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.

GLEAN: an unsupervised learning system to integrate disparate sources of gene structure evidence

Poonam Mahapatra — Sat, 02 Jun 2018 07:38:33 -0500

GLEAN is an unsupervised learning system to integrate disparate sources of gene structure evidence (gene model predictions, EST/protein genomic sequence alignments, SAGE/peptide tags, etc) to produce a consensus gene prediction, without prior training.

Address of the bookmark: https://sourceforge.net/projects/glean-gene/

GeneOverlap: An R package to test and visualize gene overlaps

Jit — Thu, 27 Dec 2018 19:45:52 -0600

Overlapping gene lists can reveal biological meanings and may lead to novel hypotheses. For example, histone modification is an important cellular mechanism that can pack and re-pack chromatin. By making the chromatin structure more dense or loose, the gene expression can be turned on or off. Tri-methylation on lysine 4 of histone H3 (H3K4me3) is associated with gene activation and its genome-wide enrichment can be mapped by using ChIP-seq experiments. Because of its activating role, if we overlap the genes that are bound by H3K4me3 with the genes that are highly expressed, we should expect a positive association. Similary, we can perform such kind of overlapping between the gene lists of different histone modifications with that of various expression groups and establish each histone modification’s role in gene regulation.

Address of the bookmark: https://bioconductor.org/packages/release/bioc/vignettes/GeneOverlap/inst/doc/GeneOverlap.pdf

ShadowCaster: a hybrid approach for the detection of horizontal gene transfer events in prokaryotes

Jit — Tue, 14 Jul 2020 06:42:10 -0500

ShadowCaster implements an evolutionary model to calculate Bayesian likelihoods for each ‘alien genes’ with an unusual sequence composition according to the host genome background to detect HGT events in prokaryotes.

https://www.mdpi.com/2073-4425/11/7/756/htm

https://shadowcaster.readthedocs.io/en/latest/

https://github.com/dani2s/ShadowCaster_testData

Address of the bookmark: https://github.com/dani2s/ShadowCaster

GenomeQC: a quality assessment tool for genome assemblies and gene structure annotations

Neel — Thu, 19 May 2022 04:29:05 -0500

The GenomeQC web application is implemented in R/Shiny version 1.5.9 and Python 3.6 and is freely available at https://genomeqc.maizegdb.org/ under the GPL license. All source code and a containerized version of the GenomeQC pipeline is available in the GitHub repository https://github.com/HuffordLab/GenomeQC.

https://bmcgenomics.biomedcentral.com/articles/10.1186/s12864-020-6568-2

Address of the bookmark: https://github.com/HuffordLab/GenomeQC

CAR: Reconstructing Contiguous Regions of an Ancestral Genome

Abhimanyu Singh — Thu, 18 May 2017 05:24:01 -0500

We describe a new method for predicting the ancestral order and orientation of those intervals from their observed adjacencies in modern species. We combine the results from this method with data from chromosome painting experiments to produce a map of an early mammalian genome that accounts for 96.8% of the available human genome sequence data. The precision is further increased by mapping inversions as small as 31 bp. Analysis of the predicted evolutionary breakpoints in the human lineage confirms certain published observations but disagrees with others. Although only a few mammalian genomes are currently sequenced to high precision, our theoretical analyses and computer simulations indicate that our results are reasonably accurate and that they will become highly accurate in the foreseeable future. Our methods were developed as part of a project to reconstruct the genome sequence of the last ancestor of human, dogs, and most other placental mammals;

Address of the bookmark: http://www.bx.psu.edu/miller_lab/car/

REGEN: Ancestral Genome Reconstruction for Bacteria

Rahul Nayak — Tue, 06 Mar 2018 05:02:36 -0600

REGEN infers evolutionary events, including gene creation and deletion and replicon fission and fusion. The reconstruction can be performed by either a maximum parsimony or a maximum likelihood method. Gene content reconstruction is based on the concept of neighboring gene pairs. REGEN was designed to be used with any set of genomes that are sufficiently related, which will usually be the case for bacteria within the same taxonomic order.

Address of the bookmark: http://www.mdpi.com/2073-4425/3/3/423

Ancestral sequence reconstruction steps !

Surabhi Chaudhary — Fri, 18 May 2018 08:28:26 -0500

Ancestral sequence reconstruction (ASR) – also known as ancestral gene/sequence reconstruction/resurrection – is a technique used in the study of molecular evolution. The method consists of the synthesis of an ancestral gene and expression of the corresponding ancestral protein. The idea of protein 'resurrection' was suggested in 1963 by Pauling and Zuckerkandl. Some early efforts were made in the eighties-nineties, led by the laboratory of Steven A. Benner, showing the potential of this technique – one that only started to be fulfilled in the post-genomic era. Thanks to the improvement of algorithms and of better sequencing and synthesis techniques, the method was developed further in the early 2000s to allow the resurrection of a greater variety of and much more ancient genes. Over the last decade, ancestral protein resurrection has developed as a strategy to reveal the mechanisms and dynamics of protein evolution.

BEAST is the best way to predict the ancestral structure. but, I suggest following steps?

1- Alignments "Mafft - http://mafft.cbrc.jp/alignment/software/source.html"

mafft --maxiterate 1000 --reorder --thread 24 --genafpair Dataset.fasta > Dataset_Alig.fasta

2- Your dataset has a good phylogenetic signal, is possible to perform with Tree-Puzzle "http://www.tree-puzzle.de";

3 - This dataset which the saturation index, I perform with "http://dambe.bio.uottawa.ca/dambe.asp";

4- Has evidence of possible recombination in your dataset, the evaluate if this presence or absence, because this may to influence the grouping of clades, I perform with

---recombination

4.1- Phi-test, implemented in SplitTree4"http://www.splitstree.org", (.nex file)

4.2- GARD deployed in webserver in the DataMonkey "http://www.datamonkey.org/" - turning to the amino acid seaview -> view proteins -> save as ...) Ideally do a tree-based groups.

4.3- RDP4 for download and installation on Windows in "http://web.cbio.uct.ac.za/~darren/rdp.html"

4.4- Hyphy (Mac, Windows, Linux) in "http://hyphy.org/w/index.php/Download"

4.5- Path-o-Gen (temporal structure of a tree input file -> arquivo.tre)

These steps above, I call of pre-processing to inferences phylogenetic...

5- Perform phylogenetic tree, used Bayesian Inference with Molecular Clock, but is necessary Clock Testing:

- This step is performed with program Beast (Beauti, Beast and TreeAnnotator), and Tracer_v1.5 more FigTree to inspection.

- Tutorials: http://beast.bio.ed.ac.uk/tutorials

- Downloads: http://beast.bio.ed.ac.uk/downloads

AlignGraph: algorithm for secondary de novo genome assembly guided by closely related references

Manisha Mishra — Tue, 17 Apr 2018 16:21:20 -0500

AlignGraph is a software that extends and joins contigs or scaffolds by reassembling them with help provided by a reference genome of a closely related organism.

Using AlignGraph

AlignGraph --read1 reads_1.fa --read2 reads_2.fa --contig contigs.fa --genome genome.fa --distanceLow distanceLow --distanceHigh distancehigh --extendedContig extendedContigs.fa --remainingContig remainingContigs.fa [--kMer k --insertVariation insertVariation --coverage coverage --part p --fastMap --ratioCheck --iterativeMap --misassemblyRemoval --resume]

Address of the bookmark: https://github.com/baoe/AlignGraph

Hercules: a profile HMM-based hybrid error correction algorithm for long reads

Jit — Mon, 20 Aug 2018 14:14:11 -0500

Choosing whether to use second or third generation sequencing platforms can lead to trade-offs between accuracy and read length. Several studies require long and accurate reads including de novo assembly, fusion and structural variation detection. In such cases researchers often combine both technologies and the more erroneous long reads are corrected using the short reads. Current approaches rely on various graph based alignment techniques and do not take the error profile of the underlying technology into account. Memory- and time- efficient machine learning algorithms that address these shortcomings have the potential to achieve better and more accurate integration of these two technologies. Results: We designed and developed Hercules, the first machine learning-based long read error correction algorithm. The algorithm models every long read as a profile Hidden Markov Model with respect to the underlying platformtextquoterights error profile. The algorithm learns a posterior transition/emission probability distribution for each long read and uses this to correct errors in these reads. Using datasets from two DNA-seq BAC clones (CH17-157L1 and CH17-227A2), and human brain cerebellum polyA RNA-seq, we show that Hercules-corrected reads have the highest mapping rate among all competing algorithms and highest accuracy when most of the basepairs of a long read are covered with short reads. Availability:

Hercules source code is available at https://github.com/BilkentCompGen/Hercules

Address of the bookmark: https://github.com/BilkentCompGen/Hercules