Nitro Bio

Real-time context-aware protein search is here! We are thrilled to release Gaia ??, a gLM2-powered search tool for microbial protein sequence annotation and exploration. Give it a try and let us know what you think! https://gaia.tatta.bio Learn more: https://lnkd.in/gaXW2Ves Blog: https://lnkd.in/gs6T9MJQ

Today we're open-sourcing DGEB, the first large-scale functional evaluation benchmark for biological language models ?? DGEB fills a key gap in BioML by providing diverse functional benchmarks for assessing pLM and gLM representations. We address two critical problems in existing functional evals: 1) Bias in evaluation datasets and 2) Lack of evaluations that assess functional relationships *between* genomic elements. Biology is incredibly diverse, yet biological research is biased towards a few model organisms. Foundation models of biology must learn from data across the tree of life. Existing evaluations using only model organisms perpetuate this bias, hindering diverse discovery and design.DGEB features 18 expert-curated datasets that span all three domains of life! ?????? For underrepresented taxa (e.g. #Archaea), we find that model performance is poor and do not improve with scaling, highlighting a key limitation of existing models. Inferring biological function requires understanding the evolutionary and functional relationships *between* biomolecules. DGEB features multi-sequence tasks, allowing us to ask questions such as how well do learned embedding distances recapitulate phylogenetic distances? Can we use pLMs to retrieve bacterial homologs given archaeal proteins? Do pLMs learn co-regulatory interactions or distinguish paralogs from orthologs? Can multi-element functions (e.g. biosynthetic gene clusters) be captured in representations? DGEB is inspired by NLP benchmarks, in particular MTEB from Hugging Face. Our field can only progress with transparent, collaborative and diversified evaluation datasets. We encourage the contribution of expert-curated datasets through our github repo: https://lnkd.in/gHJ_WWsT This was a true multi-disciplinary effort by our team at Tata Bio: Jacob West-Roberts Joshua Kravitz Nishant J. and Andre Cornman. This work is made possible with generous support by Schmidt Futures! Read our manuscript at: https://www.tatta.bio/dgeb

?? We're extremely excited to announce the results of our 2023 Bits in Bio Survey! This year's Bits in Bio survey offers a comprehensive look into the evolving landscape of biodevelopers, revealing critical trends and tools shaping the field. Take a look at the results here: https://lnkd.in/gwy2VZ8W (thanks to Nitro Bio for webdev help). A few key findings here, but make sure to take a look at the full results yourself. A Diverse Community: 76% of our respondents are biodevelopers, showcasing a blend of coding expertise within the life sciences sector. The diversity extends beyond roles, with participants hailing from across the globe—25% from outside the US—and bringing a wide range of educational backgrounds to the table. Python Leads the Way: Dominating the toolkit of biodevelopers, Python is used by 93% for data analysis, pipeline development, and more, highlighting its critical role in bioinformatics workflows. The Central Role of Data Analysis: With 41% engaging in data analysis daily, it's clear that handling and interpreting data is a cornerstone of bioinformatics. Despite new technologies, CSV remains the predominant data format, underscoring the need for accessible and straightforward data management solutions. Machine Learning's Growing Influence: 64% of biodevelopers now integrate machine learning into their work, with applications ranging from target identification to protein folding, using advanced tools like GPT4 and Alphafold. The interest in ML is set to increase, with 77% of those not currently using it looking to explore its potential. Lab Automation on the Rise: The survey indicates a significant shift towards lab automation, with 37% of respondents developing tools to enhance experimental efficiency and accuracy. Bits in Bio will continue to be the leading voice for biodevelopers in the modern biotech world -- no matter where you are located or what your background is.