon, 23 Sep 2013 18:01:12 -0500

For more information, log on to- http://shomusbiology.weebly.com/ Download the study materials here- http://shomusbiology.weebly.com/bio-materials.html A nucleosome is the basic unit of DNA packaging in eukaryotes, consisting of a segment of DNA wound in sequence around four histone protein cores.[1] This structure is often compared to thread wrapped around a spool.[2] Nucleosomes form the fundamental repeating units of eukaryotic chromatin,[3] which is used to pack the large eukaryotic genomes into the nucleus while still ensuring appropriate access to it (in mammalian cells approximately 2 m of linear DNA have to be packed into a nucleus of roughly 10 µm diameter). Nucleosomes are folded through a series of successively higher order structures to eventually form a chromosome; this both compacts DNA and creates an added layer of regulatory control, which ensures correct gene expression. Nucleosomes are thought to carry epigenetically inherited information in the form of covalent modifications of their core histones. Nucleosomes were observed as particles in the electron microscope by Don and Ada Olins [4] and their existence and structure (as histone octamers surrounded by approximately 200 base pairs of DNA) were proposed by Roger Kornberg.[5][6] The role of the nucleosome as a general gene repressor was demonstrated by Lorch et al. in vitro [7] and by Han and Grunstein in vivo.

Kamaleshwar Singh Lab

Fri, 25 Mar 2016 10:46:49 -0500

The focus of Dr. Singh’s research and teaching is on the molecular mechanistic basis for environmental carcinogen-induced genetic (DNA damage) and epigenetic changes, and susceptibility to human cancer development

More at http://www.tiehh.ttu.edu/dr.-kamaleshwar-singh.html

fineSTRUCTURE v2 & GLOBETROTTER

Shruti Paniwala — Mon, 13 Feb 2017 08:40:23 -0600

Software available at this site

FineSTRUCTURE version 2, a pipeline for running ChromoPainter and FineSTRUCTURE for population inference. A GUI is available for interpretation. Download from the Downloads page.
FineSTRUCTURE R scripts, a facility for exploring the results when the GUI is unavailable.
GLOBETROTTER, the admixture dating method based on ChromoPainter. Download from the Downloads page.
AdmixturePainting, A set of R tools to inmterpret the results of ADMIXTURE and STRUCTURE-like mixture models.
RADpainter, finestructure and ChromoPainter for RAD tag data used for non-model organisms.
Scripts to perform many types of conversion. Included in the main software download from the Downloads page.

What this page is This page provides information about and downloads for methodology for Chromosome Painting. It is not a facility to analyse your genome. Sorry if you were misled by the punchy name!
About Chromosome Painting Painting is an efficient way of identifying important haplotype information from dense genotype data. It describes ancestry in an efficient way suitable for a range of further analyses, including population identification and admixture dating.

Address of the bookmark: http://paintmychromosomes.com/

ChromHMM: Chromatin state discovery and characterization

Abhimanyu Singh — Wed, 19 Apr 2017 04:06:23 -0500

ChromHMM is software for learning and characterizing chromatin states. ChromHMM can integrate multiple chromatin datasets such as ChIP-seq data of various histone modifications to discover de novo the major re-occuring combinatorial and spatial patterns of marks. ChromHMM is based on a multivariate Hidden Markov Model that explicitly models the presence or absence of each chromatin mark. The resulting model can then be used to systematically annotate a genome in one or more cell types. By automatically computing state enrichments for large-scale functional and annotation datasets ChromHMM facilitates the biological characterization of each state. ChromHMM also produces files with genome-wide maps of chromatin state annotations that can be directly visualized in a genome browser.

Address of the bookmark: http://compbio.mit.edu/ChromHMM/

Useful links to therapy, disease, drug and drug-target network data:

Jit — Mon, 01 Jun 2020 11:47:51 -0500

Useful links to therapy, disease, drug and drug-target network data:

DrugBank:

a bioinformatics- cheminformatics resource combining detailed drug data with comprehensive drug target information with >4900 drug (~3500 experimental) and >1500 non-redundant protein entries http://www.drugbank.ca/

Drug-Target Network:

network data of 890 drugs and 394 target human proteins http://www.nature.com/nbt/journal/v25/ n10/suppinfo/nbt1338_S1.html

Drug-Therapy Network:

three layers of drug-therapy networks according to the ATC classification http://www.biomedcentral.com/1471-2210/8/5/additional/

FDA Orange Book:

approved drug products with therapeutic equivalence evaluations http://www.fda.gov/cder/ob/HIDdb: Thomson Investigational drugs database including information on 107000 patents, 25000 investigational drugs and 80000 chemical structures http://scientific.thomson.com/products/iddb/HOMIM: a knowledgebase of human genes and genetic disorders http://www.ncbi.nlm.nih.gov/ sites/entrez?db=omim

PDTD:

3D drug target structure database with a target identification option http://www.dddc.ac.cn/pdtd/

Predicted drug targets:

a set of 1383 predicted drug targets http://www.biomedcentral.com/1471-2105/8/353/additional/ [25] Protein ligand network: a network of 4208 ligands and ~15000 binding sites http://pbil.kaist.ac.kr/~parkkw/Lnet/

TDR Targets Database:

identification and ranking targets against neglected tropical diseases http://tdrtargets.org/

Therapeutic Target Database:

lists >1500 therapeutic targets, disease conditions and corresponding drugs http://xin.cz3.nus.edu.sg/group/cjttd/ttd.asp