Scientific Software Development

Best LLM-based Open-Source tool for Data Visualization, non-tech friendly CanvasXpress is a JavaScript library with built-in LLM and copilot features. This means users can chat with the LLM directly, with no code needed. It also works from visualizations in a web page, R, or Python. It’s funny how I came across this tool first and only later realized it was built by someone I know—Isaac Neuhaus. I called Isaac, of course: This tool was originally built internally for the company he works for and designed to analyze genomics and research data, which requires the tool to meet high-level reliability and accuracy. ➡️Link https://lnkd.in/gk5y_h7W As an open-source tool, it's very powerful and worth exploring. Here are some of its features that stand out the most to me: 𝐀𝐮𝐭𝐨𝐦𝐚𝐭𝐢𝐜 𝐆𝐫𝐚𝐩𝐡 𝐋𝐢𝐧𝐤𝐢𝐧𝐠: Visualizations on the same page are automatically connected. Selecting data points in one graph highlights them in other graphs. No extra code is needed. 𝐏𝐨𝐰𝐞𝐫𝐟𝐮𝐥 𝐓𝐨𝐨𝐥𝐬 𝐟𝐨𝐫 𝐂𝐮𝐬𝐭𝐨𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧: - Filtering data like in Spotfire. - An interactive data table for exploring datasets. - A detailed customizer designed for end users. 𝐀𝐝𝐯𝐚𝐧𝐜𝐞𝐝 𝐀𝐮𝐝𝐢𝐭 𝐓𝐫𝐚𝐢𝐥: Tracks every customization and keeps a detailed record. (This feature stands out compared to other open-source tools that I've tried.) ➡️Explore it here: https://lnkd.in/gk5y_h7W Isaac's team has also published this tool in a peer-reviewed journal and is working on publishing its LLM capabilities. #datascience #datavisualization #programming #datanalysis #opensource

A nice review article "Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation" covers the scope of tools and approaches for how AI can support science. Some of areas the paper covers: (link in comments) 🔎 Literature search and summarization. Traditional academic search engines rely on keyword-based retrieval, but AI-powered tools such as Elicit and SciSpace enhance search efficiency with semantic analysis, summarization, and citation graph-based recommendations. These tools help researchers sift through vast scientific literature quickly and extract key insights, reducing the time required to identify relevant studies. 💡 Hypothesis generation and idea formation. AI models are being used to analyze scientific literature, extract key themes, and generate novel research hypotheses. Some approaches integrate structured knowledge graphs to ground hypotheses in existing scientific knowledge, reducing the risk of hallucinations. AI-generated hypotheses are evaluated for novelty, relevance, significance, and verifiability, with mixed results depending on domain expertise. 🧪 Scientific experimentation. AI systems are increasingly used to design experiments, execute simulations, and analyze results. Multi-agent frameworks, tree search algorithms, and iterative refinement methods help automate complex workflows. Some AI tools assist in hyperparameter tuning, experiment planning, and even code execution, accelerating the research process. 📊 Data analysis and hypothesis validation. AI-driven tools process vast datasets, identify patterns, and validate hypotheses across disciplines. Benchmarks like SciMON (NLP), TOMATO-Chem (chemistry), and LLM4BioHypoGen (medicine) provide structured datasets for AI-assisted discovery. However, issues like data biases, incomplete records, and privacy concerns remain key challenges. ✍️ Scientific content generation. LLMs help draft papers, generate abstracts, suggest citations, and create scientific figures. Tools like AutomaTikZ convert equations into LaTeX, while AI writing assistants improve clarity. Despite these benefits, risks of AI-generated misinformation, plagiarism, and loss of human creativity raise ethical concerns. 📝 Peer review process. Automated review tools analyze papers, flag inconsistencies, and verify claims. AI-based meta-review generators assist in assessing manuscript quality, potentially reducing bias and improving efficiency. However, AI struggles with nuanced judgment and may reinforce biases in training data. ⚖️ Ethical concerns. AI-assisted scientific workflows pose risks, such as bias in hypothesis generation, lack of transparency in automated experiments, and potential reinforcement of dominant research paradigms while neglecting novel ideas. There are also concerns about the overreliance on AI for critical scientific tasks, potentially compromising research integrity and human oversight.

As AI+Science went more mainstream in 2025, our team’s seminal contributions to the field are getting wide recognition. Here are top professional contributions and achievements for 2025. 1. Medical Imaging: We applied Neural Operators as a universal AI scheme that can handle any subsampling scheme and can do zero-shot super-resolution and field of view, without the need for any retraining. We applied it to a range of modalities such as MRI, CT, ultrasound, and photo-acoustic imaging. 2. AI Weather and Climate Models: I led the creation of the first AI-based weather model FourCastNet, built on Neural Operators, back in 2021. This year we announced FourCastNet 3, the fastest AI based model to provide calibrated probabilistic answers, crucial for extreme weather events. This also serves as backbone for state of art AI-based climate models . 3. De-Novo Inverse Design of Physical Devices: We were able to design new devices that were previously out of reach in challenging systems such as gate design in quantum dots, controlling quantum systems and non-linear photonics, using Fourier Neural Operator (FNO). 4. Scientific Modeling: FNOs achieved modeling of bio-realistic neurons, quantum dynamics and black holes with significant speedups while maintaining fidelity. 5. Millennium prize in fluid dynamics: We developed high-precision physics-informed neural networks (PINN) to solve a key step in computer-assisted proofs of singularities. 6. Physics-informed chemistry: Orbitall is the first universal quantum-chemical AI model that can handle at any spin, charge and external fields, and can extrapolate to larger molecules than those in training data. Nucleusdiff improves structure-based drug design by generating physically plausible molecules that maintain proper atomic spacing. We were able to beat previously known natural and engineered enzymes in functionality and versatility using protein-language models (genSLM). 7. Neural Operator foundations: We developed a unified framework to convert many popular neural networks like convolutional and graph neural networks, transformers etc to Neural Operators. We improved generalization to different geometries and scales. We developed FunDPS, a diffusion based inverse problem solver on function spaces. It is a resolution-agnostic unified framework for both forward and inverse PDEs. We also established limitations of hybrid learning that combine numerical solvers with learned closures and superiority of operator learning. 8. Verified Learning in LLMs: We released LeanDojo v2, LeanAgent and LeanProgress for theorem proving. 9. TIME 100 Impact Award and IEEE Kiyo Tomiyasu Award. 10. Group members Zongyi Li and Miguel Liu-Schiaffini winning best graduate and undergraduate research at Caltech commencement for work on Neural Operators and alum Zhuoran Qiao winning the Tianqiao and Chrissy Chen Institute AI+Science prize.

How do materials fail, and how can we design stronger, tougher, and more resilient ones? Published in #PNAS, our physics-aware AI model integrates advanced reasoning, rational thinking, and strategic planning capabilities models with the ability to write and execute code, perform atomistic simulations to solicit new physics data from “first principles”, and conduct visual analysis of graphed results and molecular mechanisms. By employing a multiagent strategy, these capabilities are combined into an intelligent system designed to solve complex scientific analysis and design tasks, as applied here to alloy design and discovery. This is significant because our model overcomes the limitations of traditional data-driven approaches by integrating diverse AI capabilities—reasoning, simulations, and multimodal analysis—into a collaborative system, enabling autonomous, adaptive, and efficient solutions to complex, multiobjective materials design problems that were previously slow, expert-dependent, and domain-specific. Wonderful work by my postdoc Alireza Ghafarollahi! Background: The design of new alloys is a multiscale problem that requires a holistic approach that involves retrieving relevant knowledge, applying advanced computational methods, conducting experimental validations, and analyzing the results, a process that is typically slow and reserved for human experts. Machine learning can help accelerate this process, for instance, through the use of deep surrogate models that connect structural and chemical features to material properties, or vice versa. However, existing data-driven models often target specific material objectives, offering limited flexibility to integrate out-of-domain knowledge and cannot adapt to new, unforeseen challenges. Our model overcomes these limitations by leveraging the distinct capabilities of multiple AI agents that collaborate autonomously within a dynamic environment to solve complex materials design tasks. The proposed physics-aware generative AI platform, AtomAgents, synergizes the intelligence of LLMs and the dynamic collaboration among AI agents with expertise in various domains, incl. knowledge retrieval, multimodal data integration, physics-based simulations, and comprehensive results analysis across modalities. The concerted effort of the multiagent system allows for addressing complex materials design problems, as demonstrated by examples that include autonomously designing metallic alloys with enhanced properties compared to their pure counterparts. We demonstrate accurate prediction of key characteristics across alloys and highlight the crucial role of solid solution alloying to steer the development of alloys. Paper: https://lnkd.in/enusweMf Code: https://lnkd.in/eWv2eKwS MIT Schwarzman College of Computing MIT Civil and Environmental Engineering MIT Department of Mechanical Engineering (MechE) MIT Industrial Liaison Program MIT School of Engineering

AI Meets Physics 🚀 Machine Learning is transforming physics - from predicting quantum behavior to simulating complex systems like climate and fluid flow. 📌 Key Applications: - Predictive Modeling for quantum mechanics and chaotic systems - Simulation & Analysis in fluid dynamics and climate science - Discovering Physical Laws using symbolic regression - Material Science innovations via property prediction - Quantum Computing optimization with neural networks 🧠 Popular Models in Use: - MLPs for general regressions - CNNs for image-based phase detection - RNNs for time-dependent physical processes - GANs for synthetic data generation - Encoder-Decoder models for forecasting & solving differential equations - Physics-Informed Neural Networks (PINNs) for integrating physics into ML ⚖️ Benefits vs Challenges ✅ High accuracy ✅ Speed and adaptability ✅ New scientific insights ❌ Black-box nature ❌ Heavy data/computation needs ❌ Risk of overfitting As AI continues to evolve, its role in physics is no longer optional—it’s becoming foundational. 🚀

I couldn’t believe my eyes when I saw this! What if you could go into supercomputer territory just using Python? You can! Coiled lets you call up cloud machines by simply calling a function in Python. NO Kubernetes. NO Docker. Data engineers and data scientists can now reach the same massive scale that used to require a specialized cloud engineer. My video example is showing you the processing of 250TB of geospatial cloud data from NOAA’s National Water Model. Y’all know I was working at Waze previously, so geospatial data has a special place in my heart. This kind of scale needs a large, distributed cloud cluster - the kind I used to depend on our engineering team to spin up and babysit. But Coiled now brings those capabilities to you directly within Python. The geocalculations on this one are pretty insane: mean depth to soil saturation for every US county across 4 decades of data (1979-2020) at 3-hour time intervals and using a 250-meter spatial grid. That is literally BILLIONS of tiny calculations stitched together into one picture. With Coiled, it took just 20 minutes of processing and cost only 10cents per TB! That kind of scale, speed and cost are unheard of for your typical data scientist. You can read through the full use case here and even replicate it yourself: https://fandf.co/3Wi0Z19 What I love about this solution is that it’s remarkably easy to do. The magic happens in 3 steps: ask for hardware in Python and you’ll have access a minute later, then your code automatically installs on those machines with no complex middleware needed, and finally you can work as you usually do from your choice of IDE but now with 500,000% more CPU 🤯 If you’re a data scientist, researcher or anyone proficient in Python but stuck thinking you need a cloud team to do the heavy work, go give Coiled a look: https://fandf.co/3Iylx27 You don’t need to know anything about cloud infrastructure to get started. #datascience #dataengineering #python #cloudcomputing 🖤 I partnered with Coiled to help share this story. And honestly, even if it weren’t sponsored, I’d be talking about it anyway. The use case genuinely blew me away and shows just how approachable cloud computing can be.

OpenAI is positioning Prism as a “workspace for scientists.” That framing is far too modest. What’s actually happening is a quiet but decisive move up the value chain: from models → tools → ownership of the scientific workflow itself. Hypotheses, experiments, interpretation, iteration - all inside one AI-native environment. At that point, the model stops being infrastructure and becomes the operating system of discovery. That matters because whoever owns the workflow doesn’t just speed things up. They shape what gets explored, how uncertainty is handled, and which paths become economically viable. This isn’t neutral tooling. It’s epistemic leverage. What makes Prism more important than it looks is the precedent it sets. It normalizes the idea that serious thinking happens inside AI-native environments - where context is persistent, reasoning is collaborative (human + machine), and the interface is intent, not documents. Once that becomes normal in science, it won’t stay there. Strategy, engineering, finance, policy - everything that still assumes humans are the primary integrators is next. So the real question for research-heavy organizations isn’t “Should we adopt AI tools?” It’s which parts of our knowledge production we are willing to externalize - and under what governance. That’s not an IT decision. It’s a power decision. https://lnkd.in/edvU9sFY #AI #Transformation #Science #Future

🚀 Scientific Machine Learning: The Revolution of Computational Science with AI In recent years, we have seen impressive advances in Machine Learning (ML), but when it comes to scientific and engineering problems, a critical challenge remains: limited data and complex physical models. This is where Scientific Machine Learning (SciML) comes in—a field that combines machine learning with physics-based modeling to create more robust, interpretable, and efficient solutions. 🔹 Why isn’t traditional ML enough? Neural networks and statistical models are great at detecting patterns in large datasets, but many scientific phenomena have limited data or follow fundamental laws, such as the Navier-Stokes equations in fluid dynamics or Schrödinger’s equation in quantum mechanics. Training a purely data-driven model, without physical knowledge, can lead to inaccurate or physically inconsistent predictions. 🔹 What makes SciML different? SciML bridges data-driven models with partial differential equations (PDEs), physical laws, and structural knowledge, creating hybrid approaches that are more reliable. A classic example is Physics-Informed Neural Networks (PINNs), which embed differential equations directly into the loss function of the neural network. This allows solving complex simulation problems with high accuracy, even when data is scarce. 🔹 Real-world applications where SciML is already transforming science: ✅ Climate & Environment: Hybrid deep learning + atmospheric equations improve climate predictions. ✅ Engineering & Physics: Neural networks accelerate computational simulations in structural mechanics and fluid dynamics. ✅ Healthcare & Biotechnology: Simulations of molecular interactions for drug discovery. ✅ Energy & Sustainability: Optimized modeling of nuclear reactors and next-generation batteries. 🔹 Challenges and the future of SciML We still face issues such as high computational costs, training stability, and the pursuit of more interpretable models. However, as we continue to integrate deep learning with scientific principles, the potential of SciML to transform multiple fields is immense. 💡 Have you heard about Scientific Machine Learning before? If you work with computational physics, modeling, or applied machine learning, this is one of the most promising fields to explore! 🚀 #SciML #MachineLearning #AI #PhysicsInformed #DeepLearning #ComputationalScience

At Microsoft, we're dedicated to empowering every scientist with AI-augmented scientific discovery. Our Azure Quantum Elements platform is a significant step in this direction, offering two new groundbreaking capabilities: Generative Chemistry for the exploration of novel molecular structures at an unprecedented scale and speed, and Accelerated DFT for simulating chemical catalysts and other complex molecular structures using core innovation developed by Microsoft Research.   In our work with Unilever, they're harnessing the power of Azure Quantum Elements to drive forward scientific discovery. Unilever DataLab—a leading collaboration platform for in-silico R&D innovation built on Azure—is a prime example of digital transformation in action. From unlocking the secrets of our skin’s microbiome to reducing the carbon footprint of a multi-billion-dollar business, Unilever is redefining what it means to be a consumer goods company in the modern world with leading science.   Earlier this year, we demonstrated with Quantinuum the most reliable logical qubits on record, further advancing the state-of-the-art for quantum computing. And recently, we simulated a chemical catalyst combining classical supercomputers, AI and logical qubits created with Microsoft’s qubit-virtualization system and Quantinuum’s H1 hardware. This combination holds the key to unlocking scientific breakthroughs enabled by a new generation of hybrid-computing applications.   Learn more about the story behind these advancements and their impact on the future of science by reading my latest post on the Official Microsoft Blog: https://lnkd.in/gygcDd2D #AzureQuantum #AI #Science #Innovation

🧬 ggcoverage: A New Era in Genome Visualization 🧬 🔍 #Biologists, #Bioinformaticians, and #PharmaLeaders, meet ggcoverage – the latest tool transforming genome coverage visualization! 🔵 Versatile Input Formats: ggcoverage adeptly handles various file formats, including BAM, BigWig, BedGraph, and TSV, catering to diverse genomic data types. 🟢 Comprehensive Annotation Support: It requires additional files like FASTA for GC content, GTF for gene and transcript annotations, and peak files for peak annotation, ensuring detailed and accurate visualizations. 🟣 Advanced Data Preprocessing: Equipped with functions for read normalization, consensus peak generation, and track data loading, ggcoverage streamlines your data preparation using tools like deeptools, BiocParallel, and MSPC. 🔴 Rich Visualization Features: Offering twelve layers for coverage plot visualization, ggcoverage brings your genomic data to life with features like gene and transcript annotation, GC content calculation, 3D chromatin contact maps, and more. 🟠 Easy Customization: Built on ggplot2, ggcoverage provides unparalleled flexibility, allowing you to tailor your visualizations with ease. 🔗 Dive Deeper: 📚 BMC Bioinformatics paper: https://buff.ly/3T1hjTA 💻 GitHub: https://buff.ly/3GoxanA 📢 Join the Conversation📢 Explore ggcoverate and share your experience, and alternative tools in the comments!👇 💬 #ggcoverage #GenomeVisualization #Bioinformatics #Genomics #DataScience #InnovationInScience