Rana Ahmed Barghout
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rana Ahmed Barghout has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Radhakrishnan Mahadevan
University of Toronto
6 shared publications - Benjamin Sanchez-Lengeling
University of Toronto
4 shared publications - Jose Manuel Barraza Chavez
Department of Chemical Engineering & Applied Chemistry, University of Toronto, 200 College St, Toronto, M5S 3E5, ON, Canada
2 shared publications - Lya Chiñas Serrano
University of Toronto
2 shared publications - Adrian Jinich
University of California San Diego
1 shared publication Dhruv Garg
Computer Science and Engineering Department, Thapar Institute of Engineering and Technology, Patiala, India
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 22 (11) , e1014881
kinGEMs: A robust and scalable framework for resource-constraint models through stochastic tuning of deep learning-predicted kinetic parameters
The construction of accurate enzyme-constrained genome-scale models (ecGEMs) remains a critical challenge in systems biology, limited by sparse kinetic data and the need for biologically meaningful representations. This work presents an integrated framework combining CPI-Pred, a deep learning model to predict kinetic parameters ( k c a t ) from sequence and compound embeddings, with kinGEMs, a pipeline to incorporate these uncertainty-aware parameters into ecGEMs for metabolic optimization. By leveraging representations at multiple scales, the approach captures sequence, structure, and kinetic data to enhance model generalizability and accuracy. Rigorous benchmarking demonstrates the framework’s capability to predict growth rates and fluxes that are consistent with experimental observations and measured proteome fractions, reduce median flux variability by several folds, and yield better-constrained metabolic models by explicitly accounting for the uncertainty inherent in ML-predicted kinetic parameters. kinGEMs successfully generated ecGEMs for 93 models spanning a phylogenetically diverse set of organisms including Gram-negative and Gram-positive bacteria, mycobacteria, parasitic protists, fungi, and mammalian cell lines. These innovations breakdown the barrier to application of ecGEMs to non-model organisms and open new avenues for metabolic engineering and synthetic biology in more industrially relevant hosts.
- 6 November 2026
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 22 (11) , e1014881
Open AccesskinGEMs: A robust and scalable framework for resource-constraint models through stochastic tuning of deep learning-predicted kinetic parameters
The construction of accurate enzyme-constrained genome-scale models (ecGEMs) remains a critical challenge in systems biology, limited by sparse kinetic data and the need for biologically meaningful representations. This work presents an integrated framework combining CPI-Pred, a deep learning model to predict kinetic parameters ( k c a t ) from sequence and compound embeddings, with kinGEMs, a pipeline to incorporate these uncertainty-aware parameters into ecGEMs for metabolic optimization. By leveraging representations at multiple scales, the approach captures sequence, structure, and kinetic data to enhance model generalizability and accuracy. Rigorous benchmarking demonstrates the framework’s capability to predict growth rates and fluxes that are consistent with experimental observations and measured proteome fractions, reduce median flux variability by several folds, and yield better-constrained metabolic models by explicitly accounting for the uncertainty inherent in ML-predicted kinetic parameters. kinGEMs successfully generated ecGEMs for 93 models spanning a phylogenetically diverse set of organisms including Gram-negative and Gram-positive bacteria, mycobacteria, parasitic protists, fungi, and mammalian cell lines. These innovations breakdown the barrier to application of ecGEMs to non-model organisms and open new avenues for metabolic engineering and synthetic biology in more industrially relevant hosts.
- Open Access
Do protein representations encode variant function? Diagnosing residue-level protein attributions via embedding-space gradients
A common workflow in protein engineering involves building fitness predictors on protein language models (pLMs) to estimate a variant’s fitness and interpret which residues drive it. Attribution methods such as integrated gradients address this second goal by assigning residues contributions to the variant’s predicted fitness. However, without ground truth for residue importance, it is unclear whether these attributions reflect what the predictor learned about function. Here, we introduce IGLOO , a framework that scores residue-level attributions against synthetic fitness landscapes with known per-residue importance. Across experimental axes, high predictive accuracy did not guarantee faithful attributions. We identify model interventions that more than double attribution skill scores and raise TOPSIS by 29% , with similar patterns holding in real α -amylase and β -lactamase datasets. IGLOO provides a protocol for probing what pLMs learn and a guide for choosing defaults when using residue attributions to pick sequence edits and build more trustworthy protein models.
Open AccessDo protein representations encode variant function? Diagnosing residue-level protein attributions via embedding-space gradients
A common workflow in protein engineering involves building fitness predictors on protein language models (pLMs) to estimate a variant’s fitness and interpret which residues drive it. Attribution methods such as integrated gradients address this second goal by assigning residues contributions to the variant’s predicted fitness. However, without ground truth for residue importance, it is unclear whether these attributions reflect what the predictor learned about function. Here, we introduce IGLOO , a framework that scores residue-level attributions against synthetic fitness landscapes with known per-residue importance. Across experimental axes, high predictive accuracy did not guarantee faithful attributions. We identify model interventions that more than double attribution skill scores and raise TOPSIS by 29% , with similar patterns holding in real α -amylase and β -lactamase datasets. IGLOO provides a protocol for probing what pLMs learn and a guide for choosing defaults when using residue attributions to pick sequence edits and build more trustworthy protein models.
- Open Access
kinGEMs: A Robust and Scalable Framework for Resource-Constraint Models through Stochastic Tuning of Deep Learning-Predicted Kinetic Parameters
The construction of accurate enzyme-constrained genome-scale models (ecGEMs) remains a critical challenge in systems biology, limited by sparse kinetic data and the need for biologically meaningful representations. This work presents an integrated framework combining CPI-Pred, a deep learning model to predict kinetic parameters ( k cat ) from sequence and compound embeddings, with kinGEMs, a pipeline to incorporate these uncertainty-aware parameters into ecGEMs for metabolic optimization. By leveraging representations at multiple scales, the approach captures sequence, structure, and kinetic data to enhance model generalizability and accuracy. Rigorous benchmarking demonstrates the framework’s capability to predict growth rates and fluxes that are consistent with experimental observations and measured proteome fractions, reduce median flux variability by several folds, and yield better-constrained metabolic models by explicitly accounting for the uncertainty inherent in ML-predicted kinetic parameters. kinGEMs successfully generated ecGEMs for 93 models spanning a phylogenetically diverse set of organisms including Gram-negative and Gram-positive bacteria, mycobacteria, parasitic protists, fungi, and mammalian cell lines. These innovations breakdown the barrier to application of ecGEMs to non-model organisms and open new avenues for metabolic engineering and synthetic biology in more industrially relevant hosts. 1 Author Summary: Living cells are chemical factories, and computer models of their metabolism can predict how they grow, what they consume, and what they produce, useful for everything from engineering biofuel-producing microbes to understanding disease. The more realistic versions of these models require knowing how fast each cellular enzyme works, but this information is missing for the vast majority of enzymes, especially outside of a handful of well-studied organisms like E. coli . We built kinGEMs, an automated pipeline that fills these gaps using a machine learning model to predict enzyme speeds directly from protein sequence, then automatically fine-tunes those predictions so the resulting model’s growth matches real experimental measurements. We show that models built this way better match independent, real-world data they were never tuned to match, including detailed protein-abundance measurements and a classic metabolic behavior (bacteria switching to fermentation at high growth rates) that conventional models cannot reproduce without manual intervention. We also show the approach works reasonably well across 93 different organisms and successfully reconstructs known metabolic trade-offs in an oil-producing yeast unrelated to E. coli . This provides a scalable way to build usable, enzyme-aware metabolic models for organisms that currently lack the detailed experimental data such models normally require.
Open AccesskinGEMs: A Robust and Scalable Framework for Resource-Constraint Models through Stochastic Tuning of Deep Learning-Predicted Kinetic Parameters
The construction of accurate enzyme-constrained genome-scale models (ecGEMs) remains a critical challenge in systems biology, limited by sparse kinetic data and the need for biologically meaningful representations. This work presents an integrated framework combining CPI-Pred, a deep learning model to predict kinetic parameters ( k cat ) from sequence and compound embeddings, with kinGEMs, a pipeline to incorporate these uncertainty-aware parameters into ecGEMs for metabolic optimization. By leveraging representations at multiple scales, the approach captures sequence, structure, and kinetic data to enhance model generalizability and accuracy. Rigorous benchmarking demonstrates the framework’s capability to predict growth rates and fluxes that are consistent with experimental observations and measured proteome fractions, reduce median flux variability by several folds, and yield better-constrained metabolic models by explicitly accounting for the uncertainty inherent in ML-predicted kinetic parameters. kinGEMs successfully generated ecGEMs for 93 models spanning a phylogenetically diverse set of organisms including Gram-negative and Gram-positive bacteria, mycobacteria, parasitic protists, fungi, and mammalian cell lines. These innovations breakdown the barrier to application of ecGEMs to non-model organisms and open new avenues for metabolic engineering and synthetic biology in more industrially relevant hosts. 1 Author Summary: Living cells are chemical factories, and computer models of their metabolism can predict how they grow, what they consume, and what they produce, useful for everything from engineering biofuel-producing microbes to understanding disease. The more realistic versions of these models require knowing how fast each cellular enzyme works, but this information is missing for the vast majority of enzymes, especially outside of a handful of well-studied organisms like E. coli . We built kinGEMs, an automated pipeline that fills these gaps using a machine learning model to predict enzyme speeds directly from protein sequence, then automatically fine-tunes those predictions so the resulting model’s growth matches real experimental measurements. We show that models built this way better match independent, real-world data they were never tuned to match, including detailed protein-abundance measurements and a classic metabolic behavior (bacteria switching to fermentation at high growth rates) that conventional models cannot reproduce without manual intervention. We also show the approach works reasonably well across 93 different organisms and successfully reconstructs known metabolic trade-offs in an oil-producing yeast unrelated to E. coli . This provides a scalable way to build usable, enzyme-aware metabolic models for organisms that currently lack the detailed experimental data such models normally require.
- 8 July 2025
- Published by American Chemical Society (ACS)
Graph Data Modeling: Molecules, Proteins, & Chemical Processes
- 8 July 2025
- Published by American Chemical Society (ACS)
Graph Data Modeling: Molecules, Proteins, & Chemical Processes
- Open Access
CPI-Pred: A deep learning framework for predicting functional parameters of compound-protein interactions
Recent advancements in deep learning have enabled functional annotation of genome sequences, facilitating the discovery of new enzymes and metabolites. However, accurately predicting compound-protein interactions (CPI) from sequences remains challenging due to the complexity of these interactions and the sparsity and heterogeneity of available data, which constrain the generalization of patterns across their solution space. In this work, we introduce CPI-Pred, a versatile deep learning model designed to predict compound-protein interaction function. CPI-Pred integrates compound representations derived from a novel message-passing neural network and enzyme representations generated by state-of-the-art protein language models, leveraging innovative sequence pooling and cross-attention mechanisms. To train and evaluate CPI-Pred, we compiled the largest dataset of enzyme kinetic parameters to date, encompassing four key metrics: the Michaelis-Menten constant ( K M ), enzyme turnover number ( k cat ), catalytic efficiency ( k cat /K M ), and inhibition constant ( K I ).These kinetic parameters are critical for elucidating enzyme function in metabolic contexts and understanding their regulation by compounds within biological networks. We demonstrate that CPI-Pred can predict diverse types of CPI using only the amino acid sequence of enzymes and structural representations of compounds, outperforming state-of-the-art models on unseen compounds and structurally dissimilar enzymes. Over workflow provides a valuable tool for tackling a range of metabolic engineering challenges, including the designing of novel enzyme sequences and compounds, such as enzyme inhibitors. Additionally, the datasets curated in this study offer a valuable resource for the scientific community, serving as a benchmark for machine learning models focused on enzyme activity and promiscuity prediction.
Open AccessCPI-Pred: A deep learning framework for predicting functional parameters of compound-protein interactions
Recent advancements in deep learning have enabled functional annotation of genome sequences, facilitating the discovery of new enzymes and metabolites. However, accurately predicting compound-protein interactions (CPI) from sequences remains challenging due to the complexity of these interactions and the sparsity and heterogeneity of available data, which constrain the generalization of patterns across their solution space. In this work, we introduce CPI-Pred, a versatile deep learning model designed to predict compound-protein interaction function. CPI-Pred integrates compound representations derived from a novel message-passing neural network and enzyme representations generated by state-of-the-art protein language models, leveraging innovative sequence pooling and cross-attention mechanisms. To train and evaluate CPI-Pred, we compiled the largest dataset of enzyme kinetic parameters to date, encompassing four key metrics: the Michaelis-Menten constant ( K M ), enzyme turnover number ( k cat ), catalytic efficiency ( k cat /K M ), and inhibition constant ( K I ).These kinetic parameters are critical for elucidating enzyme function in metabolic contexts and understanding their regulation by compounds within biological networks. We demonstrate that CPI-Pred can predict diverse types of CPI using only the amino acid sequence of enzymes and structural representations of compounds, outperforming state-of-the-art models on unseen compounds and structurally dissimilar enzymes. Over workflow provides a valuable tool for tackling a range of metabolic engineering challenges, including the designing of novel enzyme sequences and compounds, such as enzyme inhibitors. Additionally, the datasets curated in this study offer a valuable resource for the scientific community, serving as a benchmark for machine learning models focused on enzyme activity and promiscuity prediction.
- Open Access
- 12 October 2022
- Published by Oxford University Press (OUP) in Database: The Journal of Biological Databases and Curation
- Vol. 2022
KinMod database: a tool for investigating metabolic regulation
The ability of current kinetic models to simulate the phenotypic behaviour of cells is limited since cell metabolism is regulated at different levels including enzyme regulation. The small molecule regulation network (SMRN) enables cells to respond rapidly to environmental fluctuations by controlling the activity of enzymes in metabolic pathways. However, SMRN is not as well studied relative to metabolic networks. The main contributor to the lack of knowledge on this regulatory system is the sparsity of experimental data and the absence of a standard framework for representing available information. In this paper, we introduce the KinMod database that encompasses more than 2 million data points on the metabolism and metabolic regulation network of 9814 organisms KinMod database employs a hierarchical data structure to: (i) signify relationships between kinetic information obtained through in-vitro experiments and proteins, with an emphasis on SMRN, (ii) provide a thorough insight into available kinetic parameters and missing experimental measurements of this regulatory network and (iii) facilitate machine learning approaches for parameter estimation and accurate kinetic model construction by providing a homogeneous list of linked omics data. The hierarchical ontology of the KinMod database allows flexible exploration of data attributes and investigation of metabolic relationships within- and cross-species. Identifying missing experimental values suggests additional experiments required for kinetic parameter estimation. Linking multi-omics data and providing data on SMRN encourages the development of novel machine learning techniques for predicting missing kinetic parameters and promotes accurate kinetic model construction of cells metabolism by providing a comprehensive list of available kinetic measurements. To illustrate the value of KinMod data, we develop six analyses to visualize associations between data classes belonging to separate sections of the metabolism. Through these analyses, we demonstrate that the KinMod database provides a unique framework for biologists and engineers to retrieve, evaluate and compare the functional metabolism of species, including the regulatory network, and discover the extent of available and missing experimental values of the metabolic regulation. Database URL: https://lmse.utoronto.ca/kinmod/KINMOD.sql.gz
- 12 October 2022
- Published by Oxford University Press (OUP) in Database: The Journal of Biological Databases and Curation
- Vol. 2022
Open AccessKinMod database: a tool for investigating metabolic regulation
The ability of current kinetic models to simulate the phenotypic behaviour of cells is limited since cell metabolism is regulated at different levels including enzyme regulation. The small molecule regulation network (SMRN) enables cells to respond rapidly to environmental fluctuations by controlling the activity of enzymes in metabolic pathways. However, SMRN is not as well studied relative to metabolic networks. The main contributor to the lack of knowledge on this regulatory system is the sparsity of experimental data and the absence of a standard framework for representing available information. In this paper, we introduce the KinMod database that encompasses more than 2 million data points on the metabolism and metabolic regulation network of 9814 organisms KinMod database employs a hierarchical data structure to: (i) signify relationships between kinetic information obtained through in-vitro experiments and proteins, with an emphasis on SMRN, (ii) provide a thorough insight into available kinetic parameters and missing experimental measurements of this regulatory network and (iii) facilitate machine learning approaches for parameter estimation and accurate kinetic model construction by providing a homogeneous list of linked omics data. The hierarchical ontology of the KinMod database allows flexible exploration of data attributes and investigation of metabolic relationships within- and cross-species. Identifying missing experimental values suggests additional experiments required for kinetic parameter estimation. Linking multi-omics data and providing data on SMRN encourages the development of novel machine learning techniques for predicting missing kinetic parameters and promotes accurate kinetic model construction of cells metabolism by providing a comprehensive list of available kinetic measurements. To illustrate the value of KinMod data, we develop six analyses to visualize associations between data classes belonging to separate sections of the metabolism. Through these analyses, we demonstrate that the KinMod database provides a unique framework for biologists and engineers to retrieve, evaluate and compare the functional metabolism of species, including the regulatory network, and discover the extent of available and missing experimental values of the metabolic regulation. Database URL: https://lmse.utoronto.ca/kinmod/KINMOD.sql.gz