Laura M. Gunsalus
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Laura M. Gunsalus has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Katherine S. Pollard
Chan Zuckerberg Biohub, University of California, San Francisco, Gladstone Institute, USA
6 shared publications - Gokcen Eraslan
Genentech
4 shared publications - Michael J. Keiser
Institute for Neurodegenerative Diseases, University of California, San Francisco, San Francisco, USA
4 shared publications - Avantika Lal
Genentech
3 shared publications - Surag Nair
Biology Research | AI Development, gRED Computational Sciences, Genentech, South San Francisco, CA, USA
3 shared publications - Tommaso Biancalani
RED Computational Sciences, Genentech Research and Early Development, San Francisco, USA
3 shared publications
Latest Publications
- 25 May 2026
- Published by Springer Nature in Nature Methods
- Vol. 23 (6) , 1138-1151
Decoding sequence determinants of gene expression in diverse cellular and disease states
Sequence-to-function models that predict gene expression from genomic DNA sequence have proven valuable for many biological tasks, including understanding cis-regulatory syntax and interpreting noncoding genetic variation. However, current state-of-the-art models are trained largely on bulk expression profiles from healthy tissues or cell lines and have not learned the properties of precise cell types and states that are captured in large-scale single-cell transcriptomic datasets. Thus, they cannot perform these tasks at the resolution of specific cell types or states. Here we present Decima, a model that predicts the cell type- and condition-specific expression of a gene from its surrounding DNA sequence. Decima is trained on single-cell or single-nucleus RNA sequencing data from over 22 million cells and successfully predicts the cell-type-specific expression of unseen genes. We demonstrate Decima's ability to reveal cis-regulatory mechanisms driving cell-type-specific gene expression and its changes in disease, predict noncoding-variant effects at cell type resolution and design context-specific regulatory DNA elements.
- 25 May 2026
- Published by Springer Nature in Nature Methods
- Vol. 23 (6) , 1138-1151
Decoding sequence determinants of gene expression in diverse cellular and disease states
Sequence-to-function models that predict gene expression from genomic DNA sequence have proven valuable for many biological tasks, including understanding cis-regulatory syntax and interpreting noncoding genetic variation. However, current state-of-the-art models are trained largely on bulk expression profiles from healthy tissues or cell lines and have not learned the properties of precise cell types and states that are captured in large-scale single-cell transcriptomic datasets. Thus, they cannot perform these tasks at the resolution of specific cell types or states. Here we present Decima, a model that predicts the cell type- and condition-specific expression of a gene from its surrounding DNA sequence. Decima is trained on single-cell or single-nucleus RNA sequencing data from over 22 million cells and successfully predicts the cell-type-specific expression of unseen genes. We demonstrate Decima's ability to reveal cis-regulatory mechanisms driving cell-type-specific gene expression and its changes in disease, predict noncoding-variant effects at cell type resolution and design context-specific regulatory DNA elements.
- Top Cited PapersOpen Access
Agentic systems are adept at solving well-scoped, verifiable problems in computational biology
We introduce CompBioBench, a benchmark of 100 diverse tasks for evaluating agentic systems in computational biology. Unlike mathematics and programming, which more readily admit systematic verification, biological data are inherently noisy and open to interpretation. To enable objective evaluation without reducing tasks to prescriptive checklists, we propose a new benchmark construction strategy based on synthetic/augmented data and metadata scrambling/scrubbing of real datasets to create challenging problems that have a single ground-truth answer and require multi-step reasoning, tool use, bespoke code, and interaction with real-world external resources. The benchmark spans genomics, transcriptomics, epigenomics, single-cell analysis, human genetics, and machine learning workflows. Questions are curated by domain experts to cover a broad range of skills with varying difficulty. We evaluate leading general-purpose agentic systems starting from a bare-minimum environment, requiring them to fetch data and tools as needed to solve each problem. We find strong end-to-end performance, with Codex CLI (GPT 5.4) reaching 83% accuracy, Gemini CLI (3.1 Pro) reaching 82%, Claude Code (Opus 4.6) reaching 81%, and Claude Code (Opus 4.7) reaching 78%. On the hardest questions, Claude Code (Opus 4.6) reaches 69%, Codex CLI (GPT 5.4) reaches 59%, and Gemini CLI (3.1 Pro) reaches 49%. CompBioBench provides a practical testbed for measuring the progress of agentic systems in computational biology and for guiding future benchmark design. Data and a public leaderboard are available at https://huggingface.co/collections/Genentech/compbiobench-v1.
Top Cited PapersOpen AccessAgentic systems are adept at solving well-scoped, verifiable problems in computational biology
We introduce CompBioBench, a benchmark of 100 diverse tasks for evaluating agentic systems in computational biology. Unlike mathematics and programming, which more readily admit systematic verification, biological data are inherently noisy and open to interpretation. To enable objective evaluation without reducing tasks to prescriptive checklists, we propose a new benchmark construction strategy based on synthetic/augmented data and metadata scrambling/scrubbing of real datasets to create challenging problems that have a single ground-truth answer and require multi-step reasoning, tool use, bespoke code, and interaction with real-world external resources. The benchmark spans genomics, transcriptomics, epigenomics, single-cell analysis, human genetics, and machine learning workflows. Questions are curated by domain experts to cover a broad range of skills with varying difficulty. We evaluate leading general-purpose agentic systems starting from a bare-minimum environment, requiring them to fetch data and tools as needed to solve each problem. We find strong end-to-end performance, with Codex CLI (GPT 5.4) reaching 83% accuracy, Gemini CLI (3.1 Pro) reaching 82%, Claude Code (Opus 4.6) reaching 81%, and Claude Code (Opus 4.7) reaching 78%. On the hardest questions, Claude Code (Opus 4.6) reaches 69%, Codex CLI (GPT 5.4) reaches 59%, and Gemini CLI (3.1 Pro) reaches 49%. CompBioBench provides a practical testbed for measuring the progress of agentic systems in computational biology and for guiding future benchmark design. Data and a public leaderboard are available at https://huggingface.co/collections/Genentech/compbiobench-v1.
- Open Access
- 15 October 2025
- Published by Springer Nature in Nature Methods
- Vol. 22 (11) , 2253-2257
gReLU: a comprehensive framework for DNA sequence modeling and design
Deep learning models trained on DNA sequences can predict cell-type-specific regulatory activity, reveal cis-regulatory grammar, prioritize genetic variants and design synthetic DNA. However, building and interpreting these models correctly remains difficult, and models and software built by different groups are often not interoperable. Here we present gReLU, a comprehensive software framework that enables advanced sequence modeling pipelines, including data preprocessing, modeling, evaluation, interpretation, variant effect prediction and regulatory element design.
- 15 October 2025
- Published by Springer Nature in Nature Methods
- Vol. 22 (11) , 2253-2257
Open AccessgReLU: a comprehensive framework for DNA sequence modeling and design
Deep learning models trained on DNA sequences can predict cell-type-specific regulatory activity, reveal cis-regulatory grammar, prioritize genetic variants and design synthetic DNA. However, building and interpreting these models correctly remains difficult, and models and software built by different groups are often not interoperable. Here we present gReLU, a comprehensive software framework that enables advanced sequence modeling pipelines, including data preprocessing, modeling, evaluation, interpretation, variant effect prediction and regulatory element design.
- Open Access
- 18 February 2025
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 21 (2) , e1012841
ChromaFactor: Deconvolution of single-molecule chromatin organization with non-negative matrix factorization
The investigation of chromatin organization in single cells holds great promise for identifying causal relationships between genome structure and function. However, analysis of single-molecule data is hampered by extreme yet inherent heterogeneity, making it challenging to determine the contributions of individual chromatin fibers to bulk trends. To address this challenge, we propose ChromaFactor, a novel computational approach based on non-negative matrix factorization that deconvolves single-molecule chromatin organization datasets into their most salient primary components. ChromaFactor provides the ability to identify trends accounting for the maximum variance in the dataset while simultaneously describing the contribution of individual molecules to each component. Applying our approach to two single-molecule imaging datasets across different genomic scales, we find that these primary components demonstrate significant correlation with key functional phenotypes, including active transcription, enhancer-promoter distance, and genomic compartment. Also, we find that some bulk trends exist at the single-cell level, but only in a small fraction of cells, suggesting that critical changes in genome organization may be driven by specific rare subpopulations rather than occurring uniformly across all cells. ChromaFactor offers a robust tool for understanding the complex interplay between chromatin structure and function on individual DNA molecules, pinpointing which subpopulations drive functional changes and fostering new insights into cellular heterogeneity and its implications for bulk genomic phenomena.
- 18 February 2025
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 21 (2) , e1012841
Open AccessChromaFactor: Deconvolution of single-molecule chromatin organization with non-negative matrix factorization
The investigation of chromatin organization in single cells holds great promise for identifying causal relationships between genome structure and function. However, analysis of single-molecule data is hampered by extreme yet inherent heterogeneity, making it challenging to determine the contributions of individual chromatin fibers to bulk trends. To address this challenge, we propose ChromaFactor, a novel computational approach based on non-negative matrix factorization that deconvolves single-molecule chromatin organization datasets into their most salient primary components. ChromaFactor provides the ability to identify trends accounting for the maximum variance in the dataset while simultaneously describing the contribution of individual molecules to each component. Applying our approach to two single-molecule imaging datasets across different genomic scales, we find that these primary components demonstrate significant correlation with key functional phenotypes, including active transcription, enhancer-promoter distance, and genomic compartment. Also, we find that some bulk trends exist at the single-cell level, but only in a small fraction of cells, suggesting that critical changes in genome organization may be driven by specific rare subpopulations rather than occurring uniformly across all cells. ChromaFactor offers a robust tool for understanding the complex interplay between chromatin structure and function on individual DNA molecules, pinpointing which subpopulations drive functional changes and fostering new insights into cellular heterogeneity and its implications for bulk genomic phenomena.
- Open Access
Polygraph: A Software Framework for the Systematic Assessment of Synthetic Regulatory DNA Elements
The design of regulatory elements is pivotal in gene and cell therapy, where DNA sequences are engineered to drive elevated and cell-type specific expression. However, the systematic assessment of synthetic DNA sequences without robust metrics and easy-to-use software remains challenging. Here, we introduce Polygraph, a Python framework that evaluates synthetic DNA elements, based on features like diversity, motif and k-mer composition, similarity to endogenous sequences, and screening with predictive and foundational models. Polygraph is the first instrument for assessing synthetic regulatory sequences, enabling faster progress in therapeutic interventions and improving our understanding of gene regulatory mechanisms.
Open AccessPolygraph: A Software Framework for the Systematic Assessment of Synthetic Regulatory DNA Elements
The design of regulatory elements is pivotal in gene and cell therapy, where DNA sequences are engineered to drive elevated and cell-type specific expression. However, the systematic assessment of synthetic DNA sequences without robust metrics and easy-to-use software remains challenging. Here, we introduce Polygraph, a Python framework that evaluates synthetic DNA elements, based on features like diversity, motif and k-mer composition, similarity to endogenous sequences, and screening with predictive and foundational models. Polygraph is the first instrument for assessing synthetic regulatory sequences, enabling faster progress in therapeutic interventions and improving our understanding of gene regulatory mechanisms.
- Open Access
ChromaFactor: deconvolution of single-molecule chromatin organization with non-negative matrix factorization
The investigation of chromatin organization in single cells holds great promise for identifying causal relationships between genome structure and function. However, analysis of single-molecule data is hampered by extreme yet inherent heterogeneity, making it challenging to determine the contributions of individual chromatin fibers to bulk trends. To address this challenge, we propose ChromaFactor, a novel computational approach based on non-negative matrix factorization that deconvolves single-molecule chromatin organization datasets into their most salient primary components. ChromaFactor provides the ability to identify trends accounting for the maximum variance in the dataset while simultaneously describing the contribution of individual molecules to each component. Applying our approach to two single-molecule imaging datasets across different genomic scales, we find that these primary components demonstrate significant correlation with key functional phenotypes, including active transcription, enhancer-promoter distance, and genomic compartment. ChromaFactor offers a robust tool for understanding the complex interplay between chromatin structure and function on individual DNA molecules, pinpointing which subpopulations drive functional changes and fostering new insights into cellular heterogeneity and its implications for bulk genomic phenomena.
Open AccessChromaFactor: deconvolution of single-molecule chromatin organization with non-negative matrix factorization
The investigation of chromatin organization in single cells holds great promise for identifying causal relationships between genome structure and function. However, analysis of single-molecule data is hampered by extreme yet inherent heterogeneity, making it challenging to determine the contributions of individual chromatin fibers to bulk trends. To address this challenge, we propose ChromaFactor, a novel computational approach based on non-negative matrix factorization that deconvolves single-molecule chromatin organization datasets into their most salient primary components. ChromaFactor provides the ability to identify trends accounting for the maximum variance in the dataset while simultaneously describing the contribution of individual molecules to each component. Applying our approach to two single-molecule imaging datasets across different genomic scales, we find that these primary components demonstrate significant correlation with key functional phenotypes, including active transcription, enhancer-promoter distance, and genomic compartment. ChromaFactor offers a robust tool for understanding the complex interplay between chromatin structure and function on individual DNA molecules, pinpointing which subpopulations drive functional changes and fostering new insights into cellular heterogeneity and its implications for bulk genomic phenomena.
- Open Access
- 25 September 2023
- Published by Elsevier in Cell Genomics
- Vol. 3 (10) , 100410
In silico discovery of repetitive elements as key sequence determinants of 3D genome folding
- 25 September 2023
- Published by Elsevier in Cell Genomics
- Vol. 3 (10) , 100410
Open AccessIn silico discovery of repetitive elements as key sequence determinants of 3D genome folding
- Open Access
- 23 May 2023
- Published by Springer Nature in Research Square
Comparing chromatin contact maps at scale: methods and insights
Comparing chromatin contact maps is an essential step in quantifying how three-dimensional (3D) genome organization shapes development, evolution, and disease. However, no gold standard exists for comparing contact maps, and even simple methods often disagree. In this study, we propose novel comparison methods and evaluate them alongside existing approaches using genome-wide Hi-C data and 22,500 in silico predicted contact maps. We also quantify the robustness of methods to common sources of biological and technical variation, such as boundary size and noise. We find that simple difference-based methods such as mean squared error are suitable for initial screening, but biologically informed methods are necessary to identify why maps diverge and propose specific functional hypotheses. We provide a reference guide, codebase, and benchmark for rapidly comparing chromatin contact maps at scale to enable biological insights into the 3D organization of the genome.
- 23 May 2023
- Published by Springer Nature in Research Square
Open AccessComparing chromatin contact maps at scale: methods and insights
Comparing chromatin contact maps is an essential step in quantifying how three-dimensional (3D) genome organization shapes development, evolution, and disease. However, no gold standard exists for comparing contact maps, and even simple methods often disagree. In this study, we propose novel comparison methods and evaluate them alongside existing approaches using genome-wide Hi-C data and 22,500 in silico predicted contact maps. We also quantify the robustness of methods to common sources of biological and technical variation, such as boundary size and noise. We find that simple difference-based methods such as mean squared error are suitable for initial screening, but biologically informed methods are necessary to identify why maps diverge and propose specific functional hypotheses. We provide a reference guide, codebase, and benchmark for rapidly comparing chromatin contact maps at scale to enable biological insights into the 3D organization of the genome.
- Open Access
Comparing chromatin contact maps at scale: methods and insights
Comparing chromatin contact maps is an essential step in quantifying how three-dimensional (3D) genome organization shapes development, evolution, and disease. However, no gold standard exists for comparing contact maps, and even simple methods often disagree. In this study, we propose novel comparison methods and evaluate them alongside existing approaches using genome-wide Hi-C data and 22,500 in silico predicted contact maps. We also quantify the robustness of methods to common sources of biological and technical variation, such as boundary size and noise. We find that simple difference-based methods such as mean squared error are suitable for initial screening, but biologically informed methods are necessary to identify why maps diverge and propose specific functional hypotheses. We provide a reference guide, codebase, and benchmark for rapidly comparing chromatin contact maps at scale to enable biological insights into the 3D organization of the genome.
Open AccessComparing chromatin contact maps at scale: methods and insights
Comparing chromatin contact maps is an essential step in quantifying how three-dimensional (3D) genome organization shapes development, evolution, and disease. However, no gold standard exists for comparing contact maps, and even simple methods often disagree. In this study, we propose novel comparison methods and evaluate them alongside existing approaches using genome-wide Hi-C data and 22,500 in silico predicted contact maps. We also quantify the robustness of methods to common sources of biological and technical variation, such as boundary size and noise. We find that simple difference-based methods such as mean squared error are suitable for initial screening, but biologically informed methods are necessary to identify why maps diverge and propose specific functional hypotheses. We provide a reference guide, codebase, and benchmark for rapidly comparing chromatin contact maps at scale to enable biological insights into the 3D organization of the genome.
- Open Access
In silico discovery of repetitive elements as key sequence determinants of 3D genome folding
Natural and experimental genetic variants can modify DNA loops and insulating boundaries to tune transcription, but it is unknown how sequence perturbations affect chromatin organization genome-wide. We developed an in silico deep-learning strategy to quantify the effect of any insertion, deletion, inversion, or substitution on chromatin contacts and systematically scored millions of synthetic variants. While most genetic manipulations have little impact, regions with CTCF motifs and active transcription are highly sensitive, as expected. However, our analysis also points to noncoding RNA genes and several families of repetitive elements as CTCF motif-free DNA sequences with particularly large effects on nearby chromatin interactions, sometimes exceeding the effects of CTCF sites and explaining interactions that lack CTCF. We anticipate that our available disruption tracks may be of broad interest and utility as a measure of 3D genome sensitivity and our computational strategies may serve as a template for biological inquiry with deep learning.
Open AccessIn silico discovery of repetitive elements as key sequence determinants of 3D genome folding
Natural and experimental genetic variants can modify DNA loops and insulating boundaries to tune transcription, but it is unknown how sequence perturbations affect chromatin organization genome-wide. We developed an in silico deep-learning strategy to quantify the effect of any insertion, deletion, inversion, or substitution on chromatin contacts and systematically scored millions of synthetic variants. While most genetic manipulations have little impact, regions with CTCF motifs and active transcription are highly sensitive, as expected. However, our analysis also points to noncoding RNA genes and several families of repetitive elements as CTCF motif-free DNA sequences with particularly large effects on nearby chromatin interactions, sometimes exceeding the effects of CTCF sites and explaining interactions that lack CTCF. We anticipate that our available disruption tracks may be of broad interest and utility as a measure of 3D genome sensitivity and our computational strategies may serve as a template for biological inquiry with deep learning.