In-context learning (ICL) -- the capacity of a model to infer and apply abstract patterns from examples provided within its input -- has been extensively studied in large language models trained for next-token prediction on human text. In fact, prior work often attributes this emergent behavior to distinctive statistical properties in human language. This raises a fundamental question: can ICL arise organically in other sequence domains purely through large-scale predictive training? To explore this, we turn to genomic sequences, an alternative symbolic domain rich in statistical structure. Specifically, we study the Evo2 genomic model, trained predominantly on next-nucleotide (A/T/C/G) prediction, at a scale comparable to mid-sized LLMs. We develop a controlled experimental framework comprising symbolic reasoning tasks instantiated in both linguistic and genomic forms, enabling direct comparison of ICL across genomic and linguistic models. Our results show that genomic models, like their linguistic counterparts, exhibit log-linear gains in pattern induction as the number of in-context demonstrations increases. To the best of our knowledge, this is the first evidence of organically
We introduce Genome-Factory, the first integrated Python library for tuning, deploying, and interpreting genomic foundation models. Our core contribution is to simplify and unify the workflow for genomic model development: data collection, model tuning, inference, benchmarking, and interpretability. For data collection, Genome-Factory offers an automated pipeline to download genomic sequences and preprocess them. For model tuning, Genome-Factory supports both full and parameter-efficient fine-tuning across diverse genomic models. For inference, Genome-Factory enables both embedding extraction and DNA sequence generation. For benchmarking, we include two existing benchmarks and provide a flexible interface to incorporate additional benchmarks. For interpretability, Genome-Factory introduces an open-source biological interpreter based on a sparse auto-encoder. We validate the utility of Genome-Factory across three dimensions: (i) Compatibility with diverse models and fine-tuning methods; (ii) Benchmarking downstream performance using two open-source benchmarks; (iii) Biological interpretation of learned representations with DNABERT-2. These results highlight its practical value for r
Searching for similar genomic sequences is an essential and fundamental step in biomedical research and an overwhelming majority of genomic analyses. State-of-the-art computational methods performing such comparisons fail to cope with the exponential growth of genomic sequencing data. We introduce the concept of sparsified genomics where we systematically exclude a large number of bases from genomic sequences and enable much faster and more memory-efficient processing of the sparsified, shorter genomic sequences, while providing similar or even higher accuracy compared to processing non-sparsified sequences. Sparsified genomics provides significant benefits to many genomic analyses and has broad applicability. We show that sparsifying genomic sequences greatly accelerates the state-of-the-art read mapper (minimap2) by 2.57-5.38x, 1.13-2.78x, and 3.52-6.28x using real Illumina, HiFi, and ONT reads, respectively, while providing up to 2.1x smaller memory footprint, 2x smaller index size, and more truly detected small and structural variations compared to minimap2. Sparsifying genomic sequences makes containment search through very large genomes and large databases 72.7-75.88x faster
Advances in genome sequencing technologies generate massive amounts of sequence data that are increasingly analyzed and shared through public repositories. On-demand infrastructure services on cloud computing platforms enable the processing of such large-scale genomic sequence data in distributed processing environments with a significant reduction in analysis time. However, parallel processing on cloud computing platforms presents many challenges to researchers, even skillful bioinformaticians. In particular, it is difficult to design a computing architecture optimized to reduce the cost of computing and disk storage as genomic data analysis pipelines often employ many heterogeneous tools with different resource requirements. To address these issues, we developed GenomeFlow, a tool for automated development of computing architecture and resource optimization on Google Cloud Platform, which allows users to process a large number of samples at minimal cost. We outline multiple use cases of GenomeFlow demonstrating its utility to significantly reduce computing time and cost associated with analyzing genomic and transcriptomic data from hundreds to tens of thousands of samples from se
In biomedical research, validation of a new scientific discovery is tied to the reproducibility of its experimental results. However, in genomics, the definition and implementation of reproducibility still remain imprecise. Here, we argue that genomic reproducibility, defined as the ability of bioinformatics tools to maintain consistent genomics results across technical replicates, is key to generating scientific knowledge and enabling medical applications. We first discuss different concepts of reproducibility and then focus on reproducibility in the context of genomics, aiming to establish clear definitions of relevant terms. We then focus on the role of bioinformatics tools and their impact on genomic reproducibility and assess methods of evaluating bioinformatics tools in terms of genomic reproducibility. Lastly, we suggest best practices for enhancing genomic reproducibility, with an emphasis on assessing the performance of bioinformatics tools through rigorous testing across multiple technical replicates.
Given the increasing volume and quality of genomics data, extracting new insights requires interpretable machine-learning models. This work presents Genomic Interpreter: a novel architecture for genomic assay prediction. This model outperforms the state-of-the-art models for genomic assay prediction tasks. Our model can identify hierarchical dependencies in genomic sites. This is achieved through the integration of 1D-Swin, a novel Transformer-based block designed by us for modelling long-range hierarchical data. Evaluated on a dataset containing 38,171 DNA segments of 17K base pairs, Genomic Interpreter demonstrates superior performance in chromatin accessibility and gene expression prediction and unmasks the underlying `syntax' of gene regulation.
Schizophrenia (SZ) is a severe brain disorder marked by diverse cognitive impairments, abnormalities in brain structure, function, and genetic factors. Its complex symptoms and overlap with other psychiatric conditions challenge traditional diagnostic methods, necessitating advanced systems to improve precision. Existing research studies have mostly focused on imaging data, such as structural and functional MRI, for SZ diagnosis. There has been less focus on the integration of genomic features despite their potential in identifying heritable SZ traits. In this study, we introduce a Multi-modal Imaging Genomics Transformer (MIGTrans), that attentively integrates genomics with structural and functional imaging data to capture SZ-related neuroanatomical and connectome abnormalities. MIGTrans demonstrated improved SZ classification performance with an accuracy of 86.05% (+/- 0.02), offering clear interpretations and identifying significant genomic locations and brain morphological/connectivity patterns associated with SZ.
Our genomes influence nearly every aspect of human biology from molecular and cellular functions to phenotypes in health and disease. Human genetics studies have now associated hundreds of thousands of differences in our DNA sequence ("genomic variation") with disease risk and other phenotypes, many of which could reveal novel mechanisms of human biology and uncover the basis of genetic predispositions to diseases, thereby guiding the development of new diagnostics and therapeutics. Yet, understanding how genomic variation alters genome function to influence phenotype has proven challenging. To unlock these insights, we need a systematic and comprehensive catalog of genome function and the molecular and cellular effects of genomic variants. Toward this goal, the Impact of Genomic Variation on Function (IGVF) Consortium will combine approaches in single-cell mapping, genomic perturbations, and predictive modeling to investigate the relationships among genomic variation, genome function, and phenotypes. Through systematic comparisons and benchmarking of experimental and computational methods, we aim to create maps across hundreds of cell types and states describing how coding variant
Motivation: Standard genome-wide association studies in cancer genomics rely on statistical significance with multiple testing correction, but systematically fail in underpowered cohorts. In TCGA breast cancer (n=967, 133 deaths), low event rates (13.8%) create severe power limitations, producing false negatives for known drivers and false positives for large passenger genes. Results: We developed a five-criteria computational framework integrating causal inference (inverse probability weighting, doubly robust estimation) with orthogonal biological validation (expression, mutation patterns, literature evidence). Applied to TCGA-BRCA mortality analysis, standard Cox+FDR detected zero genes at FDR<0.05, confirming complete failure in underpowered settings. Our framework correctly identified RYR2 -- a cardiac gene with no cancer function -- as a false positive despite nominal significance (p=0.024), while identifying KMT2C as a complex candidate requiring validation despite marginal significance (p=0.047, q=0.954). Power analysis revealed median power of 15.1% across genes, with KMT2C achieving only 29.8% power (HR=1.55), explaining borderline statistical significance despite stron
Supergenes are genomic regions containing sets of tightly linked loci that control multi-trait phenotypic polymorphisms under balancing selection. Recent advances in genomics have uncovered significant variation in both the genomic architecture as well as the mode of origin of supergenes across diverse organismal systems. Although the role of genomic architecture for the origin of supergenes has been much discussed, differences in the genomic architecture also subsequently affect the evolutionary trajectory of supergenes and the rate of degeneration of supergene haplotypes. In this review, we synthesize recent genomic work and historical models of supergene evolution, highlighting how the genomic architecture of supergenes affects their evolutionary fate. We discuss how recent findings on classic supergenes involved in governing ant colony social form, mimicry in butterflies, and heterostyly in flowering plants relate to theoretical expectations. Furthermore, we use forward simulations to demonstrate that differences in genomic architecture affect the degeneration of supergenes. Finally, we discuss implications of the evolution of supergene haplotypes for the long-term fate of bala
Database fingerprinting has been widely used to discourage unauthorized redistribution of data by providing means to identify the source of data leakages. However, there is no fingerprinting scheme aiming at achieving liability guarantees when sharing genomic databases. Thus, we are motivated to fill in this gap by devising a vanilla fingerprinting scheme specifically for genomic databases. Moreover, since malicious genomic database recipients may compromise the embedded fingerprint by launching effective correlation attacks which leverage the intrinsic correlations among genomic data (e.g., Mendel's law and linkage disequilibrium), we also augment the vanilla scheme by developing mitigation techniques to achieve robust fingerprinting of genomic databases against correlation attacks. We first show that correlation attacks against fingerprinting schemes for genomic databases are very powerful. In particular, the correlation attacks can distort more than half of the fingerprint bits by causing a small utility loss (e.g.,database accuracy and consistency of SNP-phenotype associations measured via p-values). Next, we experimentally show that the correlation attacks can be effectively m
This paper provides a global picture about the deployment of networked processing services for genomic data sets. Many current research make an extensive use genomic data, which are massive and rapidly increasing over time. They are typically stored in remote databases, accessible by using Internet. For this reason, a significant issue for effectively handling genomic data through data networks consists of the available network services. A first contribution of this paper consists of identifying the still unexploited features of genomic data that could allow optimizing their networked management. The second and main contribution of this survey consists of a methodological classification of computing and networking alternatives which can be used to offer what we call the Genomic-as-a-Service (GaaS) paradigm. In more detail, we analyze the main genomic processing applications, and classify not only the main computing alternatives to run genomics workflows in either a local machine or a distributed cloud environment, but also the main software technologies available to develop genomic processing services. Since an analysis encompassing only the computing aspects would provide only a p
Human genomic data carry unique information about an individual and offer unprecedented opportunities for healthcare. The clinical interpretations derived from large genomic datasets can greatly improve healthcare and pave the way for personalized medicine. Sharing genomic datasets, however, pose major challenges, as genomic data is different from traditional medical data, indirectly revealing information about descendants and relatives of the data owner and carrying valid information even after the owner passes away. Therefore, stringent data ownership and control measures are required when dealing with genomic data. In order to provide secure and accountable infrastructure, blockchain technologies offer a promising alternative to traditional distributed systems. Indeed, the research on blockchain-based infrastructures tailored to genomics is on the rise. However, there is a lack of a comprehensive literature review that summarizes the current state-of-the-art methods in the applications of blockchain in genomics. In this paper, we systematically look at the existing work both commercial and academic, and discuss the major opportunities and challenges. Our study is driven by five
Advancements in genomic research such as high-throughput sequencing techniques have driven modern genomic studies into "big data" disciplines. This data explosion is constantly challenging conventional methods used in genomics. In parallel with the urgent demand for robust algorithms, deep learning has succeeded in a variety of fields such as vision, speech, and text processing. Yet genomics entails unique challenges to deep learning since we are expecting from deep learning a superhuman intelligence that explores beyond our knowledge to interpret the genome. A powerful deep learning model should rely on insightful utilization of task-specific knowledge. In this paper, we briefly discuss the strengths of different deep learning models from a genomic perspective so as to fit each particular task with a proper deep architecture, and remark on practical considerations of developing modern deep learning architectures for genomics. We also provide a concise review of deep learning applications in various aspects of genomic research, as well as pointing out potential opportunities and obstacles for future genomics applications.
Genomic selection (GS), as a critical crop breeding strategy, plays a key role in enhancing food production and addressing the global hunger crisis. The predominant approaches in GS currently revolve around employing statistical methods for prediction. However, statistical methods often come with two main limitations: strong statistical priors and linear assumptions. A recent trend is to capture the non-linear relationships between markers by deep learning. However, as crop datasets are commonly long sequences with limited samples, the robustness of deep learning models, especially Transformers, remains a challenge. In this work, to unleash the unexplored potential of attention mechanism for the task of interest, we propose a simple yet effective Transformer-based framework that enables end-to-end training of the whole sequence. Via experiments on rice3k and wheat3k datasets, we show that, with simple tricks such as k-mer tokenization and random masking, Transformer can achieve overall superior performance against seminal methods on GS tasks of interest.
How does the genome encode the form of the organism? What is the nature of this genomic code? Inspired by recent work in machine learning and neuroscience, we propose that the genome encodes a generative model of the organism. In this scheme, by analogy with variational autoencoders, the genome comprises a connectionist network, embodying a compressed space of latent variables, with weights that get encoded by the learning algorithm of evolution and decoded through the processes of development. The generative model analogy accounts for the complex, distributed genetic architecture of most traits and the emergent robustness and evolvability of developmental processes, while also offering a conception that lends itself to formalisation.
Over the last 20 years, there has been an explosion of genomic data collected for disease association, functional analyses, and other large-scale discoveries. At the same time, there have been revolutions in cloud computing that enable computational and data science research, while making data accessible to anyone with a web browser and an internet connection. However, students at institutions with limited resources have received relatively little exposure to curricula or professional development opportunities that lead to careers in genomic data science. To broaden participation in genomics research, the scientific community needs to support students, faculty, and administrators at Underserved Institutions (UIs) including Community Colleges, Historically Black Colleges and Universities, Hispanic-Serving Institutions, and Tribal Colleges and Universities in taking advantage of these tools in local educational and research programs. We have formed the Genomic Data Science Community Network (http://www.gdscn.org/) to identify opportunities and support broadening access to cloud-enabled genomic data science. Here, we provide a summary of the priorities for faculty members at UIs, as w
Genomic selection has increased genetic gain in several livestock species, but due to the complicated genetics and reproduction biology not yet in honey bees. Recently, 2 970 queens were genotyped to gather a reference population. For the application of genomic selection in honey bees, this study analyses the predictive ability and bias of pedigree-based and genomic breeding values for honey yield, three workability traits and two traits for resistance against the parasite Varroa destructor. For breeding value estimation, we use a honey bee-specific model with maternal and direct effects, to account for the contributions of the workers and the queen of a colony to the phenotypes. We conducted a validation for the last generation and a five-fold cross-validation. In the validation for the last generation, the predictive ability of pedigree-based estimated breeding values was 0.06 for honey yield, and ranged from 0.2 to 0.41 for the workability traits. The inclusion of genomic marker data improved these predictive abilities to 0.11 for honey yield, and a range from 0.22 to 0.44 for the workability traits. The inclusion of genomic data did not improve the predictive ability for the di
We provide, on an extensive dataset and using several different distances, confirmation of the hypothesis that CGR patterns are preserved along a genomic DNA sequence, and are different for DNA sequences originating from genomes of different species. This finding lends support to the theory that CGRs of genomic sequences can act as graphic genomic signatures. In particular, we compare the CGR patterns of over five hundred different 150,000 bp genomic sequences originating from the genomes of six organisms, each belonging to one of the kingdoms of life: H. sapiens, S. cerevisiae, A. thaliana, P. falciparum, E. coli, and P. furiosus. We also provide preliminary evidence of this method's applicability to closely related species by comparing H. sapiens (chromosome 21) sequences and over one hundred and fifty genomic sequences, also 150,000 bp long, from P. troglodytes (Animalia; chromosome Y), for a total length of more than 101 million basepairs analyzed. We compute pairwise distances between CGRs of these genomic sequences using six different distances, and construct Molecular Distance Maps that visualize all sequences as points in a two-dimensional or three-dimensional space, to sim
Genomic data visualization is essential for interpretation and hypothesis generation as well as a valuable aid in communicating discoveries. Visual tools bridge the gap between algorithmic approaches and the cognitive skills of investigators. Addressing this need has become crucial in genomics, as biomedical research is increasingly data-driven and many studies lack well-defined hypotheses. A key challenge in data-driven research is to discover unexpected patterns and to formulate hypotheses in an unbiased manner in vast amounts of genomic and other associated data. Over the past two decades, this has driven the development of numerous data visualization techniques and tools for visualizing genomic data. Based on a comprehensive literature survey, we propose taxonomies for data, visualization, and tasks involved in genomic data visualization. Furthermore, we provide a comprehensive review of published genomic visualization tools in the context of the proposed taxonomies.