CAAIL is in beta. We're re-checking earlier classifications and reorganizing the research areas for v2. See the roadmap Tell us what you think
AI for Cell-Ag Researchers
Introductory resources on AI and machine learning, gathered for wet-lab researchers: biologists, biochemists, bioprocess engineers and cell-ag practitioners. The page lists playlists, courses and books on the methods catalogued in the library, from statistics and classical machine learning to deep learning, then links to the agentic-AI and foundation-model work that CAAIL indexes. Computer scientists learning the cell-ag side have a companion page, Cellular Agriculture for AI researchers.
Learn the fundamentals
Video playlists and courses that introduce statistics, machine learning, deep learning and AI agents, listed here for readers coming from biology.
- PlaylistAI Fundamentalsan IBM Technology playlist. Free.
- PlaylistStatistics Fundamentalsa StatQuest with Josh Starmer playlist giving a general overview of statistics, which also serves as a reference for statistical concepts. Free.
- PlaylistMachine Learninga StatQuest with Josh Starmer playlist on a broad range of machine-learning topics. Free.
- PlaylistNeural Networks / Deep Learninga StatQuest with Josh Starmer playlist that runs from neural-network fundamentals through the transformer architecture behind ChatGPT and other large language models. Free.
- PlaylistNeural networksan animated 3Blue1Brown series that starts with "But what is a neural network?" and goes on to backpropagation, transformers and attention. Free.
- PlaylistAI Models Explainedan IBM Technology playlist of explainers on AI models. Free.
- PlaylistAI Agents Explainedan IBM Technology playlist. Papers on AI agents are indexed in the agent rows of CAAIL's Papers matrix. Free.
- PlaylistStanford CS230: Deep Learning (Autumn 2025)Stanford Online's recordings of the Autumn 2025 lectures by Andrew Ng and Kian Katanforoosh, with sessions such as "What's Going On Inside My Model?". Free.
- PlaylistStanford CS230: Deep Learning (Autumn 2018)the Autumn 2018 lectures of Andrew Ng's Stanford deep-learning course. Free.
- PlaylistNeural Networks: Zero to HeroAndrej Karpathy's course on building neural networks and a small GPT from scratch in code, from backpropagation up to a working language model. Free.
- LinkMIT 6.S191: Introduction to Deep LearningMIT's introductory deep-learning course, with lectures and code labs, updated each year. Free.
Books
Illustrated guides and textbooks on statistics, machine learning and neural networks. Some are free to read or download online; all are sold in print, and some as PDFs.
- LinkThe StatQuest Illustrated Guide to Statisticsan illustrated book by Josh Starmer that covers statistics up to advanced topics such as ANOVA and ANCOVA, with PyTorch and R tutorials. For sale as a paperback or a PDF.
- LinkThe StatQuest Illustrated Guide to Machine Learningan illustrated book by Josh Starmer that goes from the basic concepts of machine learning through neural networks. For sale as a paperback or a PDF.
- LinkThe StatQuest Illustrated Guide to Neural Networks and AIan illustrated book by Josh Starmer that runs from neural networks to the Transformers that power ChatGPT, with PyTorch tutorials. For sale as a paperback or a PDF.
- LinkAn Introduction to Statistical Learninga textbook by James, Witten, Hastie and co-authors, with an R edition (second edition, 2021) and a Python edition (2023). Each chapter ends with a lab in R or Python. Free PDFs on the book's site; print copies are sold.
- LinkModern Statistics for Modern Biologya 2019 book by S. Holmes and W. Huber (Cambridge University Press), written for biologists, on the methods of modern computational statistics, with R and Bioconductor code. The online version is kept up to date. Free online under CC BY-NC-SA; print copies are sold.
Go deeper
Talks, courses, books and CAAIL pages at a more advanced level.
- In CAAIL AI Agents & Foundation Models for Biology talkstalks on agentic AI, foundation models and language-model-based scientific reasoning, many from the Broad Institute's MIA series.
- In CAAIL AI Agents & Foundation Models hubCAAIL's page connecting agent frameworks, single-cell foundation models and the virtual-cell initiative, among them Arc's State and Stack models, the open Virtual Cell Challenge and Cell2Sentence.
- In CAAIL Curated bibliographies & awesome listscommunity-maintained indexes of the AI, single-cell and bioinformatics literature. On the site, each list's card shows its GitHub star count and last-updated date.
- PlaylistStanford CS224N: NLP with Deep Learning (Spring 2024)Stanford's NLP course, covering self-attention, Transformers and modern LLM architectures. Free.
- LinkDeep Learning for Molecules and Materialsan online book by A. D. White, written for chemistry and materials science students and assuming knowledge of Python. Free.
Where AI shows up in CAAIL
- In CAAIL Papers ExplorerCAAIL's matrix of AI methods against research areas. Agentic and foundation-model work sits in the agent and foundation-model rows, and general-purpose AI tools not yet tied to a cell-ag result sit in the AI Tooling / Methodology column.
- LinkArtificial intelligence and machine learning applications for cultured meata 2024 review of AI and ML applied to cultured meat, by Todhunter and colleagues in Frontiers in Artificial Intelligence. Open access (CC BY).
- LinkArtificial intelligence for food innovationa 2026 review of AI in food innovation, by Datta, Kuhl and 15 co-authors in Nature Food. Paywalled at the publisher; a repository copy is free.
- In CAAIL Softwaresoftware tools for computational and AI work, open-source and proprietary, grouped by application area.
Companion primer
Linked external resources are independent of TUCCA and Tufts University and remain under their own licenses.