Big Data in Biological Sciences

Half a million genomes. 1.5 billion variants. One breakthrough: we are all truly unique. Twenty years ago, the Human Genome Project took 13 years and $2.7B to sequence a single genome. Today? We can sequence a genome in less than 24 hours for under $1,000. Last week, UK Biobank released 490,640 whole genomes — the largest genetic dataset ever (Nature, 2025). What did we learn? • Each person carries 4–5 million variants • 76% appear in fewer than 10 people — your genome is almost entirely yours • 1 in 10 carries clinically actionable mutations where doctors can intervene today (e.g., BRCA1/2 for cancer, LDLR for heart disease) Why it matters: • Previous genetic tests captured ~6% of human variation. This dataset reveals 40× more • In non-coding regions — the biological switches controlling genes — researchers found 63 new disease associations • Adding 31,785 non-European genomes uncovered 82 disease links invisible in Eurocentric studies From genetics to health impact This transforms medicine today: • Prevention - Polygenic risk scores flag disease decades before symptoms • Diagnosis - Rare disease patients waiting years for answers finally find them • Treatment - Pharmacogenomics matches the right drug, right dose, to your genome The next frontier: genetics + everything else Genetics is the hardware. Health is the software running in real time. Your DNA is fixed, but biology is dynamic, shaped by: • Epigenetics: how environment and lifestyle switch genes on/off • Proteomics & metabolomics: molecular signals revealing your current health state • Digital biomarkers: continuous data from stress, sleep, glucose, heart rate • Stress biology & neuroendocrine signaling: how cortisol and brain-body responses reshape your health trajectory Layer these dynamic signals onto genetic foundations, power them with AI, and you create living health models, not just predicting disease, but understanding when, why, and how it manifests in YOU. The critical question? We've spent decades treating the "average patient" — who doesn't exist. Now we can better see each person as they truly are: biologically unique, dynamically changing, infinitely complex. The healthcare winners of the next decade won't just collect data: they'll integrate genetics, epigenetics, molecular and phenotypic tests, lifestyle, stress biology, and digital signals to deliver truly personalized, preventive care at scale. There is no "normal" genome, only 8 billion unique experiments in being human. And we just decoded the first half million. 👉 Which excites you more: knowing your genetic blueprint, or understanding how your daily choices rewrite it?

Can large language models be used in biotech? The short answer is yes. While LLMs are often associated with chatbots, their capabilities extend beyond that. In biotech, much of the data comes in the form of sequences – like nucleotides in DNA, or amino acids in proteins. Similar to sentences in natural language, these biological sequences have unique semantic meanings based on the arrangement of their components. When input data is fed into an LLM, a transformer converts these sequences into contextual vectors using its attention mechanism. This process allows the model to understand the context and relationships within the data, enabling it to predict subsequent elements. One such use case is prediction of neoantigens that enable targeting tumor cells in personalized cancer immunotherapies. Neoantigens are tumor-specific mutated peptides presented on the surface of tumor cells because they bind to human leukocyte antigen (HLA) molecules. LLMs can predict this binding affinity. This allows the development of personalized therapies that use the patient's own immune system to kill tumor cells without damaging healthy tissues.

Probably, one of the largest collaborative efforts in biotech, since the Human Genome Project: the Human Cell Atlas has arrived! 🧬 I think the Human Cell Atlas (HCA) is a pretty monumental leap in systems biology, an international effort involving 3,600 researchers from 102 countries, has released its first draft atlas of human cells. This isn’t just another dataset—this is the blueprint of human biology, built cell by cell, tissue by tissue, organ by organ. The HCA integrated data from 62 million cells, sourced from 9,100 donors, spanning every stage of human development—embryonic to adult. Researchers organized their work into 18 Biological Networks, focusing on key organs like the lung, nervous system, and eye. Some of the tools like single-cell RNA sequencing, spatial transcriptomics, and multi-omics were combined to profile and map cells with unprecedented precision. Notably, Google provided essential cloud infrastructure and AI tools like scTab (for annotation) and SCimilarity (for cell similarity searches), helping researchers handle vast and complex datasets efficiently. It is also important that local scientists and the HCA Ethics Working Group put efforts to make sure data represented populations globally, prioritizing equity and open access. Now, how can we use it, practically speaking? Here I picked some of the key aspects that might be very useful for the biotech community: ✅ Precise Target Discovery: Pinpoint disease-specific cell types and biomarkers to create highly targeted therapies. ✅ Better Disease Models: Build realistic organoids and in vitro models informed by detailed cell maps for accurate drug testing. ✅ Personalized Medicine: Utilize data from diverse populations to design therapies tailored to genetic and environmental variations. ✅ Safer Drugs: Analyze tissue-specific metabolism to predict and avoid adverse drug effects. ✅ AI-Driven Insights: Tap into machine-learning tools like PopV and SCimilarity to accelerate discovery and refine findings. I believe, the Atlas could be a playing ground for other AI tools and new workflows! ✅ Early Diagnosis: Identify subtle gene expression changes for early detection of diseases like cancer or neurodegenerative disorders. If you're in biotech, drug discovery, or systems biology, this resource is now open and available—check it out! Link in the comments 👇 Image source:  Springer Nature

Not every shiny ML algorithm belongs in Bioinformatics. Bioinformatics doesn’t just need AI. It needs Bio-aware AI. In the rush to apply the latest AI/ML models to every problem, there’s a reality check many overlook: 👉 Bioinformatics ≠ generic tabular data. 👉 Bioinformatics ≠ simple image recognition. 👉 Bioinformatics ≠ “just another dataset.” Genomics, proteomics, structural biology, and systems biology produce data with unique statistical distributions, noise profiles, and biological constraints. - Sequence data isn’t like stock market data. - Protein structures don’t behave like social network graphs. - Gene expression matrices are not regular spreadsheets. This is why some ML models that dominate in other fields (finance, NLP, recommender systems) break down in bioinformatics unless carefully adapted. In Bioinformatics, success comes when: Algorithms are tuned for biological priors. Models respect the physics & chemistry of life. Data preprocessing mirrors the complexity of biology, not just math. The best ML algorithm is not the “newest” one, it’s the one that truly understands biological data. Here are the top ML/LLM models in 2025: - AlphaGenome (June 2025): Gene regulation & variant impact from long DNA sequences - AlphaFold 3 (Launched 2024; widely adopted by 2025): Protein complex, ligand, DNA/RNA structure prediction - SonicParanoid2 (2024): Fast orthologous gene inference using ML & LMs - NuFold (2025): RNA 3D prediction using AlphaFold 2 architecture - trRosettaRNA (Recent): Transformer-based RNA tertiary structure modeling - esmGFP / ESM3-derived protein design (Published Jan 2025): AI-designed protein simulating evolutionary processes - Generative AI Models: DNABERT, DNAGPT, GENA LM: DNA sequence modeling and classification with LLMs - EMitool (2025): Explainable multi-omics integration for cancer subtyping - DeepGO-SE and TAWFN (2025): Enhanced protein function inference via embeddings and GNNs - Graph Neural Networks (GNNs) (Growing relevance by 2025): Modeling biological networks and spatial gene expression - Quantum-Inspired Algorithms: QSVM, QNN, VQE, QFT: Experimental bioinformatics acceleration via quantum algorithms - BioMaster (2025): Automated bioinformatics pipeline management with LLM agents Models like AlphaGenome or DeepGO-SE are purpose built for biology they understand sequence context, structure, or biological ontologies. AlphaGenome handles million-base pair sequences; ESM3 was trained on hundreds of billions of protein. NuFold, AlphaFold 3, and trRosettaRNA capture 3D structure; GNNs model networks and tissue spatial contexts. Tools like EMitool and BioMaster support interpretability and autonomous workflows. Quantum-inspired algorithms and LLM agents (e.g., BioMaster) point toward the next wave of bioinformatics automation and acceleration.

Have you heard of openproblems.bio? 🧬 It's kind of like Kaggle for single-cell biology. And it's a brilliant model of how the ML and bioinformatics communities collaborate. Single-cell analysis sits at a fascinating intersection: massive, tabular datasets meet cutting-edge ML meets the messy reality of biology. But here's the challenge: ML researchers love Jupyter notebooks, while biology demands robust, reproducible pipelines for processing data. Different tools, different cultures. OpenProblems.bio bridges this gap brilliantly. It transforms core single-cell challenges into living, community-run benchmarks where anyone can: ✅ Submit methods in Python or R (no pipeline expertise needed) ✅ Compare results fairly with standardized datasets and metrics ✅ Access everything openly, including published results and methods The secret sauce? A powerful three-part ecosystem: * Viash converts scripts into reproducible pipeline components * Nextflow orchestrates complex workflows * Seqera provides the platform for elastic cloud execution on AWS What excites me most: this is **FAIR open science done right** Complete transparency, version control, quality checks built in, and a framework that welcomes contributions from both communities without forcing either to abandon their tools. Tasks range from dimensionality reduction to perturbation prediction, with new benchmarks continually added by the community. If you're working in computational biology or ML for life sciences, this is infrastructure worth knowing about. The future of biomedical AI needs exactly this kind of collaborative, rigorous foundation. Thanks to Robrecht Cannoodt and the openproblems.bio community for collaborating on the blog: https://lnkd.in/gpNJNd2r #Bioinformatics #MachineLearning #SingleCell #OpenScience #Benchmarking

Omics studies produce a large number of measurements, enabling the development, validation and interpretation of systems-level biological models. Large cohorts are required to power these complex models; yet, the cohort size remains limited due to clinical and budgetary constraints. We introduce clinical and omics multimodal analysis enhanced with transfer learning (COMET), a machine learning framework that incorporates large, observational electronic health record databases and transfer learning to improve the analysis of small datasets from omics studies. By pretraining on electronic health record data and adaptively blending both early and late fusion strategies, COMET overcomes the limitations of existing multimodal machine learning methods. Using two independent datasets, we showed that COMET improved the predictive modelling performance and biological discovery compared with the analysis of omics data with traditional methods. By incorporating electronic health record data into omics analyses, COMET enables more precise patient classifications, beyond the simplistic binary reduction to cases and controls. This framework can be broadly applied to the analysis of multimodal omics studies and reveals more powerful biological insights from limited cohort sizes. Interesting publication by Nima Aghaeepour and larger team at Stanford University.  The link to the full paper can be found here: https://lnkd.in/eeygnqn7

Important - from my personal experience: The $1M Lesson: Why Your Omics Data Fails Before Sequencing Even Begins Have you ever funded an omics project that generated terabytes of data... but zero biological insights? This post isn’t about fancy algorithms or sequencing tech – it’s about the strategic gap costing millions in misused research funds. Through analyzing different projects, I’ve identified a root cause: Treating bioinformatics as an afterthought rather than a design partner. My advice for you: 🔍 1. Define Your Biological Question FIRST What are you truly trying to prove/discover? Every sequencing dollar must map to answering this. No clear hypothesis → No meaningful analysis. 🤝 2. Involve Bioinformaticians Before Pipelines – Not After We’re not "data janitors" – we’re experimental architects: 🔹 Sample Size & Power: 100 samples/group? Often 20-30 suffice. Avoid underpowered stats or overkill costs. 🔹 Design Flaws: Cross-sectional vs longitudinal? Batch effects? We’ll bulletproof your setup. 🔹 Tech Tradeoffs: Short-read vs long-read? 100X vs 500X depth? Spoiler: More ≠ better 🧬 Actionable Takeaway Before signing any sequencing contract: 1️⃣ Draft a 1-page hypothesis framework with your bioinformatician. 2️⃣ Run pilot data simulations using publicly available datasets to test statistical power. 3️⃣ Ask us the uncomfortable question: "What’s the minimal experiment to answer this?" #Bioinformatics #Genomics #ExperimentalDesign #ResearchFunding #Sequencing #BigData

Can big data finally untangle neurodegeneration? Lessons from the 'omics era.' Omics refers to large scale biological measurements such as genes, RNA proteins and metabolites that together help to explain how diseases start and progress. Ibanez and colleagues describe in a new paper in Annals of Neurology how genomics, transcriptomics and proteomics are reshaping our understanding of neurodegenerative diseases and where the field has ‘learned hard lessons.’ Key Points: - Neurodegenerative diseases arise from complex multi-layer biological changes, rather than single genes or proteins. - Integrating genomics, transcriptomics and proteomics has uncovered shared pathways such as inflammation, protein handling and mitochondrial dysfunction across diseases. - Moving from association to causation remains challenging and requires better data integration in larger more diverse cohorts, and of course employing careful study design. My take: This review captures both the promise and the reality of ‘omics.’ We now see disease biology in far greater detail, however translating signals into clear targets and treatments remains the hardest step. The future will depend on integration, rigor and humility. Here are 5 points that resonated w/ me: 1- Neurodegenerative diseases are systems problems, not single pathway failures. 2- ‘Omics’ approaches frequently reveal shared biology across Alzheimer’s, Parkinson’s and related disorders. 3- Cell type and tissue context matter and blood, CSF and brain data do not always tell the same story. 4- Bigger datasets help, however ‘smarter integration’ and causal inference may matter more. 5- The real win will be turning ‘omics’ signals into actionable targets that improve care. https://lnkd.in/euBFABHv Parkinson's Foundation International Parkinson and Movement Disorder Society Norman Fixel Institute for Neurological Diseases