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.

Sequence Viewer: Download Transcripts, Exons and Proteins

Mon, 15 Sep 2014 17:30:36 -0500

How to download FASTA sequence for certain gene features while in the NCBI's Sequence Viewer. Sequence Viewer homepage: www.ncbi.nlm.nih.gov/projects/sviewer/ Sequence Viewer playlist: https://www.youtube.com/playlist?list=PL76D7EE6A6A8AC1C3

Narcis Fernandez-Fuentes Lab

Mon, 25 May 2015 07:30:00 -0500

Welcome to our web-site compiling all the research-related activities of the group. Our research interests relate to a number of areas within Bioinformatics. We have a long-standing interest in protein structure prediction and structure-to-function relationships. We work in the study of biomolecular interactions, modeling of protein complexes, the study and characterization of protein-protein interactions, peptide design, modeling of genetic variation, structure-based protein design and different aspects of Plant Bioinformatics. Take a look at the our databases and servers and the list of publications for more information.

More at http://www.bioinsilico.org/

FOGSAA: Fast Optimal Global Sequence Alignment Algorithm

Jit — Fri, 08 Dec 2017 14:41:08 -0600

Sequence alignment algorithms are widely used to infer similarirty and the point of differences between pair of sequences. FOGSAA is a fast Global alignment algorithm. It is basically a branch and bound approach which starts branch expansion in a greedy way taking the symbols from the given pair of sequences (protein or nucleotide) and results in an optimal alignment faster than conventional dymanic programming techniques. It is also better than the heuristic methods with respect to alignment quality.

Address of the bookmark: http://www.isical.ac.in/~bioinfo_miu/FOGSAA.htm

medaka: Sequence correction provided by ONT Research

BioStar — Mon, 18 May 2020 16:28:00 -0500

medaka is a tool to create a consensus sequence from nanopore sequencing data. This task is performed using neural networks applied from a pileup of individual sequencing reads against a draft assembly. It outperforms graph-based methods operating on basecalled data, and can be competitive with state-of-the-art signal-based methods, whilst being much faster.

Address of the bookmark: https://github.com/nanoporetech/medaka

NCBIBLAST+ 2.14.1 now available

Neel — Wed, 30 Aug 2023 02:36:13 -0500

#NCBIBLAST+ 2.14.1 now available with improved documentation, faster and more reliable database downloads, and some bug fixes.

Check out the changes they made.

They added the cleanup-blastdb-volumes.py script to remove unused BLAST database volumes. Read the documentation here.

They also switched the protocol from ftp to https to access BLAST databases for increased performance and reliability when downloading data from the NCBI with the update_blastdb.pl script.

And fixed a few bugs related to downloading data from the NCBI, and mt_mode crashing blastn and blastx.

Check out the release notes.

Download BLAST+ 2.14.1

Questions or comments? Please write the BLAST help desk.

More info and download: https://blast.ncbi.nlm.nih.gov/doc/blast-news/2023-BLAST-News.html

Taxoblast : Taxoblast is a pipeline to identify contamination in genomic sequence

Jit — Thu, 23 Nov 2017 08:37:15 -0600

Modern genome sequencing strategies are highly sensitive to contamination making the detection of foreign DNA sequences an important part of analysis pipelines. Here we use Taxoblast, a simple pipeline with a graphical user interface, for the post-assembly detection of contaminating sequences in the published genome of the kelp Saccharina japonica. Analyses were based on multiple blastn searches with short sequence fragments. They revealed a number of probable bacterial contaminations as well as hybrid scaffolds that contain both bacterial and algal sequences. This or similar types of analysis, in combination with manual curation, may thus constitute a useful complement to standard bioinformatics analyses prior to submission of genomic data to public repositories. Our analysis pipeline is open-source and freely available at http://sdittami.altervista.org/taxoblast and via SourceForge (https://sourceforge.net/projects/taxoblast).

Address of the bookmark: https://sourceforge.net/projects/taxoblast/files/

Many-to-many pairwise alignments of two sequence sets

Poonam Mahapatra — Tue, 19 Jun 2018 08:34:15 -0500

needleall reads a set of input sequences and compares them all to one or more sequences, writing their optimal global sequence alignments to file. It uses the Needleman-Wunsch alignment algorithm to find the optimum alignment (including gaps) of two sequences along their entire length. The algorithm uses a dynamic programming method to ensure the alignment is optimum, by exploring all possible alignments and choosing the best. A scoring matrix is read that contains values for every possible residue or nucleotide match. Needleall finds the alignment with the maximum possible score where the score of an alignment is equal to the sum of the matches taken from the scoring matrix, minus penalties arising from opening and extending gaps in the aligned sequences. The substitution matrix and gap opening and extension penalties are user-specified.

Address of the bookmark: http://emboss.sourceforge.net/apps/release/6.6/emboss/apps/needleall.html

Wtdbg2: a de novo sequence assembler for long noisy reads produced by PacBio or Oxford Nanopore

Neel — Fri, 19 Oct 2018 08:48:43 -0500

Wtdbg2 is a de novo sequence assembler for long noisy reads produced by PacBio or Oxford Nanopore Technologies (ONT). It assembles raw reads without error correction and then builds the consensus from intermediate assembly output. Wtdbg2 is able to assemble the human and even the 32Gb Axolotl genome at a speed tens of times faster than CANU and FALCONwhile producing contigs of comparable base accuracy.

Address of the bookmark: https://github.com/ruanjue/wtdbg2

MSAProbs - Parallel and accurate multiple sequence alignment

Neel — Tue, 09 Jul 2019 23:58:44 -0500

MSAProbs is a well-established state-of-the-art multiple sequence alignment algorithm for protein sequences. The design of MSAProbs is based on a combination of pair hidden Markov models and partition functions to calculate posterior probabilities. Assessed using the popular benchmarks: BAliBASE, PREFAB, SABmark and OXBENCH, MSAProbs achieves statistically significant accuracy improvements over the existing top performing aligners, including ClustalW, MAFFT, MUSCLE, ProbCons and Probalign. In addition, MSAProbs is optimized for shared-memory CPUs by employing a multi-threaded design, and further parallelized for distributed-memory systems using MPI to overcome high memory overhead barrier and achieve good parallel and data-size scalability.

Address of the bookmark: http://msaprobs.sourceforge.net/homepage.htm#latest