arXiv subjects

Guy-Bart Stan

Publications and source records attributed to Guy-Bart Stan.

At least 19 recordsLinked to original sources

arXiv2025

Omni-DNA: A Unified Genomic Foundation Model for Cross-Modal and Multi-Task Learning

Large Language Models (LLMs) demonstrate remarkable generalizability across diverse tasks, yet genomic foundation models (GFMs) still require separate finetuning for each downstream application, creating significant overhead as model sizes grow. Moreover, existing GFMs are constrained by rigid output formats, limiting their applicability to various genomic tasks. In this work, we revisit the transformer-based auto-regressive models and introduce Omni-DNA, a family of cross-modal multi-task models ranging from 20 million to 1 billion parameters. Our approach consists of two stages: (i) pretraining on DNA sequences with next token prediction objective, and (ii) expanding the multi-modal task-specific tokens and finetuning for multiple downstream tasks simultaneously. When evaluated on the Nucleotide Transformer and GB benchmarks, Omni-DNA achieves state-of-the-art performance on 18 out of 26 tasks. Through multi-task finetuning, Omni-DNA addresses 10 acetylation and methylation tasks at once, surpassing models trained on each task individually. Finally, we design two complex genomic tasks, DNA2Function and Needle-in-DNA, which map DNA sequences to textual functional descriptions and images, respectively, indicating Omni-DNA's cross-modal capabilities to broaden the scope of genomic applications. All the models are available through https://huggingface.co/collections/zehui127

q-bio.GN↗

arXiv2024

GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning

Genetic variants (GVs) are defined as differences in the DNA sequences among individuals and play a crucial role in diagnosing and treating genetic diseases. The rapid decrease in next generation sequencing cost has led to an exponential increase in patient-level GV data. This growth poses a challenge for clinicians who must efficiently prioritize patient-specific GVs and integrate them with existing genomic databases to inform patient management. To addressing the interpretation of GVs, genomic foundation models (GFMs) have emerged. However, these models lack standardized performance assessments, leading to considerable variability in model evaluations. This poses the question: How effectively do deep learning methods classify unknown GVs and align them with clinically-verified GVs? We argue that representation learning, which transforms raw data into meaningful feature spaces, is an effective approach for addressing both indexing and classification challenges. We introduce a large-scale Genetic Variant dataset, named GV-Rep, featuring variable-length contexts and detailed annotations, designed for deep learning models to learn GV representations across various traits, diseases, tissue types, and experimental contexts. Our contributions are three-fold: (i) Construction of a comprehensive dataset with 7 million records, each labeled with characteristics of the corresponding variants, alongside additional data from 17,548 gene knockout tests across 1,107 cell types, 1,808 variant combinations, and 156 unique clinically verified GVs from real-world patients. (ii) Analysis of the structure and properties of the dataset. (iii) Experimentation of the dataset with pre-trained GFMs. The results show a significant gap between GFMs current capabilities and accurate GV representation. We hope this dataset will help advance genomic deep learning to bridge this gap.

cs.LG↗

arXiv2024

Absorb & Escape: Overcoming Single Model Limitations in Generating Genomic Sequences

Abstract Recent advances in immunology and synthetic biology have accelerated the development of deep generative methods for DNA sequence design. Two dominant approaches in this field are AutoRegressive (AR) models and Diffusion Models (DMs). However, genomic sequences are functionally heterogeneous, consisting of multiple connected regions (e.g., Promoter Regions, Exons, and Introns) where elements within each region come from the same probability distribution, but the overall sequence is non-homogeneous. This heterogeneous nature presents challenges for a single model to accurately generate genomic sequences. In this paper, we analyze the properties of AR models and DMs in heterogeneous genomic sequence generation, pointing out crucial limitations in both methods: (i) AR models capture the underlying distribution of data by factorizing and learning the transition probability but fail to capture the global property of DNA sequences. (ii) DMs learn to recover the global distribution but tend to produce errors at the base pair level. To overcome the limitations of both approaches, we propose a post-training sampling method, termed Absorb & Escape (A&E) to perform compositional generation from AR models and DMs. This approach starts with samples generated by DMs and refines the sample quality using an AR model through the alternation of the Absorb and Escape steps. To assess the quality of generated sequences, we conduct extensive experiments on 15 species for conditional and unconditional DNA generation. The experiment results from motif distribution, diversity checks, and genome integration tests unequivocally show that A&E outperforms state-of-the-art AR models and DMs in genomic sequence generation.

q-bio.GN↗

arXiv2024

Enhancing Node Representations for Real-World Complex Networks with Topological Augmentation

Graph augmentation methods play a crucial role in improving the performance and enhancing generalisation capabilities in Graph Neural Networks (GNNs). Existing graph augmentation methods mainly perturb the graph structures, and are usually limited to pairwise node relations. These methods cannot fully address the complexities of real-world large-scale networks, which often involve higher-order node relations beyond only being pairwise. Meanwhile, real-world graph datasets are predominantly modelled as simple graphs, due to the scarcity of data that can be used to form higher-order edges. Therefore, reconfiguring the higher-order edges as an integration into graph augmentation strategies lights up a promising research path to address the aforementioned issues. In this paper, we present Topological Augmentation (TopoAug), a novel graph augmentation method that builds a combinatorial complex from the original graph by constructing virtual hyperedges directly from the raw data. TopoAug then produces auxiliary node features by extracting information from the combinatorial complex, which are used for enhancing GNN performances on downstream tasks. We design three diverse virtual hyperedge construction strategies to accompany the construction of combinatorial complexes: (1) via graph statistics, (2) from multiple data perspectives, and (3) utilising multi-modality. Furthermore, to facilitate TopoAug evaluation, we provide 23 novel real-world graph datasets across various domains including social media, biology, and e-commerce. Our empirical study shows that TopoAug consistently and significantly outperforms GNN baselines and other graph augmentation methods, across a variety of application contexts, which clearly indicates that it can effectively incorporate higher-order node relations into the graph augmentation for real-world complex networks.

cs.LG↗

arXiv2024

DiscDiff: Latent Diffusion Model for DNA Sequence Generation

This paper introduces a novel framework for DNA sequence generation, comprising two key components: DiscDiff, a Latent Diffusion Model (LDM) tailored for generating discrete DNA sequences, and Absorb-Escape, a post-training algorithm designed to refine these sequences. Absorb-Escape enhances the realism of the generated sequences by correcting `round errors' inherent in the conversion process between latent and input spaces. Our approach not only sets new standards in DNA sequence generation but also demonstrates superior performance over existing diffusion models, in generating both short and long DNA sequences. Additionally, we introduce EPD-GenDNA, the first comprehensive, multi-species dataset for DNA generation, encompassing 160,000 unique sequences from 15 species. We hope this study will advance the generative modelling of DNA, with potential implications for gene therapy and protein production.

q-bio.GN↗

arXiv2024

Hybrid Graph: A Unified Graph Representation with Datasets and Benchmarks for Complex Graphs

Graphs are widely used to encapsulate a variety of data formats, but real-world networks often involve complex node relations beyond only being pairwise. While hypergraphs and hierarchical graphs have been developed and employed to account for the complex node relations, they cannot fully represent these complexities in practice. Additionally, though many Graph Neural Networks (GNNs) have been proposed for representation learning on higher-order graphs, they are usually only evaluated on simple graph datasets. Therefore, there is a need for a unified modelling of higher-order graphs, and a collection of comprehensive datasets with an accessible evaluation framework to fully understand the performance of these algorithms on complex graphs. In this paper, we introduce the concept of hybrid graphs, a unified definition for higher-order graphs, and present the Hybrid Graph Benchmark (HGB). HGB contains 23 real-world hybrid graph datasets across various domains such as biology, social media, and e-commerce. Furthermore, we provide an extensible evaluation framework and a supporting codebase to facilitate the training and evaluation of GNNs on HGB. Our empirical study of existing GNNs on HGB reveals various research opportunities and gaps, including (1) evaluating the actual performance improvement of hypergraph GNNs over simple graph GNNs; (2) comparing the impact of different sampling strategies on hybrid graph learning methods; and (3) exploring ways to integrate simple graph and hypergraph information. We make our source code and full datasets publicly available at https://zehui127.github.io/hybrid-graph-benchmark/.

cs.LG↗

arXiv2023

Latent Diffusion Model for DNA Sequence Generation

The harnessing of machine learning, especially deep generative models, has opened up promising avenues in the field of synthetic DNA sequence generation. Whilst Generative Adversarial Networks (GANs) have gained traction for this application, they often face issues such as limited sample diversity and mode collapse. On the other hand, Diffusion Models are a promising new class of generative models that are not burdened with these problems, enabling them to reach the state-of-the-art in domains such as image generation. In light of this, we propose a novel latent diffusion model, DiscDiff, tailored for discrete DNA sequence generation. By simply embedding discrete DNA sequences into a continuous latent space using an autoencoder, we are able to leverage the powerful generative abilities of continuous diffusion models for the generation of discrete data. Additionally, we introduce Fréchet Reconstruction Distance (FReD) as a new metric to measure the sample quality of DNA sequence generations. Our DiscDiff model demonstrates an ability to generate synthetic DNA sequences that align closely with real DNA in terms of Motif Distribution, Latent Embedding Distribution (FReD), and Chromatin Profiles. Additionally, we contribute a comprehensive cross-species dataset of 150K unique promoter-gene sequences from 15 species, enriching resources for future generative modelling in genomics. We will make our code public upon publication.

cs.LG↗

arXiv2023

Genomic Interpreter: A Hierarchical Genomic Deep Neural Network with 1D Shifted Window Transformer

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.

cs.LG↗

arXiv2020

Approximations of countably-infinite linear programs over bounded measure spaces

We study a class of countably-infinite-dimensional linear programs (CILPs) whose feasible sets are bounded subsets of appropriately defined spaces of measures. The optimal value, optimal points, and minimal points of these CILPs can be approximated by solving finite-dimensional linear programs. We show how to construct finite-dimensional programs that lead to approximations with easy-to-evaluate error bounds, and we prove that the errors converge to zero as the size of the finite-dimensional programs approaches that of the original problem. We discuss the use of our methods in the computation of the stationary distributions, occupation measures, and exit distributions of Markov~chains.

math.OC↗

arXiv2020

Stationary distributions of continuous-time Markov chains: a review of theory and truncation-based approximations

Computing the stationary distributions of a continuous-time Markov chain (CTMC) involves solving a set of linear equations. In most cases of interest, the number of equations is infinite or too large, and the equations cannot be solved analytically or numerically. Several approximation schemes overcome this issue by truncating the state space to a manageable size. In this review, we first give a comprehensive theoretical account of the stationary distributions and their relation to the long-term behaviour of CTMCs that is readily accessible to non-experts and free of irreducibility assumptions made in standard texts. We then review truncation-based approximation schemes for CTMCs with infinite state spaces paying particular attention to the schemes' convergence and the errors they introduce, and we illustrate their performance with an example of a stochastic reaction network of relevance in biology and chemistry. We conclude by discussing computational trade-offs associated with error control and several open questions.

math.PR↗

arXiv2019

Robust control of biochemical reaction networks via stochastic morphing

Synthetic biology is an interdisciplinary field aiming to design biochemical systems with desired behaviors. To this end, molecular controllers have been developed which, when embedded into a pre-existing ambient biochemical network, control the dynamics of the underlying target molecular species. When integrated into smaller compartments, such as biological cells in vivo, or vesicles in vitro, controllers have to be calibrated to factor in the intrinsic noise. In this context, molecular controllers put forward in the literature have focused on manipulating the mean (first moment), and reducing the variance (second moment), of the target species. However, many critical biochemical processes are realized via higher-order moments, particularly the number and configuration of the modes (maxima) of the probability distributions. To bridge the gap, a controller called stochastic morpher is put forward in this paper, inspired by gene-regulatory networks, which, under suitable time-scale separations, morphs the probability distribution of the target species into a desired predefined form. The morphing can be performed at the lower-resolution, allowing one to achieve desired multi-modality/multi-stability, and at the higher-resolution, allowing one to achieve arbitrary probability distributions. Properties of the controller, such as robust perfect adaptation and convergence, are rigorously established, and demonstrated on various examples. Also proposed is a blueprint for an experimental implementation of stochastic morpher.

q-bio.MN↗

arXiv2019

Rigorous bounds on the stationary distributions of the chemical master equation via mathematical programming

The stochastic dynamics of biochemical networks are usually modelled with the chemical master equation (CME). The stationary distributions of CMEs are seldom solvable analytically, and numerical methods typically produce estimates with uncontrolled errors. Here, we introduce mathematical programming approaches that yield approximations of these distributions with computable error bounds which enable the verification of their accuracy. First, we use semidefinite programming to compute increasingly tighter upper and lower bounds on the moments of the stationary distributions for networks with rational propensities. Second, we use these moment bounds to formulate linear programs that yield convergent upper and lower bounds on the stationary distributions themselves, their marginals and stationary averages. The bounds obtained also provide a computational test for the uniqueness of the distribution. In the unique case, the bounds form an approximation of the stationary distribution with a computable bound on its error. In the non-unique case, our approach yields converging approximations of the ergodic distributions. We illustrate our methodology through several biochemical examples taken from the literature: Schlögl's model for a chemical bifurcation, a two-dimensional toggle switch, a model for bursty gene expression, and a dimerisation model with multiple stationary distributions.

math.PR↗

arXiv2019

The exit time finite state projection scheme: bounding exit distributions and occupation measures of continuous-time Markov chains

We introduce the exit time finite state projection (ETFSP) scheme, a truncation-based method that yields approximations to the exit distribution and occupation measure associated with the time of exit from a domain (i.e., the time of first passage to the complement of the domain) of time-homogeneous continuous-time Markov chains. We prove that: (i) the computed approximations bound the measures from below; (ii) the total variation distances between the approximations and the measures decrease monotonically as states are added to the truncation; and (iii) the scheme converges, in the sense that, as the truncation tends to the entire state space, the total variation distances tend to zero. Furthermore, we give a computable bound on the total variation distance between the exit distribution and its approximation, and we delineate the cases in which the bound is sharp. We also revisit the related finite state projection scheme and give a comprehensive account of its theoretical properties. We demonstrate the use of the ETFSP scheme by applying it to two biological examples: the computation of the first passage time associated with the expression of a gene, and the fixation times of competing species subject to demographic noise.

math.PR↗

arXiv2018

Characterization of Biologically Relevant Network Structures form Time-series Data

High-throughput data acquisition in synthetic biology leads to an abundance of data that need to be processed and aggregated into useful biological models. Building dynamical models based on this wealth of data is of paramount importance to understand and optimize designs of synthetic biology constructs. However, building models manually for each data set is inconvenient and might become infeasible for highly complex synthetic systems. In this paper, we present state-of-the-art system identification techniques and combine them with chemical reaction network theory (CRNT) to generate dynamic models automatically. On the system identification side, Sparse Bayesian Learning offers methods to learn from data the sparsest set of dictionary functions necessary to capture the dynamics of the system into ODE models; on the CRNT side, building on such sparse ODE models, all possible network structures within a given parameter uncertainty region can be computed. Additionally, the system identification process can be complemented with constraints on the parameters to, for example, enforce stability or non-negativity---thus offering relevant physical constraints over the possible network structures. In this way, the wealth of data can be translated into biologically relevant network structures, which then steers the data acquisition, thereby providing a vital step for closed-loop system identification.

eess.SY↗

arXiv2018

Global Network Prediction from Local Node Dynamics

The study of dynamical systems on networks, describing complex interactive processes, provides insight into how network structure affects global behaviour. Yet many methods for network dynamics fail to cope with large or partially-known networks, a ubiquitous situation in real-world applications. Here we propose a localised method, applicable to a broad class of dynamical models on networks, whereby individual nodes monitor and store the evolution of their own state and use these values to approximate, via a simple computation, their own steady state solution. Hence the nodes predict their own final state without actually reaching it. Furthermore, the localised formulation enables nodes to compute global network metrics without knowledge of the full network structure. The method can be used to compute global rankings in the network from local information; to detect community detection from fast, local transient dynamics; and to identify key nodes that compute global network metrics ahead of others. We illustrate some of the applications of the algorithm by efficiently performing web-page ranking for a large internet network and identifying the dynamic roles of inter-neurons in the C. Elegans neural network. The mathematical formulation is simple, widely applicable and easily scalable to real-world datasets suggesting how local computation can provide an approach to the study of large-scale network dynamics.

physics.soc-ph↗

arXiv2016

Bounding stationary averages of polynomial diffusions via semidefinite programming

We introduce an algorithm based on semidefinite programming that yields increasing (resp. decreasing) sequences of lower (resp. upper) bounds on polynomial stationary averages of diffusions with polynomial drift vector and diffusion coefficients. The bounds are obtained by optimising an objective, determined by the stationary average of interest, over the set of real vectors defined by certain linear equalities and semidefinite inequalities which are satisfied by the moments of any stationary measure of the diffusion. We exemplify the use of the approach through several applications: a Bayesian inference problem; the computation of Lyapunov exponents of linear ordinary differential equations perturbed by multiplicative white noise; and a reliability problem from structural mechanics. Additionally, we prove that the bounds converge to the infimum and supremum of the set of stationary averages for certain SDEs associated with the computation of the Lyapunov exponents, and we provide numerical evidence of convergence in more general settings.

math.PR↗

arXiv2015

Identifying Biochemical Reaction Networks From Heterogeneous Datasets

In this paper, we propose a new method to identify biochemical reaction networks (i.e. both reactions and kinetic parameters) from heterogeneous datasets. Such datasets can contain (a) data from several replicates of an experiment performed on a biological system; (b) data measured from a biochemical network subjected to different experimental conditions, for example, changes/perturbations in biological inductions, temperature, gene knock-out, gene over-expression, etc. Simultaneous integration of various datasets to perform system identification has the potential to avoid non-identifiability issues typically arising when only single datasets are used.

eess.SY↗

arXiv2015

A Sparse Bayesian Approach to the Identification of Nonlinear State-Space Systems

This technical note considers the identification of nonlinear discrete-time systems with additive process noise but without measurement noise. In particular, we propose a method and its associated algorithm to identify the system nonlinear functional forms and their associated parameters from a limited number of time-series data points. For this, we cast this identification problem as a sparse linear regression problem and take a Bayesian viewpoint to solve it. As such, this approach typically leads to nonconvex optimisations. We propose a convexification procedure relying on an efficient iterative re-weighted $\ell_1$-minimisation algorithm that uses general sparsity inducing priors on the parameters of the system and marginal likelihood maximisation. Using this approach, we also show how convex constraints on the parameters can be easily added to our proposed iterative re-weighted $\ell_1$-minimisation algorithm. In the supplementary material \cite{appendix}, we illustrate the effectiveness of the proposed identification method on two classical systems in biology and physics, namely, a genetic repressilator network and a large scale network of interconnected Kuramoto oscillators.

math.OC↗