CBIRT, Centre of Bioinformatics Research & Tech’s Post

Artificial intelligence #ai #bioinformatics

ɢᴇɴᴇɢᴘᴛ: Answering Genomics Questions 🧬 Scientists from the National Library of Medicine (NLM), The National Institutes of Health, and University of Maryland , College Park, US, have presented this Large Language Models (LLM) that is trained to use the Web APIs of the National Center for Biotechnology Information (NCBI) for generating answers to genomic questions. ɢᴇɴᴇɢᴘᴛ is largely surpassing retrieval-augmented LLMs (Bing), biomedical LLMs (BioMedLM and BioGPT) as well as GPT-3 and ChatGPT. NCBI provides API access to its entire biomedical databases and tools, including Entrez Programming Utilities (E-utils) and BLAST URL API. E-utils API accesses the Entrez portal that covers 38 NCBI databases of biomedical data such as genes and proteins. The BLAST API allows users to submit queries to assess similarities between nucleotide or protein sequences to existing databases using the BLAST algorithm on NCBI servers 🔥 🔗https://lnkd.in/geFshgBj . . . #ai #breakthrough #ncbi #blast #tools #database #algorithm #bioinformatics #genomics #biotechnology #biomedical #gene #protein

Improving Protein Function Prediction: The Power of ProtEx As biology delves deeper into the intricate world of proteins, understanding their functions becomes increasingly paramount. Proteins, the workhorses of organisms, play multifaceted roles, and categorizing these roles accurately is no small feat. Enter ProtEx, a cutting-edge solution developed by a collaborative effort from Google DeepMind, Google, and the University of Cambridge. This groundbreaking method combines the prowess of retrieval-based techniques with deep learning to revolutionize protein function prediction. https://is.gd/ExflKM #AI #artificialintelligence #Biotechnology #llm #machinelearning #protein #ProtEx

Single-cell GPT has just been published in Nature Methods: https://lnkd.in/gSt82WQx Generative pretrained models have achieved remarkable success in various domains such as language and computer vision. Specifically, the combination of large-scale diverse datasets and pretrained transformers has emerged as a promising approach for developing foundation models. Drawing parallels between language and cellular biology (in which texts comprise words; similarly, cells are defined by genes), this study probes the applicability of foundation models to advance cellular biology and genetic research. Using burgeoning single-cell sequencing data, we have constructed a foundation model for single-cell biology, scGPT, based on a generative pretrained transformer across a repository of over 33 million cells. Congrats to Haotian Cui, Bo Wang and the entire team! #mylliabio

🤔 Are you ready for this amazing webinar today? Have a clearer idea as to what AI & ML is today! 👩💻Exploring the Future Career Scope of AI & ML in Biology - Live Webinar 👉 Set Your Reminders Here: https://lnkd.in/gDx_RzBy

📊 Reviving Single-Cell Data Imputation: cnnImpute 🧬 Mary Qu Yang's article in Scientific Reports introduces cnnImpute, a new stride in scRNA-seq data analysis. 🌟 Key Takeaways: 🟡 cnnImpute employs a convolutional neural network (CNN) for missing value recovery in scRNA-seq data. 🟡 It estimates missing probabilities, then uses a CNN model for expression value recovery. 🟡 Proven to accurately impute missing values, maintaining cell cluster integrity in scRNA-seq data. 🟡 Offers an accurate, scalable solution for comprehensive scRNA-seq analysis. 🔗 Read more: [https://buff.ly/3TlXBS0] 📢 Join the Conversation 📢 Share your thoughts, methods, and tools in the comments 👇 💬 #SingleCellAnalysis #Bioinformatics #DataImputation #scRNAseq #Genomics

🚀𝐓𝐡𝐞 𝐅𝐮𝐭𝐮𝐫𝐞 𝐨𝐟 𝐁𝐢𝐨𝐢𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐜𝐬: 𝐄𝐦𝐛𝐫𝐚𝐜𝐢𝐧𝐠 𝐀𝐈 𝐓𝐫𝐚𝐧𝐬𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧🤖🔬 In the rapidly evolving world of bioinformatics, Artificial Intelligence (AI) is not here to replace us but to revolutionize our approach to understanding complex biological data. 🌟 🤝 𝘐𝘯𝘵𝘦𝘨𝘳𝘢𝘵𝘪𝘯𝘨 𝘈𝘐 𝘪𝘯𝘵𝘰 𝘣𝘪𝘰𝘪𝘯𝘧𝘰𝘳𝘮𝘢𝘵𝘪𝘤𝘴 𝘰𝘱𝘦𝘯𝘴 𝘶𝘱 𝘪𝘯𝘤𝘳𝘦𝘥𝘪𝘣𝘭𝘦 𝘱𝘰𝘴𝘴𝘪𝘣𝘪𝘭𝘪𝘵𝘪𝘦𝘴 𝘢𝘯𝘥 𝘩𝘪𝘨𝘩𝘭𝘪𝘨𝘩𝘵𝘴 𝘵𝘩𝘦 𝘪𝘮𝘱𝘰𝘳𝘵𝘢𝘯𝘤𝘦 𝘰𝘧 𝘩𝘶𝘮𝘢𝘯 𝘰𝘷𝘦𝘳𝘴𝘪𝘨𝘩𝘵 𝘢𝘯𝘥 𝘤𝘳𝘦𝘢𝘵𝘪𝘷𝘪𝘵𝘺. 𝘖𝘶𝘳 𝘳𝘰𝘭𝘦 𝘪𝘴 𝘵𝘰 𝘨𝘶𝘪𝘥𝘦 𝘈𝘐, 𝘷𝘢𝘭𝘪𝘥𝘢𝘵𝘦 𝘪𝘵𝘴 𝘧𝘪𝘯𝘥𝘪𝘯𝘨𝘴, 𝘢𝘯𝘥 𝘮𝘢𝘬𝘦 𝘦𝘵𝘩𝘪𝘤𝘢𝘭 𝘥𝘦𝘤𝘪𝘴𝘪𝘰𝘯𝘴, 𝘦𝘯𝘴𝘶𝘳𝘪𝘯𝘨 𝘵𝘩𝘢𝘵 𝘵𝘦𝘤𝘩𝘯𝘰𝘭𝘰𝘨𝘪𝘤𝘢𝘭 𝘢𝘥𝘷𝘢𝘯𝘤𝘦𝘮𝘦𝘯𝘵𝘴 𝘣𝘦𝘯𝘦𝘧𝘪𝘵 𝘴𝘰𝘤𝘪𝘦𝘵𝘺. 👇 Add your thoughts in the comment below! #Bioinformatics #ArtificialIntelligence #AI #MachineLearning #DrugDiscovery #Genomics #PredictiveModeling #Innovation #FutureOfWork

🔬 The latest version of DeepMind's AlphaFold exhibits markedly enhanced precision, it now tackles a wider array of biological molecules, including ligands. A remarkable leap in understanding molecular structures! Quick Read: https://lnkd.in/g9tZJQkV #Bioinformatics #AlphaFold #AF2 #StructuralBiology #deeplearning #AI

Read #NewPaper "A Probabilistic Result on Impulsive Noise Reduction in Topological Data Analysis through Group Equivariant Non-Expansive Operators" from Patrizio Frosini et al. https://lnkd.in/g7U6PvNA The paper is part of the research contributing to building a bridge between TDA and Geometric Deep Learning. It shows how GENEOs might make TDA stable when data are affected by impulsive noise.

By 2025, we'll need 40 exabytes to store all human genome data! 🧬 That's 8x more than what's needed to record every word ever spoken. Another one of the challenges lies in decoding the 100GB+ of data each genome generates – a task that demands the power of accelerated computing, data science, and AI. AI is revolutionizing the speed and accuracy of genome sequencing. With deep learning technology, base calling, and DNA sequence alignment become faster and more precise. This advancement allows for the ultrafast and accurate identification of genetic variations, enhancing our understanding of genetics and improving medical research and diagnosis. More here: https://lnkd.in/dkTrbbds