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.

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

This is a fixed term post for 36 months.

We wish to recruit a highly motivated, postdoctoral scientist to carry out a BBSRC funded project in the laboratory of Dr. Denis Larkin. The project is focused on developing and applying new algorithms to study genome and chromosome evolution in birds, mammals and other vertebrate species using whole-genome sequences and existing algorithms. The post holder will use cutting edge computational and laboratory approaches to generate chromosomal assemblies for sequenced genomes, study chromosomal structures and genome differences between bird and other vertebrate species in attempt to identify species- and clade-specific genome signatures.

Applicants must have a Ph.D. and a track record of success, as indicated by first-author publications in international journals. They must possess excellent organisation skills and be capable of individual initiative and of interacting as part of a team. Applicants with extensive practical experience in bioinformatics or computer science, programming, visualization, handling of large data sets, high-performance computing are encouraged to apply. The post will involve collaboration with a wide range of academic partners both within the UK, EU and worldwide. In addition to leading their own project the post holder will have opportunities to contribute to multiple international genome initiatives.

Experience in programming, bioinformatics and comparative genome analysis is essential. Applicants should have a minimum of a degree and preferably a higher degree in a relevant subject.

The Royal Veterinary College has the largest range of veterinary, para-veterinary and animal science undergraduate and postgraduate courses of any veterinary school in the world and is one of the largest veterinary schools in Europe.

Prospective applicants are encouraged to contact Dr. Denis Larkin, Comparative Biomedical Sciences Department on +442071211906 or email: dlarkin@rvc.ac.uk

We offer a generous reward package.

For further information and to apply on-line please visit our website: www.rvc.ac.uk
Job reference CBS-0025-14A

Closing date: 4 July 2014
Interviews are likely to be held in July 2014

We promote equality of opportunity and diversity within the workplace and welcome applications from all sections of the community.

Current computational interests:

Systematic analysis of genetic epistasis to identify redundant or compensatory systems and to reveal order of action in genetic pathways.
Using knockout, knockdown, or overexpression, or other perturbation experiments in combinations of genes in S. cerevisiae, C. elegans or mouse.
Using genome-scale genotyping of natural polymorphisms in S. cerevisiae and human populations.
Alternative splicing and its relationship to protein interaction networks.
Integrating large-scale studies including phenotype, genetic epistasis, protein-protein and transcription-regulatory interactions and sequence patterns to quantitatively assign function to genes and guide experimentation.

More at http://llama.mshri.on.ca/index.html

minimap -t 24 assembly.fasta long_reads.fastq.gz | racon -t 24 long_reads.fastq.gz - assembly.fasta racon_assembly.fasta
nucmer -p nucmer assembly.fasta racon_assembly.fasta
show-snps -C -T -r nucmer.delta

This reports Racon's changes in a table. You can exclude indels with the -I option in show-snps. 

This process (Racon -> MUMmer -> SNP table) solves the problem I originally raised in this issue. So as far as I'm concerned, you can close this issue (or keep it open if you still want to implement some kind of variant table).

usage:   canu [-correct | -trim | -assemble | -trim-assemble] \
              [-s ] \
               -p  \
               -d  \
               genomeSize=[g|m|k] \
               -maxThreads=2 \
               useGrid=false \
              [other-options] \
               read_file.fastq.gz

A default Canu run produces usually high quality assembly, example of a command that was used for testing can be found below. However, there are still a lot of parameters that are possible to tweak. For example if we desire to assemble haplotypes separately of if we want to smash them together, we can alternate the error correction process.

canu -p test_asmbl \
     -d asm_test3 \
     genomeSize=2m \
     -maxThreads=2 useGrid=false \
     -pacbio-raw \ ~/pacbio/dna/sample_reads.fastq.gz

There is a brilliant section in documentation about parameter tweaking.

The output directory contains will contain many files. The most interesting ones are:

• *.correctedReads.fasta.gz : file containing the input sequences after correction, trim and split based on consensus evidence.
• *.trimmedReads.fastq : file containing the sequences after correction and final trimming
• *.layout : file containing informations about read inclusion in the final assembly
• *.gfa : file containing the assembly graph by Canu
• *.contigs.fasta : file containing everything that could be assembled and is part of the primary assembly

The basic stats of assembly can be read from reports generated by the assembler, or calculated using standard UNIX command line tools.

More at https://canu.readthedocs.io/en/latest/faq.html

No of vacancies: 01

Pay scale:Rs. 15600 – 39100 + 6600/-

Essential Academic Qualifications / Experience : Good academic record as defined by the concerned university with at least 55% marks (or an equivalent grade in a point scale wherever grading system is followed) at the Master's Degree level in a relevant subject from an Indian University, or an equivalent degree from an accredited foreign university.

Besides fulfilling the above qualifications, the candidate must have cleared the National Eligibility Test (NET) conducted by the UGC, CSIR or similar test accredited by the UGC like SLET/ SET.

Notwithstanding anything contained in sub-clauses (a) and (b) to this Clause, candidates, who are, or have been awarded a Ph.D. Degree in accordance with the University Grants Commission (Minimum Standards and Procedure for Award of Ph.D. Degree) Regulations, 2009, shall be exempted from the requirement of the minimum eligibility condition of NET/SLET/SET for recruitment and appointment of Assistant Professor or equivalent positions in Universities/Colleges/Institutions.

NET/SLET/SET shall also not be required for such Masters Programmes in disciplines for which NET/SLET/SET is not conducted.

Apply online: http://www.psc.cg.gov.in/htm/OA_ME2014.html

Last Date for Online Registration: 22/05/2014

For more details: http://www.psc.cg.gov.in/pdf/Advertisement/ADV_ME2014.pdf

https://academic.oup.com/nar/article/47/11/e63/5377471

Address of the bookmark: https://github.com/linzhi2013/MitoZ

More at http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1000369

Address of the bookmark: http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1000369

ftp://ftp.ncbi.nih.gov/genomes/

https://hgdownload.soe.ucsc.edu/downloads.html

Address of the bookmark: ftp://ftp.ncbi.nih.gov/genomes/