Biology subjects

Emad, A.

Publications and source records attributed to Emad, A..

At least 19 recordsLinked to original sources

bioRxiv2026

DiffDose: Differentiable Programming for Personalized Dose-Regimen Optimal Control

Dose-regimen design requires choosing how much drug to give, when to give it, and how treatment should vary across patients. Mechanistic pharmacokinetic-pharmacodynamic (PK/PD) and quantitative systems pharmacology (QSP) models can predict treatment responses, but optimizing dosing inputs depends on model-specific sensitivity derivations or derivative-free search. Here, we introduce DiffDose, a differentiable programming framework for mechanistic open-loop dose-regimen optimization that uses automatic differentiation (AD) to handle clinically interpretable dose amounts and administration times as differentiable controls. We evaluate our method in three settings: fixed-schedule dose-amplitude optimization in OptiDose PK/PD benchmarks; dose-timing optimization in a chemotherapy-induced neutropenia model with state-dependent delay; and individualized mosunetuzumab dosing in a QSP virtual population. Across these examples, AD produced gradients consistent with references, reduced model-specific derivative work, and shortened benchmark time to solution. DiffDose thereby turns mechanistic PK/PD and QSP models from tools that evaluate prespecified regimens into gradient-based engines for individualized regimen design.

systems biology↗

bioRxiv2026

A latent space thermodynamic model of cell differentiation

Inferring the governing dynamics of differentiation that capture cell state evolution remains a central challenge in single-cell biology. We present Latent Space Dynamics (LSD), a thermodynamics-inspired framework that models cell differentiation as evolution on a learned Waddington landscape in latent space. LSD jointly infers a low-dimensional cell state, a differentiable potential function governing developmental flow, and a local entropy term that quantifies cellular plasticity. Using a neural ordinary differential equation, LSD reconstructs continuous differentiation trajectories from time-ordered single-cell data. Across diverse developmental systems, LSD accurately recovers lineage hierarchies, predicts fate commitment for unseen cell types, and outperforms existing trajectory inference approaches in directional accuracy. Moreover, in silico gene perturbations reveal how individual regulators reshape the landscape, and entropy provides a quantitative measure of plasticity in development and cancer.

bioinformatics↗

bioRxiv2026

CellPace: A temporal diffusion-forcing framework for simulation, interpolation and forecasting of single-cell dynamics

Single-cell omics technologies resolve cellular heterogeneity at high resolution but provide only static snapshots of continuous developmental processes. This makes it difficult to recover coherent temporal dynamics when developmental stages are irregularly sampled or missing. While recent generative models can simulate observed cell states, they often treat timepoints as discrete categories, hindering interpolation across gaps and extrapolation to unobserved future stages. We present CellPace, a generative model that learns and generates developmental dynamics by leveraging a transformer-based temporal diffusion backbone conditioned on continuous, gap-aware temporal encodings. Across diverse mouse developmental lineages, CellPace achieves state-of-the-art performance in simulation, interpolation, and forecasting tasks. Beyond recovering global population statistics, generated cells preserve fine-grained biological structure, retaining dynamic gene regulatory programs and mapping accurately to anatomical regions in spatial transcriptomics data. Furthermore, CellPace extends naturally to multi-modal data, modeling joint RNA-chromatin dynamics even when temporal ordering is inferred from pseudotime. Together, these results position CellPace as a robust framework for modeling and generating continuous developmental dynamics from sparse, cross-sectional single-cell data.

bioinformatics↗

bioRxiv2025

Causal single-cell RNA-seq simulation, in silico perturbation, and GRN inference benchmarking using GRouNdGAN-Toolkit

BackgroundRapid advances in high-throughput single-cell sequencing technologies, coupled with the development of computational methods capable of leveraging large datasets, have led to the emergence of numerous approaches for deciphering regulatory interactions in the form of Gene Regulatory Networks (GRNs). However, in the absence of context-specific gold-standard ground truths, particularly those containing causal interactions, systematically benchmarking GRN inference methods remains a challenge. Thus, we previously developed GRouNdGAN, a causal implicit generative model capable of simulating realistic observational and interventional scRNA-seq data following a user-defined GRN on any biological system of interest. Importantly, we demonstrated that GRouNdGAN generates datasets that bridge the gap between experimentation and simulation for GRN inference benchmarking. MethodBuilding upon the GRouNdGAN framework, we developed an extended toolkit that offers additional features, including interactive model visualization, training monitoring, more customizable GRN creation options, synthetic data similarity and GRN inference benchmarking metrics, and an intuitive TF knockout prediction module. Here, we provide a step-by-step procedure for implementing the protocol from start to finish and introduce alternative variations to adapt GRouNdGAN to studies with different experimental setups. GRouNdGAN-Toolkit is publicly available as a python code repository and containerized application and is accompanied by a tutorial website featuring a collection of simulated datasets. Model training largely depends on graphic hardware and the size and density of the input GRN, and typically takes around 75h to complete on a single GPU. Excluding model training, this protocol typically takes less than 25min to complete. DiscussionGRouNdGAN-Toolkit is a versatile simulator with user friendly interface that does not assume advanced computational genomics expertise, enhancing its usability and accessibility across a wide range of users.

bioinformatics↗

bioRxiv2025

Multi-Modal Protein Representation Learning with CLASP

Effectively integrating data modalities pertaining to proteins amino acid sequences, three-dimensional structures, and curated text-based descriptions of their biochemical and functional properties can lead to informative representations capturing different views of proteins. Here, we introduce CLASP, a unified tri-modal framework that combines the strengths of geometric deep learning, natural large language models (LLMs), protein language models (pLMs), and contrastive learning to learn informative protein representations based on their structure, amino acid sequence, and text-based biochemical and functional descriptions. We show that CLASP enables accurate zero-shot classification and retrieval tasks, such as matching a protein structure to its sequence or description, outperforming state-of-the-art baselines. CLASP embeddings also exhibit superior clustering by protein family, and ablation studies confirm that all three modalities contribute synergistically to performance. Our results highlight the power of integrating structural, sequential, and textual signals in a single model, establishing CLASP as a general-purpose embedding framework for protein understanding.

bioinformatics↗

bioRxiv2025

A flaw in using pre-trained pLLMs in protein-protein interaction inference models

With the growing pervasiveness of pre-trained protein large language models (pLLMs), pLLM-based methods are increasingly being put forward for the protein-protein interaction (PPI) inference task. Here, we identify and confirm that existing pre-trained pLLMs are a source of data leakage for the downstream PPI task. We characterize the extent of the data leakage problem by training and comparing small and efficient pLLMs on a dataset that controls for data leakage ("strict") with one that does not ("non-strict"). While data leakage from pre-trained pLLMs cause measurable inflation of testing scores, we find that this does not necessarily extend to other, non-paired biological tasks such as protein keyword annotation. Further, we find no connection between the context-lengths of pLLMs and the performance of pLLM-based PPI inference methods on proteins with sequence lengths that surpass it. Furthermore, we show that pLLM-based and non-pLLM-based models fail to generalize in tasks such as prediction of the human-SARS-CoV-2 PPIs or the effect of point mutations on binding-affinities. This study demonstrates the importance of extending existing protocols for the evaluation of pLLM-based models applied to paired biological datasets and identifies areas of weakness of current pLLM models.

bioinformatics↗

bioRxiv2025

Refining sequence-to-expression modelling with chromatin accessibility

MotivationSequence-to-expression models typically do not consider chromatin accessibility, a major factor limiting gene regulation. We hypothesized that supplying accessibility as an input feature would allow a sequenceto-expression model to focus on important open regions of the genome. ResultsWe found that the performance of such an augmented model was significantly better than that of sequence-only or accessibility-only models with similar architectures. Specifically, its ability to predict the expression of highly variable genes and gene expression in other cell types improved, and higher attribution scores in the input DNA sequences of the augmented model conformed to accessibility, enabling the learning of cell type-specific sequence patterns. Additionally, we show that fine-tuning a pre-trained sequence-only model with both sequence and accessibility can boost performance further and highlight the importance of sequencing depth in sequence-toexpression prediction. Availability and ImplementationSource code is available on GitHub at https://github.com/lapohosorsolya/accessible_seq2exp.

bioinformatics↗

bioRxiv2024

A long context RNA foundation model for predicting transcriptome architecture

Linking DNA sequence to genomic function remains one of the grand challenges in genetics and genomics. Here, we present a large-scale compendium of single-molecule transcriptome sequencing of diverse cancer cell lines, revealing their isoform diversity and specificity. We used this compendium to build Mach-1, an RNA foundation model that learns how the nucleotide sequence of unspliced pre-mRNA dictates transcriptome architecture--the relative abundances and molecular structures of mRNA isoforms. By using the Striped-Hyena architecture, Mach-1 handles extremely long sequence inputs at nucleotide resolution (64 kilobase pairs), allowing for quantitative, zero-shot prediction of all aspects of transcriptome architecture, spanning isoform abundance, structure, and variant-induced splicing changes. To test both the interpretive and generative capabilities of Mach-1, we experimentally validated its learned regulatory grammar and predictions through perturbation of RNA-binding proteins nominated by Mach-1 to impact targeted splicing, precise CRISPR editing of variants of uncertain significance that the model predicted to alter splicing, and de novo transcript synthesis and expression in human cells. Together, this release establishes a new foundation for sequence-to-transcript modeling. Mach-1s representations can be extended and fine-tuned across a spectrum of biological contexts, from variant interpretation to RNA engineering.

bioinformatics↗

bioRxiv2024

INTREPPPID - An Orthologue-Informed Quintuplet Network for Cross-Species Prediction of Protein-Protein Interaction

An overwhelming majority of protein-protein interaction (PPI) studies are conducted in a select few model organisms largely due to constraints in time and cost of the associated "wet lab" experiments. In silico PPI inference methods are ideal tools to overcome these limitations, but often struggle with cross-species predictions. We present INTREPPPID, a method which incorporates orthology data using a new "quintuplet" neural network, which is constructed with five parallel encoders with shared parameters. INTREPPPID incorporates both a PPI classification task and an orthologous locality task. The latter learns embeddings of orthologues that have small Euclidean distances between them and large distances between embeddings of all other proteins. INTREPPPID outperforms all other leading PPI inference methods tested on both the intra-species and cross-species tasks using strict evaluation datasets. We show that INTREPPPIDs orthologous locality loss increases performance because of the biological relevance of the orthologue data, and not due to some other specious aspect of the architecture. Finally, we introduce PPI.bio and PPI Origami, a web server interface for INTREPPPID and a software tool for creating strict evaluation datasets, respectively. Together, these two initiatives aim to make both the use and development of PPI inference tools more accessible to the community. GRAPHICAL ABSTRACT O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=75 SRC="FIGDIR/small/580150v1_ufig1.gif" ALT="Figure 1"> View larger version (19K): org.highwire.dtl.DTLVardef@19edfd6org.highwire.dtl.DTLVardef@17997f4org.highwire.dtl.DTLVardef@1e74524org.highwire.dtl.DTLVardef@6c52f3_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2023

GRouNdGAN: GRN-guided simulation of single-cell RNA-seq data using causal generative adversarial networks

We introduce GRouNdGAN, a gene regulatory network (GRN)-guided causal implicit generative model for simulating single-cell RNA-seq data, in-silico perturbation experiments, and benchmarking GRN inference methods. Through the imposition of a user-defined GRN in its architecture, GRouNdGAN simulates steady-state and transient-state single-cell datasets where genes are causally expressed under the control of their regulating transcription factors (TFs). Training on three experimental datasets, we show that our model captures non-linear TF-gene dependences and preserves gene identities, cell trajectories, pseudo-time ordering, and technical and biological noise, with no user manipulation and only implicit parameterization. Despite imposing rigid causality constraints, it outperforms state-of-the-art simulators in generating realistic cells. GRouNdGAN learns meaningful causal regulatory dynamics, allowing sampling from both observational and interventional distributions. This enables it to synthesize cells under conditions that do not occur in the dataset at inference time, allowing to perform in-silico TF knockout experiments. Our results show that in-silico knockout of cell type-specific TFs significantly reduces cells of that type being generated. Interactions imposed through the GRN are emphasized in the simulated datasets, resulting in GRN inference algorithms assigning them much higher scores than interactions not imposed but of equal importance in the experimental training dataset. Benchmarking various GRN inference algorithms reveals that GRouNdGAN effectively bridges the existing gap between simulated and biological data benchmarks of GRN inference algorithms, providing gold standard ground truth GRNs and realistic cells corresponding to the biological system of interest. Our results show that GRouNdGAN is a stable, realistic, and effective simulator with various applications in single-cell RNA-seq analysis.

bioinformatics↗

bioRxiv2022

Interpretable deep learning architectures for improving drug response prediction: myth or reality?

Motivation: Recent advances in deep learning model development have enabled more accurate prediction of drug response in cancer. However, the black-box nature of these models still remains a hurdle in their adoption for precision cancer medicine. Recent efforts have focused on making these models interpretable by incorporating signaling pathway information in model architecture. While these models improve interpretability, it is unclear whether this higher interpretability comes at the cost of less accurate predictions, or a prediction improvement can also be obtained. Results: In this study, we comprehensively and systematically assessed four state-of-the-art interpretable models developed for drug response prediction to answer this question using three pathway collections. Our results showed that models that explicitly incorporate pathway information in the form of a latent layer perform worse compared to models that incorporate this information implicitly. Moreover, in most evaluation setups the best performance is achieved using a simple black-box model. In addition, replacing the signaling pathways with randomly generated pathways shows a comparable performance for the majority of these interpretable models. Our results suggest that new interpretable models are necessary to improve the drug response prediction performance. In addition, the current study provides different baseline models and evaluation setups necessary for such new models to demonstrate their superior prediction performance. Availability and Implementation: Implementation of all methods are provided in https://github.com/Emad-COMBINE-lab/InterpretableAI_for_DRP. Generated uniform datasets are in https://zenodo.org/record/7101665#.YzS79HbMKUk. Contact: amin.emad@mcgill.ca Supplementary Information: Online-only supplementary data is available at the journals website.

bioinformatics↗

bioRxiv2022

MARSY: A multitask deep learning framework for prediction of drug combination synergy scores

MotivationCombination therapies have emerged as a treatment strategy for cancers to reduce the probability of drug resistance and to improve outcome. Large databases curating the results of many drug screening studies on preclinical cancer cell lines have been developed, capturing the synergistic and antagonistic effects of combination of drugs in different cell lines. However, due to the high cost of drug screening experiments and the sheer size of possible drug combinations, these databases are quite sparse. This necessitates the development of transductive computational models to accurately impute these missing values. ResultsHere, we developed MARSY, a deep learning multi-task model that incorporates information on gene expression profile of cancer cell lines, as well as the differential expression signature induced by each drug to predict drug-pair synergy scores. By utilizing two encoders to capture the interplay between the drug-pairs, as well as the drug-pairs and cell lines, and by adding auxiliary tasks in the predictor, MARSY learns latent embeddings that improve the prediction performance compared to state-of-the-art and traditional machine learning models. Using MARSY, we then predicted the synergy scores of 133,722 new drug-pair cell line combinations, which we have made available to the community as part of this study. Moreover, we validated various insights obtained from these novel predictions using independent studies, confirming the ability of MARSY in making accurate novel predictions. Availability and ImplementationAn implementation of the algorithms in Python and cleaned input datasets are provided in https://github.com/Emad-COMBINE-lab/MARSY. Contactamin.emad@mcgill.ca Supplementary InformationOnline-only supplementary data is available at the journals website.

bioinformatics↗

bioRxiv2021

RAPPPID: Towards Generalisable Protein Interaction Prediction with AWD-LSTM Twin Networks

MotivationComputational methods for the prediction of protein-protein interactions, while important tools for researchers, are plagued by challenges in generalising to unseen proteins. Datasets used for modelling protein-protein predictions are particularly predisposed to information leakage and sampling biases. ResultsIn this study, we introduce RAPPPID, a method for the Regularised Automatic Prediction of Protein-Protein Interactions using Deep Learning. RAPPPID is a twin AWD-LSTM network which employs multiple regularisation methods during training time to learn generalised weights. Testing on stringent interaction datasets composed of proteins not seen during training, RAPPPID outperforms state-of-the-art methods. Further experiments show that RAPPPIDs performance holds regardless of the particular proteins in the testing set and its performance is higher for biologically supported edges. This study serves to demonstrate that appropriate regularisation is an important component of overcoming the challenges of creating models for protein-protein interaction prediction that generalise to unseen proteins. Additionally, as part of this study, we provide datasets corresponding to several data splits of various strictness, in order to facilitate assessment of PPI reconstruction methods by others in the future. Availability and Implementation: Code and datasets are freely available at https://github.com/jszym/rapppid. Contactamin.emad@mcgill.ca Supplementary InformationOnline-only supplementary data is available at the journals website.

systems biology↗

bioRxiv2021

Looking at the BiG picture: Incorporating bipartite graphs in drug response prediction

MotivationThe increasing number of publicly available databases containing drugs chemical structures, their response in cell lines, and molecular profiles of the cell lines has garnered attention to the problem of drug response prediction. However, many existing methods do not fully leverage the information that is shared among cell lines and drugs with similar structure. As such, drug similarities in terms of cell line responses and chemical structures could prove to be useful in forming drug representations to improve drug response prediction accuracy. ResultsWe present two deep learning approaches, BiG-DRP and BiG-DRP+, for drug response prediction. Our models take advantage of the drugs chemical structure and the underlying relationships of drugs and cell lines through a bipartite graph and a heterogenous graph convolutional network that incorporate sensitive and resistant cell line information in forming drug representations. Evaluation of our methods and other state-of-the-art models in different scenarios shows that incorporating this bipartite graph significantly improves the prediction performance. Additionally, genes that contribute significantly to the performance of our models also point to important biological processes and signaling pathways. Analysis of predicted drug response of patients tumors using our model revealed important associations between mutations and drug sensitivity, illustrating the utility of our model in pharmacogenomics studies. Availability and ImplementationAn implementation of the algorithms in Python is provided in github.com/ddhostallero/BiG-DRP. Contactamin.emad@mcgill.ca Supplementary InformationOnline-only supplementary data is available at the journals website.

bioinformatics↗

bioRxiv2021

A Deep Learning Framework for Prediction of Clinical Drug Response of Cancer Patients and Identification of Drug Sensitivity Biomarkers using Preclinical Samples

BackgroundPrediction of the response of cancer patients to different treatments and identification of biomarkers of drug sensitivity are two major goals of individualized medicine. In this study, we developed a deep learning framework called TINDL, completely trained on preclinical cancer cell lines, to predict the response of cancer patients to different treatments. TINDL utilizes a tissue-informed normalization to account for the tissue and cancer type of the tumours and to reduce the statistical discrepancies between cell lines and patient tumours. In addition, this model identifies a small set of genes whose mRNA expression are predictive of drug response in the trained model, enabling identification of biomarkers of drug sensitivity. ResultsUsing data from two large databases of cancer cell lines and cancer tumours, we showed that this model can distinguish between sensitive and resistant tumours for 10 (out of 14) drugs, outperforming various other machine learning models. In addition, our siRNA knockdown experiments on 10 genes identified by this model for one of the drugs (tamoxifen) confirmed that all of these genes significantly influence the drug sensitivity of the MCF7 cell line to this drug. In addition, genes implicated for multiple drugs pointed to shared mechanism of action among drugs and suggested several important signaling pathways. ConclusionsIn summary, this study provides a powerful deep learning framework for prediction of drug response and for identification of biomarkers of drug sensitivity in cancer.

bioinformatics↗

bioRxiv2020

Identification of COVID-19-relevant transcriptional regulatory networks and associated kinases as potential therapeutic targets

Identification of transcriptional regulatory mechanisms and signaling networks involved in the response of host to infection by SARS-CoV-2 is a powerful approach that provides a systems biology view of gene expression programs involved in COVID-19 and may enable identification of novel therapeutic targets and strategies to mitigate the impact of this disease. In this study, we combined a series of recently developed computational tools to identify transcriptional regulatory networks involved in the response of epithelial cells to infection by SARS-CoV-2, and particularly regulatory mechanisms that are specific to this virus. In addition, using network-guided analyses, we identified signaling pathways that are associated with these networks and kinases that may regulate them. The results identified classical antiviral response pathways including Interferon response factors (IRFs), interferons (IFNs), and JAK-STAT signaling as key elements upregulated by SARS-CoV-2 in comparison to mock-treated cells. In addition, comparing SARS-Cov-2 infection of airway epithelial cells to other respiratory viruses identified pathways associated with regulation of inflammation (MAPK14) and immunity (BTK, MBX) that may contribute to exacerbate organ damage linked with complications of COVID-19. The regulatory networks identified herein reflect a combination of experimentally validated hits and novel pathways supporting the computational pipeline to quickly narrow down promising avenue of investigations when facing an emerging and novel disease such as COVID-19.

systems biology↗

bioRxiv2019

Tissue-guided LASSO for prediction of clinical drug response using preclinical samples

Prediction of clinical drug response (CDR) of cancer patients, based on their clinical and molecular profiles obtained prior to administration of the drug, can play a significant role in individualized medicine. Machine learning models have the potential to address this issue, but training them requires data from a large number of patients treated with each drug, limiting their feasibility. While large databases of drug response and molecular profiles of preclinical in-vitro cancer cell lines (CCLs) exist for many drugs, it is unclear whether preclinical samples can be used to predict CDR of real patients.\n\nWe designed a systematic approach to evaluate how well different algorithms, trained on gene expression and drug response of CCLs, can predict CDR of patients. Using data from two large databases, we evaluated various linear and non-linear algorithms, some of which utilized information on gene interactions. Then, we developed a new algorithm called TG-LASSO that explicitly integrates information on samples tissue of origin with gene expression profiles to improve prediction performance. Our results showed that regularized regression methods provide significantly accurate prediction. However, including the network information or common methods of including information on the tissue of origin did not improve the results. On the other hand, TG-LASSO improved the predictions and distinguished resistant and sensitive patients for 7 out of 13 drugs. Additionally, TG-LASSO identified genes associated with the drug response, including known targets and pathways involved in the drugs mechanism of action. Moreover, genes identified by TG-LASSO for multiple drugs in a tissue were associated with patient survival. In summary, our analysis suggests that preclinical samples can be used to predict CDR of patients and identify biomarkers of drug sensitivity and survival.\n\nAUTHOR SUMMARYCancer is among the leading causes of death globally and perdition of the drug response of patients to different treatments based on their clinical and molecular profiles can enable individualized cancer medicine. Machine learning algorithms have the potential to play a significant role in this task; but, these algorithms are designed based the premise that a large number of labeled training samples are available, and these samples are accurate representation of the profiles of real tumors. However, due to ethical and technical reasons, it is not possible to screen humans for many drugs, significantly limiting the size of training data. To overcome this data scarcity problem, machine learning models can be trained using large databases of preclinical samples (e.g. cancer cell line cultures). However, due to the major differences between preclinical samples and real tumors, it is unclear how accurately such preclinical-to-clinical computational models can predict the clinical drug response of cancer patients.\n\nHere, first we systematically evaluate a variety of different linear and nonlinear machine learning algorithms for this particular task using two large databases of preclinical (GDSC) and tumor samples (TCGA). Then, we present a novel method called TG-LASSO that utilizes a new approach for explicitly incorporating the tissue of origin of samples in the prediction task. Our results show that TG-LASSO outperforms all other algorithms and can accurately distinguish resistant and sensitive patients for the majority of the tested drugs. Follow-up analysis reveal that this method can also identify biomarkers of drug sensitivity in each cancer type.

bioinformatics↗

bioRxiv2019

Knowledge-guided analysis of ‘omics’ data using the KnowEnG cloud platform

We present KnowEnG, a free-to-use computational system for analysis of genomics data sets, designed to accelerate biomedical discovery. It includes tools for popular bioinformatics tasks such as gene prioritization, sample clustering, gene set analysis and expression signature analysis. The system offers knowledge-guided data-mining and machine learning algorithms, where user-provided data are analyzed in light of prior information about genes, aggregated from numerous knowledge-bases and encoded in a massive Knowledge Network. KnowEnG adheres to FAIR principles: its tools are easily portable to diverse computing environments, run on the cloud for scalable and cost-effective execution of compute-intensive and data-intensive algorithms, and are interoperable with other computing platforms. They are made available through multiple access modes including a web-portal, and include specialized visualization modules. We present use cases and re-analysis of published cancer data sets using KnowEnG tools and demonstrate its potential value in democratization of advanced tools for the modern genomics era.

cancer biology↗