Kevin McKernan

CellAgent ushers in the 'Agent for Science' era! 🚀 Researchers from Northwestern Polytechnical University introduced a ground-breaking tool, #CellAgent, that may change how single-cell RNA sequencing (scRNA-seq) data is analyzed. 🎯 CellAgent is an LLM-driven multi-agent framework for #Automated #scRNAseq data analysis. It delivers high-quality results with no human intervention, transforming cellular heterogeneity research. Quick Read: https://lnkd.in/gHvKjycw #bioinformatics #scRNAseq #dataanalysis #ngs #ai #llm #singlecell #automation #sciencenews

2

1 Comment

Single Transcript Unit Surrogate Reporter (STU-SR) systems to enhance the selection of genome-edited plants https://lnkd.in/eevaDBt5

7

1 Comment

Researching on applying large language models to genomics is booming - so much so that this team from University of California, Berkeley has written a survey paper https://lnkd.in/gW9XgBY7 covering 30 different models. (And this must be big because genomics models have their own acronym now 🤣) "Large language models (LLMs) are having transformative impacts across a wide range of scientific fields, particularly in the biomedical sciences. Just as the goal of Natural Language Processing is to understand sequences of words, a major objective in biology is to understand biological sequences." "Genomic Language Models (gLMs), which are LLMs trained on DNA sequences, have the potential to significantly advance our understanding of genomes and how DNA elements at various scales interact to give rise to complex functions." "In this review, we showcase this potential by highlighting key applications of gLMs, including fitness prediction, sequence design, and transfer learning." "One of the key pillars of this development is self-supervised learning, in which training on massive amounts of unlabeled data enables the learning of complex features and their interactions." There should already be a gLM on a li'l GPU in every Illumina sequencer! (my post from a year ago 😠 https://lnkd.in/gGk4cA6h) Then Illumina could have announced a deal with NVIDIA and be one of the cool kids like Thermo Fisher Scientific this week 🥳 (or...Molly He? Francisco Garcia? ElementAI 🤣)

76

7 Comments

𝐓𝐨𝐝𝐚𝐲'𝐬 𝐭𝐨𝐩𝐢𝐜 : 𝐎𝐩𝐞𝐧𝐂𝐑𝐈𝐒𝐏𝐑-𝟏 : 𝐅𝐢𝐫𝐬𝐭 𝐨𝐩𝐞𝐧 𝐬𝐨𝐮𝐫𝐜𝐞 𝐀𝐈 𝐭𝐨 𝐞𝐝𝐢𝐭 𝐠𝐞𝐧𝐞𝐬 In the dynamic field of biological sciences, Artificial Intelligence (AI) is pushing boundaries by delving into the realm of human DNA editing. This intersection of AI and genetics holds immense promise for revolutionizing medical treatments and disease management. 𝐖𝐡𝐚𝐭 𝐢𝐬 𝐎𝐩𝐞𝐧𝐂𝐑𝐈𝐒𝐏𝐑-𝟏? Profluent introduces OpenCRISPR-1, the world’s first open-source, AI-generated gene editor, marking a significant milestone in precision genetic editing. 𝐁𝐚𝐬𝐢𝐜 𝐅𝐞𝐚𝐭𝐮𝐫𝐞𝐬 𝐚𝐧𝐝 𝐀𝐝𝐯𝐚𝐧𝐭𝐚𝐠𝐞𝐬 : Through sophisticated AI algorithms, Profluent leverages vast biological data to design customizable gene editors, promising unparalleled precision in editing the human genome. The technology’s potential to revolutionize disease treatment is vast, offering unprecedented efficiency and accuracy in targeting genetic abnormalities. OpenCRISPR-1's open-source nature facilitates collaboration and innovation by making the technology freely available to researchers, academic institutions, and companies. By drawing insights from natural CRISPR mechanisms, Profluent’s AI creates novel gene editors, optimizing biological processes for therapeutic applications. 𝐅𝐮𝐭𝐮𝐫𝐞 𝐩𝐫𝐨𝐬𝐩𝐞𝐜𝐭𝐬 : Profluent’s groundbreaking initiative represents a pivotal convergence of AI and biological sciences, promising transformative advancements in genetic editing and healthcare. As OpenCRISPR-1 undergoes rigorous testing and collaborative refinement, it sets the stage for a future where AI-driven innovations redefine the landscape of medical research and treatment, offering hope for improved health outcomes worldwide. To read more : https://lnkd.in/dPVPyYuu Website : https://www.profluent.bio/ Follow ✎Arindom Roy✎ for more interesting knowledge. https://lnkd.in/dvU4NjfK  #artificialintelligence #AI #geneediting #humangenome #dnaediting #opencrispr1 #profluent #molecularbiology #newsletter #sciencecommunication #linkedinfamily #linkedinforcreators #followformore Video credits : Profluent (https://lnkd.in/dTWuQcza)

24

2 Comments

Coming from a family with a high prevalence of autism, I fully understand that it is a spectrum disorder. Many individuals on the spectrum, especially those who have learned to mask or adapt, may struggle to envision a different life (raises hand). However, there are also many others who would do anything to alleviate or manage the challenges they face—challenges that, at their most severe, can leave individuals non-verbal or hinder their ability to engage socially, secure employment, or achieve independence. I look forward to reading this paper, along with the others to come, whilst also refreshing my knowledge of RNAseq workflows.

3

Scientists unveil #GeneRAG: A new framework enhancing LLMs' gene analysis capabilities. GeneRAG outperforms GPT-3.5 and GPT-4 in gene-related tasks, showcasing the power of Retrieval-Augmented Generation in genomics. Quick Read: https://lnkd.in/gyiyM28F #bioinformatics #LLMs #AIinBiology #datascience #ai #sciencenews

8

Amazing seeing an entire new field of bioinformatics emerging and evolving so rapidly from pLM -> gLM -> cLM: "The discrete and sequential nature of biological sequences, such as proteins or DNA and RNA, paired with the abundance of unlabeled data, obtained through high-throughput sequencing, make it a perfect application for [generative AI] methods to thrive. This effort started first in proteomics [pLMs], where several works showed that training large Transformer models to recover masked amino acids in protein sequences leads to powerful representations that can then be used to solve diverse downstream tasks with state-of-the-art performance." "More recently, similar models were developed for genomics [gLMs] and trained over the human reference genome as well as hundreds of reference genomes from different species to recover masked consecutive nucleotides in chunks." "Motivated by the central dogma of biology which states that the genome encodes all protein information, and by the fact that codon usage can influence protein structure and function, a third class of models, codon language models (cLMs), was recently introduced." Summary of the paper (ChatGPT): Key relationships between gLMs, pLMs, and cLMs: 1. Genomic Language Models (gLMs): • gLMs are trained on full genomes, which include both coding (exons) and non-coding regions (introns). This makes them highly suitable for general genomic tasks. However, the ability of gLMs to predict protein-related tasks is less understood because only a small fraction of genomic sequences directly encode proteins. • The paper finds that gLMs can indeed perform competitively on protein tasks when carefully curated coding sequences (CDS) are provided. They even outperform pLMs on some tasks like protein melting point prediction. 2. Protein Language Models (pLMs): • pLMs are trained specifically on amino acid sequences and are thus highly specialized for protein-related tasks. Their tokenization is based on amino acids, making them directly suited for tasks like predicting protein structure and function. • On tasks that require fine-grained protein information, such as secondary structure prediction and beta-lactamase activity prediction, pLMs generally outperform gLMs. 3. Codon Language Models (cLMs): • cLMs are an intermediate approach that tokenize on codons (three nucleotides that encode an amino acid). They focus on capturing patterns of codon usage, which can affect protein expression and function. • In some tasks, particularly those sensitive to codon-level changes, cLMs have shown better performance than pLMs, indicating the importance of codon usage in protein behavior.

35

Multiplexed CRISPR-Cas9 mutagenesis of rice PSBS1 noncoding sequences for transgene-free overexpression https://lnkd.in/eJA-4j-K

4

Generation and Application of Epigenetic Mouse Models Epigenetic mouse models have become an important tool for studying how epigenetic modifications (heritable changes in gene expression that do not involve changes in DNA sequence) affect development, disease, and treatment response. Epigenetic changes (such as DNA methylation, histone modifications, and non-coding RNA regulation) play a crucial role in gene regulation, so epigenetic mouse models are essential for understanding complex diseases such as cancer, neurodegenerative diseases, and metabolic diseases. 1. Generation of epigenetic mouse models: Epigenetic mouse models are usually generated by one of the following methods: (1) Gene Editing Technology: Technologies such as CRISPR/Cas9 are used to target and modify specific genes involved in epigenetic regulation, such as DNMTs (DNA methyltransferases) that control DNA methylation or HDACs (histone deacetylases) that regulate histone modifications. (2) Conditional Knockout: By selectively knocking out or modifying genes in specific tissues or certain developmental stages, researchers can study how epigenetic changes affect tissue-specific gene regulation. This is particularly useful for diseases such as cancer and neurodegenerative diseases. (3) Transgenic mice: Transgenic models overexpress or inhibit specific epigenetic regulators to understand their role in development and disease progression. 2. Applications of epigenetic mouse models: Epigenetic mouse models have many applications in biomedical research: (1) Cancer research: Epigenetic alterations, such as abnormal methylation patterns, play a key role in tumor progression. Mouse models help researchers study how these changes promote cancer and explore potential epigenetic therapies. (2) Neurodegenerative diseases: Epigenetic models allow researchers to study the role of chromatin remodeling and DNA methylation in diseases such as Alzheimer's and Parkinson's. (3) Developmental studies: Epigenetic mouse models are used to study how epigenetic marks affect embryonic development and lead to congenital diseases. These mouse models are essential for developing epigenetic therapies that can reverse or modify harmful epigenetic changes in human diseases. References [1] Takuro Horii et al., Epigenetics Chromatin 2022 (10.1186/s13072-022-00474-3) [2] Matthew Gemberling et al., Nature Methods 2021 (https://lnkd.in/eKehdZTk) [3] Raquel Pace et al., Journal of Genetics 2018 (10.4236/ojgen.2018.83007) #EpigeneticModels #MouseModels #CRISPR #DNA #HistoneModifications #CancerResearch #NeurodegenerativeDiseases #Epigenetics #GeneEditing #BiomedicalResearch #TherapeuticDevelopment #DiseaseModeling #ResearchInnovation #Newsletter #ScientificBreakthroughs

21

How to use Google Gemini multi-modal to write math formulas in Latex without writing in Latex https://lnkd.in/g3A2AqX8

5

And that 👉 https://lnkd.in/giNXhs-7 is why folks designing and building plasmids or strains should instead use GitLife Biotech's tech to document in full their engineering process!

19

You wouldn't build a house with one tool, so why build proteins that way? The EntoEngine is the first biomanufacturing platform for proteins that expands the protein production toolkit to >200 distinct cell types (i.e. the tools). This enables production of the most complex proteins that traditional systems fail to express. Bravo to our team of brilliant geneticists Anzer Khan, Connor Davis, and Sophie Keegan that put together this informative article on benefits of our Drosophila genetics toolkit.

29

Human permeability by high-throughput MS methods...

2

ScienceDirect Public acceptance of the use of Far-UVC for virus inactivation: Challenges and opportunities https://lnkd.in/gxynhqG7. Abstract Objectives There is an urgent need for technologies which can reduce the impact of airborne disease transmission. Far-UVC (200–230 nm) is a range of wavelengths growing in relevance for airborne virus disinfection in occupied public spaces. Methods  Outcome measures included how safe respondents would feel with or without Far-UVC in indoor spaces and how acceptable the technology would be in certain indoor spaces. Results There were 111 respondents to the survey. The median age range of the respondents was 36–45, most respondents had never studied biology or related science subjects beyond school level (68%, n = 76), and 87% (n = 97) were indoor workers or attended formal education. Less than one-third of respondents had heard of the term ‘Far-UVC’. Though, on learning about the core principles of Far-UVC, respondents became more supportive of its use in public spaces. Acceptance of Far-UVC was strongest in areas where a higher benefit-risk ratio was perceived, such as in hospitals. Conclusion We have shown that when the basic concepts of Far-UVC are clearly communicated, public opinion on its adoption improves. Without such a general understanding amongst members of the public, Far-UVC may then face challenges in gaining widespread adoption. What is your opinion of (222nm) Far UV?  I would like to know, please leave a comment here or at [email protected]. #222nm #faruvc #cleanindoorair #sterilray

2

Scalable querying of human cell atlases via a foundational model reveals commonalities across fibrosis-associated macrophages https://lnkd.in/eQMVCqRU github https://lnkd.in/eHZz8UR4

67

µMap proximity labeling in living cells reveals stress granule disassembly mechanisms https://lnkd.in/e5WQyVee

20

DICE: Fast and Accurate Distance-Based Reconstruction of Single-Cell Copy Number Phylogenies https://lnkd.in/ey2rRMup

8

GGNBP2 regulates MDA5 sensing triggered by self double-stranded RNA following loss of ADAR1 editing https://lnkd.in/e8kvGGrg