Biology subjects

Faraj, A.

Publications and source records attributed to Faraj, A..

6 recordsLinked to original sources

bioRxiv2026

Deep Learning Based Cell Segmentation of 3D Confocal Images of Wood for Enzymatic Hydrolysis Applications

Plant cell walls are an abundant renewable resource for biobased products, but their recalcitrance limits enzymatic hydrolysis efficiency. Cell and tissue morphological parameters provide reliable biomarkers for predicting enzymatic hydrolysis efficiency. Accurate cell segmentation in 3D microscopy images is essential for quantifying these parameters. Although deep learning has achieved high performance in biological image segmentation, confocal microscopy's limited penetration depth leaves elongated wood cells partially imaged, creating open-ended structures that challenge existing segmentation methods. Based on an artificial longitudinal domain restriction, an adapted framework is presented here for the training of a 3D U-net model for the cell segmentation of wood images. Quantitative evaluation on a dedicated benchmark dataset identified a model configuration that reduced segmentation errors and produced more robust predictions during early enzymatic hydrolysis. These results support the use of the framework to quantify morphological parameters relevant to assessing and predicting biomass conversion efficiency.

bioengineering↗

bioRxiv2026

Taming complexity in enzymatic saccharification: A predictive hierarchical modeling framework

Lignocellulosic biomass biotechnological conversion relies on enzymatic hydrolysis of recalcitrant plant cell walls, which limits conversion efficiency and economic viability and renders sugar-release dynamics difficult to predict. Mathematical modeling has therefore emerged as a key approach for elucidating the mechanisms governing enzymatic hydrolysis and predicting its dynamics. Here, a hierarchical adsorption-inhibition framework is developed, beginning with a detailed Dynamic Adsorption-Inhibition Model (DyAIM). This model is then simplified into a Reduced Adsorption-Inhibition Model (ReAIM) by pruning weak adsorption and inhibition interactions. Finally, ReAIM is further simplified into an Effective Activity Model (EAM), in which nonproductive enzyme adsorption onto lignin is represented by a reduction in effective enzymatic activity. Plant cell wall composition is expressed as four structural polymers coupled to six soluble products, with inhibition by mono- and oligosaccharides acting on five functional enzyme pools. Using glucose, xylose and mannose release at two enzyme loadings, the model hierarchy is validated in reproducing saccharification dynamics and in delivering a quantitative product-enzyme inhibition network consistent with literature trends. The model framework was further validated by prediction of saccharification dynamics at an unseen enzyme loading, demonstrating robust performance beyond the calibration conditions. Sensitivity analysis further supported the progressive simplifications adopted in ReAIM and EAM. Maintaining predictive performance across increasing levels of simplification indicates that the hierarchy effectively distinguishes essential mechanisms from dispensable complexity, enabling rational model selection.

biochemistry↗

bioRxiv2025

Plant Cell Wall Enzymatic Hydrolysis: Predicting Yield Dynamics from Autofluorescence and Morphological Temporal Changes

Enzymatic hydrolysis of plant cell walls into fermentable sugars is a critical step in biotechnological conversion, yet efficiency is limited by cell wall recalcitrance. Predicting conversion yields of cell wall-derived sugars during hydrolysis is challenging due to the complex underlying mechanisms and the labor-intensive nature of conventional assays. This study introduces an innovative pipeline that accurately quantifies cell wall autofluorescence intensity and morphological descriptors during enzymatic hydrolysis. The pipeline incorporates a novel adaptive drift compensation strategy which dynamically adjusts to the progression and extent of deconstruction ensuring robust analysis. Applied to time-lapse images of spruce wood enzymatic deconstruction, the pipeline revealed strong negative correlations of conversion yields during hydrolysis with both the dynamics of cell wall autofluorescence intensity and morphological descriptors. Phase-specific analysis uncovered distinct correlation patterns dependent on hydrolysis stage and sugar type. This non-destructive pipeline eliminates the need for extensive sampling and time-consuming chemical assays, establishing plant cell wall autofluorescence and morphological descriptors as accurate predictive real-time biomarkers of dynamics of sugar conversion yields. The findings provide a framework for accelerating the development of optimized biotechnological conversion processes.

biochemistry↗

bioRxiv2025

A high-throughput platform for biophysical antibody developability assessment to enable AI/ML model training

Antibodies must bind their targets with high affinity and specificity to achieve useful therapeutic activity. They must also possess suitable developability properties (e.g., thermostability, solubility, viscosity, polyreactivity) to ensure favorable manufacturing, formulation, and in vivo performance. Both binding and developability properties are inherent to a given antibody amino acid sequence. Identification or selection of antibodies possessing suitable binding characteristics is now routine, and de novo computational design models, trained on extensive complementarity-determining region sequence and structural data, are rapidly improving. Developability properties, however, remain difficult to predict largely due to insufficient training data, with empirical testing being heavily used to avoid challenges in late-stage antibody development. To fill this gap, we built a high-throughput antibody developability assay platform designed to generate the large datasets needed to train improved machine learning (ML) models. We optimized and automated known developability assays [Jain et al., 2017], and developed a robust integrated data analytics pipeline. Here we report data on 246 antibodies--representing 106 approved, 135 clinical-stage, and 5 preregistration/withdrawn molecules--across a panel of 10 developability assays, in a "tidy data" format suitable for AI/ML modeling. We used these data to develop an XGBoost [Chen et al., 2016] ML model that better predicts similarity to approved antibodies compared to conventional use of developability warning thresholds. Additionally, we confirm that preliminary predictive models do improve with more training data. Our high-throughput PROPHET-Ab platform enables data generation at the scale needed to develop improved ML models to predict antibody developability. SignificanceSuccessful antibody drugs exhibit important "developability" properties, beyond tight and specific binding to their target, including high expressibility, high stability and solubility, low aggregation propensity, low viscosity, low polyreactivity, and long in vivo half-life. Collectively, developability properties predict favorable manufacturing, storage, administration, and safety, and deficiencies in these properties increase risk for clinical failure. Despite progress in developing machine learning models to predict structure and binding, antibody developability models lag, largely due to a lack of sufficiently large training datasets. We have built a high-throughput platform, PROPHET-Ab, that enables data generation at the scale needed to train improved AI/ML models to predict antibody developability.

biophysics↗

bioRxiv2024

A Distinct Autofluorescence Distribution Pattern Marks Enzymatic Deconstruction of Plant Cell Wall

Achieving an economically viable transformation of plant cell walls into bioproducts requires a comprehensive understanding of enzymatic deconstruction. Microscale quantitative analysis offers a relevant approach to enhance our understanding of cell wall hydrolysis, but becomes challenging under high deconstruction conditions. This study comprehensively addresses the challenges of quantifying the impact of extensive enzymatic deconstruction on plant cell wall at microscale. Investigation of highly deconstructed spruce wood provided spatial profiles of cell walls during hydrolysis with a remarkable precision. A distinct cell wall autofluorescence distribution pattern marking enzymatic hydrolysis along with an asynchronous impact of hydrolysis on cell wall structure, with cell wall volume reduction preceding cell wall accessible surface area decrease, were revealed. This study provides novel insights into enzymatic deconstruction of cell wall at under-investigated cell scale, and a robust computational pipeline applicable to diverse biomass species and pretreatment types for assessing hydrolysis impact and efficiency.

biochemistry↗

bioRxiv2023

A BCG Skin Challenge Model for Assessing TB Vaccines

Controlled Human infection models (CHIM) are valuable tools for assessing relevant biological activity in vaccine candidates, with the potential to accelerate Tuberculosis vaccine development into the clinic. Tuberculosis infection poses significant constraints on the design of a CHIM using the causative agent Mycobacterium tuberculosis. As a safer alternative, we propose a challenge model using the attenuated vaccine agent Mycobacterium bovis BCG as a surrogate for Mycobacterium tuberculosis, and intradermal (skin) challenge as an alternative to pulmonary infection. We have developed a unique non-invasive imaging system based on fluorescent reporters to quantitatively measure bacterial load over time, thereby determining a relevant biological vaccine effect. We assessed the utility of this model to measure the effectiveness of two TB vaccines: the currently licenced BCG and a novel subunit vaccine candidate. To assess the efficacy of the skin challenge model a pharmacometric model was built describing the decline of fluorescence over time. The results show that vaccination is a statistically significant factor which reduced the fluorescence readout of both fluorophores. The higher decline in vaccinated mice correlated with bacterial burden in the lungs. This supports the fluorescence output from the skin as a reflection of vaccine induced functional pulmonary immune responses. This novel non-invasive approach allows for repeated measurements from the challenge site, providing a dynamic readout of vaccine induced responses over time. This BCG skin challenge model represents an important contribution to the ongoing development of controlled challenge models for Tuberculosis.

microbiology↗