Nick Tarazona, MD’s Post

👉🏼 Bioinformatics and biomedical informatics with ChatGPT: Year one review 🤓 Jinge Wang 👇🏻 https://lnkd.in/evP5TekD 🔍 Focus on data insights: - 📈 Increased application of large language models in bioinformatics shows a growing trend in the integration of AI tools. - 🧬 ChatGPT's capabilities in omics and genetic analysis have facilitated several research breakthroughs. - 📊 Enhanced biomedical text mining through AI has streamlined the extraction of relevant information from vast datasets. - 🤖 The success of ChatGPT in drug discovery indicates its potential as a versatile research assistant. 💡 Main outcomes and implications: - 🌐 The integration of AI in bioinformatics suggests a paradigm shift in research methodologies and workflows. - 🔍 Current limitations of ChatGPT highlight the need for continuous improvement and adaptation in AI applications. - 📚 Future developments could further enhance educational tools within bioinformatics, promoting wider accessibility to complex concepts. 📚 Field significance: - 🌟 The exploration of AI tools like ChatGPT marks a significant advancement in bioinformatics, potentially transforming how data is analyzed and interpreted. - ✒️ The survey provides a foundation for future research, encouraging interdisciplinary collaboration between AI developers and biomedical researchers. 🗄️ [#bioinformatics] [#AI] [#ChatGPT] [#drugdiscovery] [#genomics] [#biomedicalinformatics] [#dataanalysis]

Biomedical engineering is indeed rapidly evolving into data science, driven by high-throughput technologies. Here's an overview: *Key Drivers:* 1. *Big Data*: Explosive growth in biomedical data from sources like genomics, proteomics, imaging, and wearables. 2. *High-Throughput Technologies*: Advances in sequencing, imaging, and sensor technologies generating vast amounts of data. 3. *Artificial Intelligence (AI)*: AI's ability to analyze complex data, identify patterns, and make predictions. 4. *Computational Power*: Increased computing capacity and cloud-based infrastructure enabling faster data processing. *Data Science Applications in Biomedical Engineering:* 1. *Precision Medicine*: Tailoring treatments to individual patients using genomic, epigenomic, and phenotypic data. 2. *Image Analysis*: AI-powered imaging diagnostics for disease detection, segmentation, and quantification. 3. *Predictive Modeling*: Forecasting patient outcomes, disease progression, and treatment responses. 4. *Personalized Health Monitoring*: Wearable sensors and mobile health (mHealth) apps tracking vital signs and lifestyle. 5. *Synthetic Biology*: Designing biological systems using computational models and machine learning. *Emerging Areas:* 1. *Multi-omics Integration*: Combining genomics, transcriptomics, proteomics, and metabolomics data for holistic understanding. 2. *Single-Cell Analysis*: Studying individual cells to understand heterogeneity and cellular behavior. 3. *Digital Twinning*: Creating virtual replicas of patients for simulated testing and personalized medicine. 4. *Natural Language Processing (NLP)*: Extracting insights from clinical notes, medical literature, and patient reports. *Skills Required:* 1. *Programming*: Python, R, Julia, and MATLAB. 2. *Data Analysis*: Statistics, machine learning, and data visualization. 3. *Domain Knowledge*: Biomedical engineering, biology, medicine, and healthcare. 4. *Communication*: Interpreting results for clinicians, researchers, and stakeholders. *Challenges and Opportunities:* 1. *Data Quality and Standardization*: Ensuring accuracy, completeness, and interoperability. 2. *Regulatory Frameworks*: Addressing data privacy, security, and ethics. 3. *Interdisciplinary Collaboration*: Integrating expertise from engineering, biology, medicine, and data science. 4. *Translational Research*: Bridging the gap between basic research and clinical applications. *References:* 1. National Institutes of Health (NIH) - Big Data to Knowledge (BD2K) 2. National Science Foundation (NSF) - Biomedical Data Science 3. IEEE Transactions on Biomedical Engineering 4. Nature Biomedical Engineering The convergence of biomedical engineering and data science is revolutionizing healthcare. Stay updated on the latest advancements and opportunities in this exciting field!

Role of AI in Research The integration of AI in research methodology is transforming the landscape of academic and scientific inquiry. Here’s a look at some key roles AI plays in this field: 1. Data Collection and Analysis: Efficiency: AI tools like IBM Watson can analyze large datasets swiftly. For instance, in climate research, AI can process satellite imagery to monitor environmental changes. Accuracy: AI algorithms are used in healthcare to analyze patient data accurately, predicting disease outbreaks by examining patterns in electronic health records. 2. Literature Review: Speed: Tools like Semantic Scholar use AI to quickly scan and summarize relevant research papers. For example, during the COVID-19 pandemic, AI helped researchers rapidly review thousands of studies to understand the virus better. Relevance: AI platforms like Litmaps can map out the most impactful papers in a particular field, highlighting critical studies for cancer research. 3. Hypothesis Generation: Insight: AI can analyze genetic data to suggest new hypotheses in genomics. For example, AI in the Human Genome Project helped identify new genetic markers associated with diseases. Innovation: AI models have been used in neuroscience to identify unexpected links between brain regions and cognitive functions. 4. Experimental Design: Optimization: AI-driven tools like Design Expert can suggest optimal experimental designs. For instance, in pharmaceutical research, AI helps determine the best dosage combinations for drug trials. Simulation: In materials science, AI simulations can predict how new compounds will behave, guiding researchers in creating better materials without extensive physical testing. 5. Data Visualization: Clarity: Tools like Tableau use AI to create interactive dashboards that present data in clear, understandable formats. For instance, in public health, AI visualizations help track disease spread and inform policy decisions. Interactivity: AI-powered tools can create dynamic data visualizations, such as the interactive maps used in epidemiology to show the spread of diseases like Zika. 6. Writing and Publication: Drafting: Tools like Grammarly use AI to assist in writing, ensuring coherence and clarity. For example, AI can help researchers draft their papers by suggesting better phrasing and structure. Proofreading: AI tools like Hemingway Editor improve writing quality by checking for readability and style, helping researchers prepare manuscripts for publication. 7. Reproducibility: Validation: AI tools can reanalyze datasets to verify research findings. For example, AI was used to revalidate results in psychology studies to ensure their reproducibility. Automation: AI platforms can automatically repeat experiments in silico, as seen in drug discovery where AI helps replicate chemical reactions to confirm results. AI is becoming an indispensable tool in research methodology, bringing a wealth of practical applications across various fields. 🚀🔬

👨💻 🧬 AI & Bioinformatics 🧬 🖥️ 🚀 List of LLM trained and/or applied to Single Cell, Oncology & More 📊 🔵 CellPLM: Pre-training of Cell Language Model Beyond Single Cells 🔵 🛠️ Treats cells as tokens and tissues as sentences to enhance data interpretation 📈 Improves cell type annotation and clustering capabilities 🔗 My LinkedIn: https://buff.ly/4dW4mCx 🟠 Cell2Sentence: Teaching Large Language Models the Language of Biology 🟠 🛠️ converts gene expression data into "cell sentences" 📈 Robust text generation capabilities with significant single-cell biology understanding 🔗 My LinkedIn: https://buff.ly/4brDclj 🟢 GPTCelltype: Assessing GPT-4 for cell type annotation in single-cell RNA-seq analysis 🟢 🛠️ Fit into existing single-cell pipelines 📈 Identifies mixed/single and known/unknown cell types under varying conditions 🔗 My LinkedIn: https://buff.ly/4bwch7U 🟣 OncoGPT: A Medical Conversational Model Tailored with Oncology Domain Expertise on a Large Language Model Meta-AI (LLaMA) 🟣 🛠️ Fine-tuned from over 180,000 physician-patient exchanges, aiming to provide accurate cancer-related guidance 📈 Against baseline models, OncoGPT demonstrated superior precision, recall, and F1 score in 737 oncology conversations 🔗 My LinkedIn: https://buff.ly/3Vk2tbF 🟡 scGPT: toward building a foundation model for single-cell multi-omics using generative AI 🟡 🛠️ Pre-trained on over 33 million single-cell RNA-sequencing profiles 📈 Facilitates diverse single-cell analysis tasks through transfer learning 🔗 My LinkedIn: https://buff.ly/3KloTTt 🔵 MarkerGeneBERT: A natural language processing system for the efficient extraction of cell markers 🔵 🛠️ Automatically extract cell type markers from single-cell sequencing literature 📈 75% precision and 76% recall. MarkerGeneBERT has identified 183 marker genes and 89 cell types previously undocumented 🔗 https://buff.ly/4bToHXi 🟣 GeneGPT: augmenting large language models with domain tools for improved access to biomedical information 🟣 🛠️ Uses NCBI Web APIs for complex genomic queries 📈 Outperforms other models in the GeneTuring benchmark 🔗 https://buff.ly/3R59x9s 🟢 scMulan: a multitask generative pre-trained language model for single-cell analysis 🟢 🛠️ Represents a cell as a structured cell sentence encoding gene expression, metadata terms, and target tasks 📈 Cell type annotation, batch integration, and conditional cell generation 🔗 My LinkedIn: https://buff.ly/3yAQVYD 🔴 BioLLMBench: A Comprehensive Benchmarking of Large Language Models in Bioinformatics 🔴 🛠️ Unique scoring metric to assess LLMs in bioinformatics 📈 GPT-4, Bard, and LLaMA for 36 diverse bioinformatics tasks ❗ Notable differences in model performance when switching chats 🔗 My LinkedIn: https://buff.ly/4aJUNUd 📢 Join the Conversation 📢 Your thoughts? Used these tools? Recommendations? Let me know below!! 👇 💬 #Bioinformatics #SingleCell #LLM

👉🏼 Exploring the Role of ChatGPT in Bioinformatics: A Year in Review 🤓 Jinge Wang 👇🏻 https://lnkd.in/e6Vc_t-R 🔍 Focus on data insights: - 📈 There has been a notable increase in the application of ChatGPT in diverse areas such as omics, genetics, and drug discovery. - 🧠 The integration of large language models is enhancing biomedical text mining capabilities and facilitating complex biomedical image understanding. - 💻 ChatGPT demonstrates potential in bioinformatics programming and educational contexts, providing valuable support for researchers and students. 💡 Main outcomes and implications: - ⚙️ The strengths of ChatGPT include its accessibility and ability to process large datasets, making it a powerful tool for researchers. - 🚀 However, limitations such as accuracy and domain-specific knowledge highlight the need for further refinement and training. - 🔮 Future developments may focus on improving the model's adaptability to specialized bioinformatics challenges and enhancing user interaction. 📚 Field significance: - 🌍 The exploration of chatbots like ChatGPT indicates a shift towards greater reliance on AI tools in bioinformatics and biomedical research. - 🔗 This trend signifies the growing importance of artificial intelligence in supporting complex analytical tasks and fostering innovation across the field. - 🎓 Enhanced educational tools powered by AI could significantly improve learning outcomes in bioinformatics education. 🗄️: [#bioinformatics #AI #ChatGPT #biomedicalinformatics #genetics #drugdiscovery #textmining #education #research]

𝗛𝗼𝘄 𝘁𝗼 𝗹𝗲𝘃𝗲𝗿𝗮𝗴𝗲 𝗔𝗜 𝗳𝗼𝗿 𝗶𝗻 𝘀𝗶𝗹𝗶𝗰𝗼 𝗽𝗿𝗲𝗱𝗶𝗰𝘁𝗶𝗼𝗻 𝗼𝗳 𝗱𝗿𝘂𝗴 𝗮𝗰𝘁𝗶𝘃𝗶𝘁𝘆 & 𝘁𝗼𝘅𝗶𝗰𝗶𝘁𝘆? #AI algorithms can be used to efficiently scan large compound libraries for potential candidates for subsequent validation - creating an elegant AI-human synergy. Today's #interestingread is a #casestudy outlining how BioLizard set this up for a client💡 https://lnkd.in/eygeUD4s 𝙄𝙣 𝙖 𝙣𝙪𝙩𝙨𝙝𝙚𝙡𝙡: 𝗕𝗶𝗼𝗟𝗶𝘇𝗮𝗿𝗱'𝘀 𝗮𝗽𝗽𝗿𝗼𝗮𝗰𝗵: 1️⃣ Assemble a large annotated compound database 2️⃣ Leverage natural language processing (#NLP) & text mining to scope toxicity & activity of compounds 3️⃣ Develop a tailored #ML based in silico model for predicting compound toxicity & activity for subsequent experimental validation For the results... You'll need to 𝙧𝙚𝙖𝙙 𝙩𝙝𝙚 𝙬𝙝𝙤𝙡𝙚 𝙨𝙩𝙤𝙧𝙮 𝙗𝙚𝙡𝙤𝙬 👇 Want more info on leveraging #AI and advanced #analytics for #drugdiscovery and development? If you are attending #BIOEuropeSpring in #Barcelona March 18-20, then be sure to listen in to the panel 𝗨𝗻𝗹𝗲𝗮𝘀𝗵𝗶𝗻𝗴 𝗵𝗲𝗮𝗹𝘁𝗵𝗰𝗮𝗿𝗲: 𝘁𝗵𝗲 𝗽𝗼𝘄𝗲𝗿 𝗼𝗳 𝗔𝗜, 𝗱𝗮𝘁𝗮, 𝗮𝗻𝗱 𝗽𝗲𝗿𝘀𝗼𝗻𝗮𝗹𝗶𝘇𝗲𝗱 𝘁𝗵𝗲𝗿𝗮𝗽𝗶𝗲𝘀 on Tuesday, March 19, 16:00 - 16:45 (Room 111) - featuring our Business Development Director Europe, Dr. Amparo Cuéllar as a panelist 👉 https://lnkd.in/eVpC48tD Or reach out to us today to start discussing how we can help you leverage #AI for your R&D pipelines: https://lnkd.in/e7_CQm3E

Chemoinformatics and AI Tools in Drug Design (Beginners guide to RDKit for AI) With over twenty-five years of experience in insilico design of drugs using chemoinformatics tools for cancer, malaria, tuberculosis, sickle cell anemia, antifungal, antibacterial, and antiviral agents etc., I thought it is time to highlight the key component in chemoinformatics especially the open source tools like RDKit in the field of Artificial Intelligence. Chemoinformatics combines computational and statistical methods to analyze chemical compounds, while AI encompasses machine learning, deep learning, and natural language processing for pattern recognition and prediction. The fundamental challenge lies in translating pictorial chemical structures, easily understood by chemists, into numeric formats that computers can process and analyze. Inductive learning is a process that converts molecular structures into descriptors that include biological activity, physicochemical properties, and toxicological information. These descriptors enable the creation of AI models that transform data into knowledge. Once the model is trained and optimized using experimental data, it gains the ability to predict the properties of new molecules. These predictions guide decisions about which molecules to synthesize, evaluate biologically, and test for properties and toxicology. The predicted data can then be compared with experimental results to assess prediction accuracy. Today's students and faculty, particularly those in bioinformatics familiar with sequences, should expand their knowledge to understand molecules at the atomic level using free chemoinformatics tools like RDKit. While new-gen students quickly grasp these tools, success requires patience and persistence through installation challenges and source code implementation. Starting with tutorials builds confidence before advancing to novel methods for research projects. Data quality remains the critical factor in AI modeling, as errors in input data will lead to model failure. Modern AI systems are being developed to detect input data errors, ensuring clean data for building high-quality models with minimal errors through the learning process. The current success of generative AI in producing textual outputs suggests that when fine-tuned for chemical information, without proprietary data restrictions, it could revolutionize drug discovery by identifying valuable therapeutic molecules more efficiently. This practical approach to learning chemoinformatics, particularly using RDKit, creates opportunities for technical and scientific positions in pharmaceutical industries. Try yourself. Please share this post/repost with your network. Happy Learning! 🙂 Please DM/contact me if you want to collaborate in "GenAI for Drug Design". #cheminformatics #artificialintelligence #ai #drugdesign #drugdiscovery #chemistry #education #research #llm #genAI #ML #DL #rdkit #opensource #python #qsar #chemistry #biology #bioinformatics

If you're an in silico drug discovery researcher, there's a vast array of AI and machine learning tools that can optimize your workflows and boost productivity. Here’s a curated list of AI and machine learning tools useful for in silico drug discovery researchers:  1. DeepChem    - Description: Open-source library offering various machine learning models for Molecular modeling, QSAR modeling, protein-ligand interactions, and virtual screening.  2. RDKit    - Description: A widely used cheminformatics library for Chemical informatics, molecular descriptors, and machine learning-based predictions.  3. Mol2Vec    - Description: Natural language processing-inspired tool that generates vector representations of molecules based on SMILES, useful for similarity searches, molecule clustering, and machine learning model input generation.  4. Schrödinger’s AutoQSAR    - Description: Automated QSAR modeling platform that uses machine learning to predict the activity of small molecules.  5. Chemprop    - Description: Deep learning tool for predicting molecular properties such as toxicity by using message-passing neural networks (MPNNs).      6. ChEMBL    - Description: Machine learning-friendly database with bioactivity data for Drug-target interaction predictions, virtual screening, and hit identification.  7. ATAC (Atomistic Toolkit for AI-Driven Computation)    - Description: AI-driven computational toolkit designed for accelerating discovery pipelines through reinforcement learning and optimization algorithms.  8. gnina    - Description: A deep learning-based tool for molecular docking with support for scoring functions based on neural networks.  9. PyCaret    - Description: Low-code machine learning library to build and tune predictive QSAR models with ease.      10. OpenPharmacophore    - Description: An open-source toolkit for pharmacophore modeling and screening.      11. BioSymPy    - Description: Python library for building and simulating biomolecular systems using machine learning models.      12. PaccMann    - Description: AI-based tool that integrates multi-omics data with drug sensitivity for precision medicine.      13. AlphaFold    - Description: State-of-the-art AI model developed by DeepMind for protein structure prediction.      14. ROCS (Rapid Overlay of Chemical Structures)    - Description: Tool from OpenEye that uses shape-based molecular alignment for ligand-based virtual screening.      15. DeepPurpose    - Description: An end-to-end deep learning framework for drug-target interaction predictions and optimizing lead compounds. That’s a wrap!! Are you looking for a service provider to implement any of the above ?! Then, look no further explore Innovative Informatica Technologies at https://lnkd.in/gSPsnJ9F What cool libraries would you add to this list? 👇 Drop your suggestions in the replies below 👇" #drugdiscovery #machinelearning #python #deeplearning

𝗟𝗮𝘀𝘁 𝗪𝗲𝗲𝗸 𝗶𝗻 𝗠𝗲𝗱𝗶𝗰𝗮𝗹 𝗔𝗜: 𝗧𝗼𝗽 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗣𝗮𝗽𝗲𝗿𝘀/𝗠𝗼𝗱𝗲𝗹𝘀   🏅(September 14 - September 21, 2024) 𝗠𝗲𝗱𝗶𝗰𝗮𝗹 𝗔𝗜 𝗣𝗮𝗽𝗲𝗿 𝗼𝗳 𝘁𝗵𝗲 𝗪𝗲𝗲𝗸 How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities - This paper proposes a vision for "AI-powered Virtual Cells," aiming to create robust, data-driven representations of cells and cellular systems. It discusses the potential of AI to generate universal biological representations across scales and facilitate interpretable in-silico experiments using "Virtual Instruments." 1) 𝗠𝗲𝗱𝗶𝗰𝗮𝗹 𝗟𝗟𝗠 & 𝗢𝘁𝗵𝗲𝗿 𝗠𝗼𝗱𝗲𝗹𝘀 - 𝗚𝗣-𝗚𝗣𝗧: 𝗟𝗟𝗠𝘀 𝗳𝗼𝗿 𝗚𝗲𝗻𝗲-𝗣𝗵𝗲𝗻𝗼𝘁𝘆𝗽𝗲 𝗠𝗮𝗽𝗽𝗶𝗻𝗴 This paper introduces GP-GPT, the first specialized large language model for genetic-phenotype knowledge representation and genomics relation analysis. Trained on over 3 million terms from genomics, proteomics, and medical genetics datasets and publications. - 𝗛𝘂𝗮𝘁𝘂𝗼𝗚𝗣𝗧-𝗜𝗜, 1-𝘀𝘁𝗮𝗴𝗲 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 𝗳𝗼𝗿 𝗠𝗲𝗱𝗶𝗰𝗮𝗹 𝗟𝗟𝗠𝘀 This paper introduces HuatuoGPT-II, a new large language model (LLM) for Traditional Chinese Medicine, trained using a unified input-output pair format to address data heterogeneity challenges in domain adaptation. - 𝗛𝘂𝗮𝘁𝘂𝗼𝗚𝗣𝗧-𝗩𝗶𝘀𝗶𝗼𝗻: 𝗠𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗠𝗲𝗱𝗶𝗰𝗮𝗹 𝗟𝗟𝗠𝘀 This paper introduces PubMedVision, a 1.3 million sample medical VQA dataset created by refining and denoising PubMed image-text pairs using MLLMs (GPT-4V). - 𝗔𝗽𝗼𝗹𝗹𝗼: 𝗔 𝗟𝗶𝗴𝗵𝘁𝘄𝗲𝗶𝗴𝗵𝘁 𝗠𝘂𝗹𝘁𝗶𝗹𝗶𝗻𝗴𝘂𝗮𝗹 𝗠𝗲𝗱𝗶𝗰𝗮𝗹 𝗟𝗟𝗠 This paper introduces ApolloCorpora, a multilingual medical dataset, and XMedBench, a benchmark for evaluating medical LLMs in six major languages. The authors develop and release Apollo models (0.5B-7B parameters) 2) 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀 𝗮𝗻𝗱 𝗠𝗲𝘁𝗵𝗼𝗱𝗼𝗹𝗼𝗴𝗶𝗲𝘀 • CoD: Chain of Diagnosis for Medical Agents • Interpretable Visual Concept Discovery with SAM • Aligning Human Knowledge for Explainable Med Image • ReXErr: Synthetic Errors in Radiology Reports • Fine Tuning LLMs for Medicine: The Role of DPO 3) 𝗖𝗹𝗶𝗻𝗶𝗰𝗮𝗹 𝗧𝗿𝗶𝗮𝗹𝘀 • LLMs to Generate Clinical Trial Tables and Figures • LLMs for Clinical Report Correction • AlpaPICO: LLMs for Clinical Trial PICO Frames 4) 𝗠𝗲𝗱𝗶𝗰𝗮𝗹 𝗟𝗟𝗠 𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀 • Microsoft's Learnings of Large-Scale Bot Deployment in Medical .... Check the full thread in detail: https://lnkd.in/gky973ea Follow Open Life Science AI For daily New Medical AI Papers/LLMs Updates #ClinicalTrials #MedicalAI #HealthcareInnovation #ArtificialIntelligence #MachineLearning #FutureOfHealthcare #opensource #MedicalResearch #medical #clinical #clinicaltrials #healthcare #health #Radiology #pathology #llm #chatgpt #GPT4o #claude #google #genai #ai #NLProc #academia #nature #huggingface #meta #Harvard #Stanford #pfizer #AstraZeneca #gilead #OpenLifeScienceAI #OpenLifeSciAI

Today the most important article in chatgpt and "BioNexusSentinel: a visual tool for bioregulatory network and cytohistological RNA-seq genetic expression profiling within the context of multicellular simulation research using ChatGPT-augmented software engineering" - Developed a unique integrated visual platform for efficient cytohistological RNA-seq and bioregulatory network exploration. - Utilized Reactome as the primary source of remotely accessible biological models. - Introduced a novel gene expression profiler component to enhance the exploratory experience for researchers. - Integrated a cytohistological classifier through pre-processed analysis of RNA-seq data using R statistical language. - Implications include model orthogonality evaluations, gap identification in network modeling, automatic kinetics parameterization, and cellular biological state analysis. - Collaboration with generative natural language processing AI enhanced worker productivity and coding acceleration. #chatgpt #BioNexusSentinel #RNAseq #bioregulatorynetwork #computational