arXiv subjects

Loza F. Tadesse

Publications and source records attributed to Loza F. Tadesse.

10 recordsLinked to original sources

arXiv2026

Sharpness-Aware Minimization (SAM) Improves Classification Accuracy of Bacterial Raman Spectral Data Enabling Portable Diagnostics

Antimicrobial resistance is expected to claim 10 million lives per year by 2050, and resource-limited regions are most affected. Raman spectroscopy is a novel pathogen diagnostic approach promising rapid and portable antibiotic resistance testing within a few hours, compared to days when using gold standard methods. However, current algorithms for Raman spectra analysis 1) are unable to generalize well on limited datasets across diverse patient populations and 2) require increased complexity due to the necessity of non-trivial pre-processing steps, such as feature extraction, which are essential to mitigate the low-quality nature of Raman spectral data. In this work, we address these limitations using Sharpness-Aware Minimization (SAM) to enhance model generalization across a diverse array of hyperparameters in clinical bacterial isolate classification tasks. We demonstrate that SAM achieves accuracy improvements of up to 10.5% on a single split, and an increase in average accuracy of 2.7% across all splits in spectral classification tasks over the traditional optimizer, Adam. These results display the capability of SAM to advance the clinical application of AI-powered Raman spectroscopy tools.

cs.LG↗

arXiv2026

Pic2Spec: Generative Modeling Reconstructs Single Cell Raman Fingerprints from Brightfield Images

Single-cell molecular characterization remains a bottleneck in scalable biological analysis because of labeling requirements, limited multiplexing, and reagents that perturb physiology. Raman spectroscopy addresses these limits by providing chemically specific, label-free vibrational fingerprints, but long acquisition times and specialized instruments restrict high-throughput use. Here, we overcome this barrier by showing that spectral fingerprints can be reconstructed from brightfield microscopy using generative modeling. We introduce Pic2Spec, a framework that learns a shared latent biochemical representation linking image morphology to vibrational spectral structure, enabling virtual Raman spectroscopy without hardware. We validate Pic2Spec across mammalian and bacterial cells, generating high-fidelity spectra that reproduce measured Raman fingerprints with 98% cosine similarity and Pearson correlations of ~95%, while preserving biochemical peaks and population distributions. Beyond spectral similarity, Pic2Spec provides molecular-level resolution in bacterial systems: generated spectra discriminate mutation-driven transgenic states and predict GFP expression with accuracy approaching true Raman measurements, outperforming conventional image analysis by 20%. These findings establish Pic2Spec as a first demonstration of chemically informative virtual molecular fingerprinting from brightfield images, complementing slow, hardware-intensive spectroscopy with computational inference. By redefining microscopy as an inference-enabled molecular profiling platform, Pic2Spec democratizes label-free biochemical phenotyping and overcomes the hardware and time constraints that have confined spectroscopy to specialized laboratories. This enables high-throughput molecular analysis for clinical diagnostics, screening, and monitoring at the scale and accessibility of standard microscopy.

physics.optics↗

arXiv2026

Deep Speckle Holography Redefines Label-free Nanoparticle Phenotyping

Nanoparticle metrology has long been constrained by the assumption that, in mixed and unprocessed fluids, particle size, morphology, composition, and species-specific abundance cannot be resolved simultaneously from a single label-free measurement. Here, we revisit this long-standing limitation by showing that complex forward speckle-holographic fields define an information-rich optical space for multidimensional particle signatures. We report deep speckle holography, a physics-informed generative framework that profiles particle identity, size, morphology, and species-resolved abundance from a single non-contact optical measurement. Across purified suspensions, mixed particle populations, environmental waters, human urine, and other unprocessed native fluids, the method enables direct nanoparticle inference without purification, labeling, or destructive preprocessing, delivering concurrent multidimensional readouts in 0.9 s over a dynamic range spanning 10 orders of magnitude. Deep speckle holography establishes a route toward direct label-free nanoparticle phenotyping in real-world fluids, moving nanoscale measurement beyond isolated-particle characterization toward multidimensional inference in complex mixtures, and expanding the scope of questions nanoscale measurement can address, from real-time tracking of nanoparticle transformations in living and environmental systems to non-invasive quality control of nanomedicine formulations, and beyond.

eess.IV↗

arXiv2025

Towards Breath Based Diagnostics via Water-mediated Capture of Synthetic Breath Biomarkers in SERS-active Plasmonic Nanogaps

Volatile organic compounds (VOCs) are valuable health indicators, with synthetic breath biomarkers offering rapid and disease specific diagnostics. However, their <100 ppb level exhalation requires mass spectrometry, limiting clinical integration. Surface-enhanced Raman spectroscopy (SERS) offers a portable, cost-effective alternative. Yet, detecting synthetic breath biomarkers, with inherently low Raman cross-sections, at <100 ppb remains challenging. We demonstrate SERS detection down to clinically relevant 10 ppb via water-mediated trapping in hydroxylated nanoporous silica-coated plasmonic nanogaps, using pentafluoropropylamine (PFP) as a representative synthetic breath biomarker. Uniform nanogaps, with >1000 times electric field enhancement, were generated between a gold film and gold-silica core-shell nanoparticle assemblies using electric field-driven evaporation. Oxygen plasma treatment hydroxylated the silica, enabling water-mediated hydrogen bonding that strengthened PFP adsorption, confirmed by density functional theory. This mechanism improved SERS sensitivity by 10000 fold, enabling ppb level PFP detection in mouse bronchial fluid and establishing a VOC capturing SERS platform for breath-based diagnostics.

physics.app-ph↗

arXiv2025

Nano-engineered surface enhanced Raman spectroscopy substrates for probing tissue-material interactions

Innovation in biomaterials has brought both breakthroughs and new challenges in medicine, as implant materials have become increasingly multifunctional and complex. One of the greatest issues is the difficulty in assessing the temporal and multidimensional dynamics of tissue-implant interactions. Implant biology remains hard to decipher without a noninvasive and multiplexed technique that can accurately monitor real-time biological processes. To address this, we developed a multifunctional, self-sensing implant material composed of gold nano-columns patterned on a titanium surface (AuNC-Ti). This material acts as a nanoengineered surface-enhanced Raman spectroscopy (SERS) substrate that amplifies biological Raman signals at the tissue-implant interface, providing the ability to sense tissue-material interactions in a multiplexed and nondestructive manner. AuNC-Ti SERS substrates were fabricated using oblique angle deposition (OAD) and characterized using scanning electron microscopy (SEM) to show uniform formation of AuNCs ($360 \pm 40$ nm in length and $50 \pm 16$ nm in width). X-ray photoelectron spectroscopy (XPS), X-ray diffraction (XRD), and contact angle measurements demonstrated biocompatible surface chemistry with ideal wettability. Biocompatibility was further demonstrated via in vitro cytotoxicity assays on human aortic endothelial cells (HAECs) cultured on AuNC-Ti surfaces. The median SERS enhancement factor (EF) was calculated to be $1.8 \times 10^5$, and spatial identification of reporter molecules and porcine tissue components on AuNC-Ti surfaces was demonstrated using confocal Raman imaging and multivariate analysis. Our approach utilizes unlabeled SERS and machine learning, promising multiplexed characterization of tissue-material interactions and subsequently enabling tissue state determination and non-invasive monitoring of implant-tissue interaction.

cond-mat.mtrl-sci↗

arXiv2025

Interplay of Electrostatic Interaction and Steric Repulsion between Bacteria and Gold Surface Influences Raman Enhancement

Plasmonic nanostructures have wide applications in photonics including pathogen detection and diagnosis via Surface-Enhanced Raman Spectroscopy (SERS). Despite major role plasmonics play in signal enhancement, electrostatics in SERS is yet to be fully understood and harnessed. Here, we perform a systematic study of electrostatic interactions between 785 nm resonant gold nanorods designed to harbor zeta potentials of +29, +16, 0 and -9 mV spanning positive neutral and negative domains. SERS activity is tested on representative Gram-negative Escherichia coli and Gram-positive Staphylococcus epidermidis bacteria with zeta potentials of -30 and -23 mV respectively in water. Raman spectroscopy and Cryo-Electron microscopy reveal that +29, +16, 0 and -9 mV nanorods give SERS enhancement of 7.2X, 3.6X, 4.2X, 1.3X to Staphylococcus epidermidis and 3.9X, 2.8X, 2.9X, 1.1X to Escherichia coli. Theoretical results show that electrostatics play the major role among all interaction forces in determining cell-nanorod proximity and signal enhancement. We identify steric repulsion due to cell protrusions to be the critical opposing force. Finally, a design principle is proposed to estimate the electrostatic strength in SERS. Our work provides new insights into the principle of bacteria-nanorod interactions, enabling reproducible and precise biomolecular readouts, critical for next-generation point-of-care diagnostics and smart healthcare applications.

q-bio.CB↗

arXiv2024

Universal Spectral Transfer with Physical Prior-Informed Deep Generative Learning

Spectroscopy is a powerful analytical technique for characterizing matter across physical and biological realms1-5. However, its fundamental principle necessitates specialized instrumentation per physical phenomena probed, limiting broad adoption and use in all relevant research. In this study, we introduce SpectroGen, a novel physical prior-informed deep generative model for generating relevant spectral signatures across modalities using experimentally collected spectral input only from a single modality. We achieve this by reimagining the representation of spectral data as mathematical constructs of distributions instead of their traditional physical and molecular state representations. The results from 319 standard mineral samples tested demonstrate generating with 99% correlation and 0.01 root mean square error with superior resolution than experimentally acquired ground truth spectra. We showed transferring capability across Raman, Infrared, and X-ray Diffraction modalities with Gaussian, Lorentzian, and Voigt distribution priors respectively6-10. This approach however is globally generalizable for any spectral input that can be represented by a distribution prior, making it universally applicable. We believe our work revolutionizes the application sphere of spectroscopy, which has traditionally been limited by access to the required sophisticated and often expensive equipment towards accelerating material, pharmaceutical, and biological discoveries.

cs.LG↗

arXiv2024

Rapid, antibiotic incubation-free determination of tuberculosis drug resistance using machine learning and Raman spectroscopy

Tuberculosis (TB) is the world's deadliest infectious disease, with over 1.5 million deaths annually and 10 million new cases reported each year. The causative organism, Mycobacterium tuberculosis (Mtb) can take nearly 40 days to culture, a required step to determine the pathogen's antibiotic susceptibility. Both rapid identification of Mtb and rapid antibiotic susceptibility testing (AST) are essential for effective patient treatment and combating antimicrobial resistance. Here, we demonstrate a rapid, culture-free, and antibiotic incubation-free drug susceptibility test for TB using Raman spectroscopy and machine learning. We collect few-to-single-cell Raman spectra from over 25,000 cells of the MtB complex strain Bacillus Calmette Guerin (BCG) resistant to one of the four mainstay anti-TB drugs, isoniazid, rifampicin, moxifloxacin and amikacin, as well as a pan susceptible wildtype strain. By training a neural network on this data, we classify the antibiotic resistance profile of each strain, both on dried samples and in patient sputum samples. On dried samples, we achieve >98% resistant versus susceptible classification accuracy across all 5 BCG strains. In patient sputum samples, we achieve ~79% average classification accuracy. We develop a feature recognition algorithm in order to verify that our machine learning model is using biologically relevant spectral features to assess the resistance profiles of our mycobacterial strains. Finally, we demonstrate how this approach can be deployed in resource-limited settings by developing a low-cost, portable Raman microscope that costs <$5000. We show how this instrument and our machine learning model enables combined microscopy and spectroscopy for accurate few-to-single-cell drug susceptibility testing of BCG.

physics.bio-ph↗

arXiv2023

More than magnetic isolation: Dynabeads as strong Raman reporters towards simultaneous capture and identification of targets

Dynabeads are superparamagnetic particles used for immunomagnetic purification of cells and biomolecules. Post-capture, however, target identification relies on tedious culturing, fluorescence staining and/or target amplification. Raman spectroscopy presents a rapid detection alternative, but current implementations target cells themselves with weak Raman signals. We present antibody-coated Dynabeads as strong Raman reporter labels whose effect can be considered a Raman parallel of immunofluorescent probes. Recent developments in techniques for separating target-bound Dynabeads from unbound Dynabeads makes such an implementation feasible. We deploy Dynabeads anti-Salmonella to bind and identify Salmonella enterica, a major foodborne pathogen. Dynabeads present signature peaks at 1000 and 1600 1/cm from aliphatic and aromatic C-C stretching of polystyrene, and 1350 1/cm and 1600 1/cm from amide, alpha-helix and beta-sheet of antibody coatings of the Fe2O3 core, confirmed with electron dispersive X-ray (EDX) imaging. Their Raman signature can be measured in dry and liquid samples even at single shot ~30 x 30-micrometer area imaging using 0.5 s, 7 mW laser acquisition with single and clustered beads providing a 44- and 68-fold larger Raman intensity compared to signature from cells. Higher polystyrene and antibody content in clusters yields to the larger signal intensity and conjugation to bacteria strengthens clustering as a bacterium can bind to more than one bead as observed via transmission electron microscopy (TEM). Our findings shed light on the intrinsic Raman reporter nature of Dynabeads, demonstrating their dual function for target isolation and detection without additional sample preparation, staining, or unique plasmonic substrate engineering, advancing their applications in heterogeneous samples like food, water, and blood.

physics.bio-ph↗

arXiv2023

Combining acoustic bioprinting with AI-assisted Raman spectroscopy for high-throughput identification of bacteria in blood

Identifying pathogens in complex samples such as blood, urine, and wastewater is critical to detect infection and inform optimal treatment. Surface-enhanced Raman spectroscopy (SERS) and machine learning (ML) can distinguish among multiple pathogen species, but processing complex fluid samples to sensitively and specifically detect pathogens remains an outstanding challenge. Here, we develop an acoustic bioprinter to digitize samples into millions of droplets, each containing just a few cells, which are identified with SERS and ML. We demonstrate rapid printing of 2 pL droplets from solutions containing S. epidermidis, E. coli, and blood; when mixed with gold nanorods (GNRs), SERS enhancements of up to 1500x are achieved.We then train a ML model and achieve >=99% classification accuracy from cellularly-pure samples, and >=87% accuracy from cellularly-mixed samples. We also obtain >=90% accuracy from droplets with pathogen:blood cell ratios <1. Our combined bioprinting and SERS platform could accelerate rapid, sensitive pathogen detection in clinical, environmental, and industrial settings.

physics.bio-ph↗