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.

Reference

Cuccuru G1, Orsini M, Pinna A, Sbardellati A, Soranzo N, Travaglione A, Uva P, Zanetti G, Fotia G. (2014) Orione, a web-based framework for NGS analysis in microbiology. Bioinformatics [Epub ahead of print]. [article]

Address of the bookmark: http://orione.crs4.it/

Webinar on 'An integrated RNA and DNA approach to unravel genetic regulation in cancer'

Abstract

Whole exome DNA sequencing (WES) or whole genome DNA sequencing (WGS) allows detection of mutations and polymorphisms in all exonic and genomic regions, respectively, while messenger RNA sequencing (RNA-Seq) enables quantitative analysis of gene expression. Mutations in the genome result in diverse transcriptional aberrations that can be missed in a stand-alone WES/WGS analysis. An integration of DNA variant analysis and RNA-Seq analysis enables one to investigate the consequences of genomic changes in the RNA transcripts including germline and somatic changes, imprinting, RNA editing and allele specific expression (ASE). In this webinar, we will demonstrate this integrated approach using Strand NGS to identify high confidence mutations, RNA editing events and ASE in cancer.

Webinar Details

Register here: http://www.strand-ngs.com/webinar_registration

About Speaker:

Dr. Veena Hedatale, has a PhD in Plant Genetics from The Radboud University, Netherlands focused on meiosis and recombination. Her prior academic experience at Cornell University was on genetic mapping and gene transformation in Rice. She has worked with Monsanto, and contributed to data mining, database development as well as gene/promoter/pathway discovery for traits related to yield and stress in crop species. At Strand, Veena has worked on Pharmacogenomic analysis of targets and Gene family analysis projects. Currently, she is part of the Strand NGS Application Science team and is involved in the analysis of next generation sequencing data.

Please feel free to contact us 24/5, for availing free online training or if you have any questions.

Most people who have a balanced translocation have the right amount of chromosome material but it has been rearranged in some way. This may happen if two chromosomes swap pieces (a reciprocal translocation). In other cases two whole chromosomes may become stuck together (a Robertsonian translocation). This page describes what happens when someone has a reciprocal translocation.

Reciprocal chromosomal translocations occur following double-strand breaks (DSBs) in DNA when a section of one chromosome is exchanged with that of another, non-homologous chromosome. These exchanges may produce a dysfunctional fusion gene that disrupts cell growth and survival pathways, such as the translocations seen in leukemia and childhood sarcomas.

Chromosomal translocations have been well studied in cancer cell lines which are associated with two types of cancer, acute myeloid leukemia and Ewing's sarcoma, but determining how they contribute to cancer development is complicated by additional mutations and altered gene expression profiles in these cultured cells. Now, Juan Carlos Ramirez, head of the Viral Vector Facility at the Fundacion Centro Nacional de Investigaciones Cardiovasculares (CNIC) and his colleagues Raul Torres at CNIC and Sandra Rodriguez-Peralez at the Spanish National Cancer Center (CNIO) in Madrid, Spain have used a new genome editing tool, CRISPR-Cas9, to induce chromosomal translocations for the first time in a human cell line and in primary cells. The study's authors conclude by stating that the use of this technology will allow for the clarification of how and why chromosomal translocation occurs, which without doubt will allow new anti-cancer therapeutic strategies to be tackled.

Using RNA-Guided Endonuclease (RGEN) technology or CRISPR/Cas9 genome engineering technology, CNIO and CNIC researchers have shown that it is possible to obtain such chromosomal translocations. The CRISPR-Cas9 system is extremely simple to introduce a cut at the desired locus, easier to design, and cheaper than many other systems. Using the CRISPR-Cas9 system, Ramirez and his colleagues reproduced the translocations observed in Ewing’s Sarcoma (ES) and Acute Myeloid Leukemia (AML) patient cell lines in HEK293 cells and also generated the ES translocation in human mesenchymal stem cells and the AML translocation in umbilical cord blood cells.

By focusing on chromosomal translocation without the confounding characteristics of established cell lines, these new cells lines should help answer the fundamental question of what causes a cell to become cancerous. Ramirez and his team now look forward to modeling other chromosome translocations in a variety of cell types.

Reference:

http://en.wikipedia.org/wiki/Chromosomal_translocation

http://www.nature.com/ncomms/2014/140603/ncomms4964/abs/ncomms4964.html

Address of the bookmark: https://github.com/nedaz/kraken

Brief description: We are looking for suitable candidates in the area o computational biology/bioinformatics/genomics or related field for next-generation sequencing (NGS) data analysis for small-RNAs, RNA-Seq and targeted resequencing of plants and associated organisms. We are an interdisciplinary group where projects equally involve bioinformatics and systems biology (specially microarrays and next-generation sequencing (NGS) data analysis and its use), along with plant molecular biology, genetic engineering, field biology, and analytical plant chemistry for understanding response of plants to biotic stresses.

Essential qualification: MSc/BTech/MTech/PhD (or other suitable qualification) in disciplines preferable to bioinformatics, computational biology, computer application (or equivalent)/ ‘Advance Post-Graduate Diploma in Bioinformatics’. Proficiency in programming languages (such as Perl, C++) and/or statistics (proficient in R for example) is compulsory.

Desirable qualification: Experience in the field of genomics e.g. microarray analysis, NGS, genome annotation, database development and management, software development, systems and network biology (or related fields) will be preferred.

Application process: Applications should contain CV along with brief description (maximum 1 page) of research conducted (highlighting skills and experience) till now. Applications should be sent by e-mail to Shree Prakash Pandey, Department of Biological Sciences, Indian Institute of Science Education and Research Kolkata, Mohanpur Campus, WB, India within 14 days of this advertisement.

E-mail: sppiiserkol@gmail.com, sppandey@iiserkol.ac.in

Advertisement:

http://www.iiserkol.ac.in/announcements/adverts/671-advt_ra_shree_prakash_july_2014

Address of the bookmark: http://chmille4.github.io/Scribl/

Scientists with a long-running Framingham Heart Study looked at 1,932 people (examination of about 1.5 million markers of genetic variations), comparing unrelated friends to unrelated strangers. They found that friends shared about 1% of their genes — a percentage much higher than those shared with strangers.This new findings made it clear that people have more DNA in common with those who are selected as friends than with strangers in the same population. 

The genes that lined up the most were olfactory genes, which deal with smell. The ones that lined up the least were immune system genes. The researchers weren't sure why that happened :/. Olfactory genes might be a straightforward explanation: People who like the same smells tend to be drawn to similar environments, where they meet others with the same tendencies.

Reference:

http://www.pnas.org/content/111/Supplement_3/10796.full

Image : http://i.kinja-img.com

http://www.phyloxml.org/archaeopteryx-js/adh.html

Address of the bookmark: http://www.phyloxml.org/

Job Description: We are interested in finding an excellent postdoc with interests in protein functional annotation, machine learning and computer grids. The position is open for 3.5 years at the Université Pierre et Marie Curie, in the heart of paris.

Research topic: Protein function annotation, multiple probabilistic models, domain architecture, machine learning, combinatorial optimization, computer grid.

Title: A novel integrative platform for large scale protein annotation that exploits a multitude of diversified probabilistic models in several protein signature databases.

We propose a novel integrated approach for large scale protein annotation that will exploit an unprecedented amount of genomic data as well as sophisticated machine learning techniques and combinatorial optimization approaches taking advantages of High Performance Computing (HPC) environments. The idea is to uncover as much as possible the evolutionary processes of protein sequences that took place throughout the whole tree of life and that affected the evolution of a protein family. We have already demonstrated in a previous work that the problem of functional annotation is inherent to the ability of uncovering such paths. Now, we shall extend this approach to large scale genome annotation by considering 11 different protein databases, constituted by about 10^9 protein sequences, and by producing a large pool of diversified probabilistic models coding for about 10^7 evolutionary protein pathways. Such models will be used to search for specific domains in genomes to be annotated. Our previous methodology needs to be fundamentally improved to deal with this large amount of biological data. In this project, we shall work on the algorithms to reduce the space of models and the search complexity, and we shall implement some important algorithmic changes towards the realization of a powerful integrated annotation tool.

Where: This project is run on the Laboratoire de Biologie Computationnelle et Quantitative UMR7238 CNRS-UPMC – Analytical Genomics team, headed by A.Carbone. It is co-advised with Pierre-Henri Wuillemin, Laboratoire d’Informatique de Paris 6 – Equipe DECISION.

Start date: September 1st, 2014
Contact Person: Alessandra Carbone
Contact: alessandra.carbone@lip6.fr