Significant advancements in hardware, algorithms, generative AI (GenAI) techniques and genomic science underpin current progress and future opportunities. AI has demonstrated the ability to analyze and identify genetic variations and detect patterns and protein structures, she added. "AI is extensively used in genomics to expand its application potential and increase the speed and accuracy at which vast amounts of genomic data are analyzed," said Neeraja V, senior analyst at the consultancy Everest Group. Recent AI advancements in computing, management techniques, algorithms and multimodal large language models are enhancing genomic research.
Training data was sourced from large public consortia including ENCODE, GTEx, 4D Nucleome and FANTOM5, which experimentally measured these properties covering important modalities of gene regulation across hundreds of human and mouse cell types and tissues. Predicted properties include where genes start and where they end in different cell types and tissues, where they get spliced, the amount of RNA being produced, and also which DNA bases are accessible, close to one another, or bound by certain proteins. Today, we introduce AlphaGenome, a new artificial intelligence (AI) tool that more comprehensively and accurately predicts how single variants or mutations in human DNA sequences impact a wide range of biological processes regulating genes.
The potential for time and cost reductions in this process has drawn significant stakeholder attention and resulted in numerous investigative projects. This will significantly cut downtime and expenses in identifying potential drug candidates. Only one out of 5,000–10,000 compounds is approved as a potential drug for a particular condition. Zhuang H (2025) How genomics and multi-modal AI are reshaping precision medicine.
Bayesian efficient multiple kernel learning is a way to develop a response prediction model based on multi-omics data. The superiority of gene expression profile datasets may make it challenging to understand prediction models, but this can be reduced using TANDEM, a two-stage method . While developing a drug response prediction model, the data type, complexity noise ratio, dimensionality, and heterogeneity are essential elements. In precision medicine, there are ten algorithms which are generally used. Machine Learning is transforming healthcare by guiding individual and population health through a variety of computational benefits.
This approach mirrors how physicians naturally think about patients—not as isolated genetic data, but as complex individuals whose health comes from multiple interacting factors. More recent models using data fusion layer to fuse multiple embedding into one embedding for downstream tasks (10), such as predicting diagnostics. Multi-modal AI can be one of our most powerful techniques to explore this complexity. And for an example in infectious disease, researchers developed VirCapSeq-VERT, a positive selection system based on genetics for detecting RNA and DNA viruses (8).
Generated proteins also have structural alignment to natural proteins, though the structure prediction confidences of generated proteins are relatively lower than those of natural genes (Fig. 5k and Extended Data Fig. 9f–h). https://www.dnaxplore.com/ and secondary structure distributions of generated proteins resemble natural M. We next leveraged the million-base-pair context window of Evo 2 to generate DNA sequences at the scale of small prokaryotic genomes.
Just as ChatGPT can analyze text to predict words and phrases, GenomeOcean reads vast amounts of genomic sequences to uncover patterns and relationships within DNA. One groundbreaking initiative is GenomeOcean, an AI-powered model designed to learn the “natural language” of genomes. By bridging computational innovation and biological insight, this collection highlights the potential of AI-powered genomic medicine to empower research and clinical practice and to enable broad access. Share Your Requirements to help our experts understand your business objectives and create your customized plan. A. AI diagnosis of genetic disorders can help by using sequencing data to find mutations that cause diseases.
Introducing a new, unifying DNA sequence model that advances regulatory variant-effect prediction and promises to shed new light on genome function — now available via API. We spoke to Mo Lotfollahi, a new Group Leader in the Cellular Genetics programme who is developing generative artificial intelligence (AI) models for predicting cellular responses The Institute’s Policy Team carried out initial research with international stakeholders, to consider the ethical implications of creating synthetic genomes. At the Sanger Institute, Leopold Parts leads a research group that aims to develop new technologies to write and edit genomes at scale and speed to biological design. Generative AI is also set to transform synthetic genomics – a field of biotechnology where scientists design and create new artificial genetic sequences. As we draw on the power of AI, we aim to engineer biology with precision, and eventually reimagine the future of genomic research and its eventual impact on areas such as healthcare, agriculture and biotechnology."
Artificial intelligence (AI) has emerged as a powerful platform to streamline the analysis of complex genomic datasets and help researchers explore the genetic basis of important diseases or phenotypes. These tools use histone modification and high-throughput sequencing assay data as a training data set and based on the extracted features predict the enhancers in genomes. There are numerous experimental techniques used for the identification of enhancers. To resolve this issue, Gaur et al. proposed a new model that uses eXplainable AI modelling techniques for the prediction of brain tumours. However, where the machine learning and Deep learning-based model achieves higher accuracy, these techniques are unable to explain how a particular result has been classified by a specific model.
Two decades after the first human genome was sequenced, DNA data has been reserved for understanding rare diseases, treating cancer and general research. The obtained “big data” in combination with the machine learning analytics could improve not only the clinical practice but also provide a deeper understanding of cancer and rare diseases. Despite the recent advances in AI toolkits and their performance in medical studies, there are still some gaps and margin for improvement, suggesting that AI needs either more data or better algorithms to improve the precision medicine accuracy. Therefore, it is necessary to re-think the current paradigm of one disease – one target – one drug.41 The current understanding of drug design is that a drug must be capable of re-establishing homeostasis; the drug hits the targets causing the disease by re-establishing the equilibrium.
Predictive platforms like Cox-nnet integrate neural networks with Cox regression to prioritize prognostic markers, improving five-year survival prediction . Pharmacogenomic models that match tumor-specific mutations with drug sensitivity profiles have improved response rates . More recently, DL frameworks such as EPInformer have leveraged DL to predict chromatin accessibility from DNA sequences, enabling insights into chromatin state dynamics .