Biology subjects

Sapiro, G.

Publications and source records attributed to Sapiro, G..

11 recordsLinked to original sources

bioRxiv2025

An Evidence-Grounded Research Assistant for Functional Genomics and Drug Target Assessment

The growing availability of biological data resources has transformed research, yet their effective use remains challenging: selecting appropriate sources requires domain knowledge, data are fragmented across databases, and synthesizing results into reliable conclusions is labor-intensive. Although large language models promise to address these barriers, their impact in biomedicine has been limited by unsupported statements, incorrect claims, and lack of provenance. We introduce Alvessa, an evidence-grounded agentic research assistant designed around verifiability. Alvessa integrates entity recognition, orchestration of pre-validated biological tools, and data-constrained answer generation with statement-level verification against retrieved records, explicitly flagging unsupported claims and guiding revision when reliability criteria are not met. We evaluate Alvessa on dbQA from LAB-Bench and GenomeArena, a benchmark of 720 questions spanning gene and variant annotation, pathways, molecular interactions, miRNA targets, drug-target evidence, protein structure, and gene-phenotype associations. Alvessa substantially improves accuracy relative to general-purpose language models and performs comparably to coding-centric agents while producing fully traceable outputs. Using adversarial perturbations, we show that detection of fabricated statements depends critically on access to retrieved evidence. We further demonstrate application to drug discovery, where evidence-grounded synthesis enables identification of candidate targets missed or misattributed by literature-centered reasoning alone. Alvessa and GenomeArena are released to the community to support reproducible, verifiable AI-assisted biological research.

bioinformatics↗

bioRxiv2021

Computational and Image Processing Methods for Analysis and Automation of Anatomical Alignment and Joint Spacing in Reconstructive Surgery

PurposeReconstructive surgeries to treat a number of musculoskeletal conditions, from arthritis to severe trauma, involve implant placement and reconstructive planning components. Anatomically matched 3D printed implants are becoming increasingly patient-specific; however the preoperative planning and design process requires several hours of manual effort from highly trained engineers and clinicians. Our work mitigates this problem by proposing algorithms for the automatic re-alignment of unhealthy anatomies, leading to more efficient, affordable, and scalable treatment solutions. MethodsOur solution combines global alignment techniques such as iterative closest points (ICP) with novel joint space refinement algorithms. The latter is achieved by a low dimensional characterization of the joint space, computed from the distribution of the distance between adjacent points in a joint. ResultsExperimental validation is presented on real clinical data from human subjects. Compared with ground truth healthy anatomies, our algorithms can reduce misalignment errors by 22% in translation and 19% in rotation for the full foot-and-ankle and 37% in translation and 39% in rotation for the hind-foot only, achieving a performance comparable to expert technicians. ConclusionOur methods and histogram-based metric allow for automatic and unsupervised alignment of anatomies, a major step toward a fully automated and data driven re-positioning, designing, and diagnosing tool.

bioengineering↗

bioRxiv2021

ImPartial: Partial Annotations for Cell Instance Segmentation

Segmenting noisy multiplex spatial tissue images constitutes a challenging task, since the characteristics of both the noise and the biology being imaged differs significantly across tissues and modalities; this is compounded by the high monetary and time costs associated with manual annotations. It is therefore imperative to build algorithms that can accurately segment the noisy images based on a small number of annotations. Recently techniques to derive such an algorithm from a few scribbled annotations have been proposed, mostly relying on the refinement and estimation of pseudo-labels. Other techniques leverage the success of self-supervised denoising as a parallel task to potentially improve the segmentation objective when few annotations are available. In this paper, we propose a method that augments the segmentation objective via self-supervised multi-channel quantized imputation, meaning that each class of the segmentation objective can be characterized by a mixture of distributions. This approach leverages the observation that perfect pixel-wise reconstruction or denoising of the image is not needed for accurate segmentation, and introduces a self-supervised classification objective that better aligns with the overall segmentation goal. We demonstrate the superior performance of our approach for a variety of cancer datasets acquired with different highly-multiplexed imaging modalities in real clinical settings. Code for our method along with a benchmarking dataset is available at https://github.com/natalialmg/ImPartial.

bioengineering↗

bioRxiv2020

Deep-learning based fully automatic segmentation of the globus pallidus interna and externa using ultra-high 7 Tesla MRI

Deep brain stimulation (DBS) surgery has been shown to dramatically improve the quality of life for patients with various motor dysfunctions, such as those afflicted with Parkinsons disease (PD), dystonia, and essential tremor (ET), by relieving motor symptoms associated with such pathologies. The success of DBS procedures is directly related to the proper placement of the electrodes, which requires the ability to accurately detect and identify relevant target structures within the subcortical basal ganglia region. In particular, accurate and reliable segmentation of the globus pallidus (GP) interna is of great interest for DBS surgery for PD and dystonia. In this work, we present a deep-learning based neural network, which we term GP-net, for the automatic segmentation of both the external and internal segments of the globus pallidus. High resolution 7 Tesla images from 101 subjects were used in this study; GP-net is trained on a cohort of 58 subjects, containing patients with movement disorders as well as healthy control subjects. GP-net performs 3D inference in a patient-specific manner, alleviating the need for atlas-based segmentation. GP-net was extensively validated, both quantitatively and qualitatively over 43 test subjects including patients with movement disorders and healthy control and is shown to consistently produce improved segmentation results compared with state-of-the-art atlas-based segmentations. We also demonstrate a post-operative lead location assessment with respect to a segmented globus pallidus obtained by GP-net.

neuroscience↗

bioRxiv2019

Measuring Robustness of Brain Networks in Autism Spectrum Disorder with Ricci Curvature

Ricci curvature is a method for measuring the robustness of networks. In this work, we use Ricci curvature to measure robustness of brain networks affected by autism spectrum disorder (ASD). Subjects with ASD are given a stem cell infusion and are imaged with diffusion MRI before and after the infusion. By using Ricci curvature to measure changes in robustness, we quantify both local and global changes in the brain networks correlated with the infusion. Our results find changes in regions associated with ASD that were not detected via traditional brain network analysis.

neuroscience↗

bioRxiv2019

Multifaceted Changes in Synaptic Composition and Astrocytic Involvement in a Mouse Model of Fragile X Syndrome

Fragile X Syndrome (FXS), a common inheritable form of intellectual disability, is known to alter neocortical circuits. However, its impact on the diverse synapse types comprising these circuits, or on the involvement of astrocytes, is not well known. We used immunofluorescent array tomography to quantify different synaptic populations and their association with astrocytes in layers 1 through 4 of the adult somatosensory cortex of a FXS mouse model, the FMR1 knockout mouse. The collected multi-channel data contained approximately 1.6 million synapses which were analyzed using a probabilistic synapse detector. Our study reveals complex, synapse-type and layer specific changes in the neocortical circuitry of FMR1 knockout mice. In layers 1 and 2/3, there is a significant decrease in the density of excitatory glutamatergic synapses, both VGluT1 and VGluT2 type, and their association with astrocytes, while the changes in inhibitory GABAergic synapses are less pronounced. Meanwhile in layer 4, there is a significant increase in the density of small VGluT1 synapses, with no changes in the astrocytic association of synapses. The ability to dissect the circuit deficits by synapse type and astrocytic involvement, will be crucial for understanding how these changes affect circuit function, and ultimately define targets for therapeutic intervention.

neuroscience↗

bioRxiv2018

Development of algorithms for automated detection of cervical pre-cancers with a low-cost, point-of-care, Pocket Colposcope

GoalIn this work, we propose methods for (1) automatic feature extraction and classification for acetic acid and Lugols iodine cervigrams and (2) methods for combining features/diagnosis of different contrasts in cervigrams for improved performance.\n\nMethodsWe developed algorithms to pre-process pathology-labeled cervigrams and to extract simple but powerful color and textural-based features. The features were used to train a support vector machine model to classify cervigrams based on corresponding pathology for visual inspection with acetic acid, visual inspection with Lugols iodine, and a combination of the two contrasts.\n\nResultsThe proposed framework achieved a sensitivity, specificity, and accuracy of 81.3%, 78.6%, and 80.0%, respectively when used to distinguish cervical intraepithelial neoplasia (CIN+) relative to normal and benign tissues. This is superior to the average values achieved by three expert physicians on the same data set for discriminating normal/benign cases from CIN+ (77% sensitivity, 51% specificity, 63% accuracy).\n\nConclusionThe results suggest that utilizing simple color- and textural-based features from visual inspection with acetic acid and visual inspection with Lugols iodine images may provide unbiased automation of cervigrams.\n\nSignificanceThis would enable automated, expert-level diagnosis of cervical pre-cancer at the point-of-care.

bioinformatics↗

bioRxiv2018

Automatic Localization of the Subthalamic Nucleus on Patient-Specific Clinical MRI by Incorporating 7T MRI and Machine Learning: Application in Deep Brain Stimulation

Deep Brain Stimulation (DBS) of the subthalamic nucleus (STN) has shown clinical potential for relieving the motor symptoms of advanced Parkinsons disease. While accurate localization of the STN is critical for consistent across-patients effective DBS, clear visualization of the STN under standard clinical MR protocols is still challenging. Therefore, intraoperative microelectrode recordings (MER) are incorporated to accurately localize the STN. However, MER require significant neurosurgical expertise and lengthen the surgery time. Recent advances in 7T MR technology facilitate the ability to clearly visualize the STN. The vast majority of centers, however, still do not have 7T MRI systems, and fewer have the ability to collect and analyze the data. This work introduces an automatic STN localization framework based on standard clinical MRIs without additional cost in the current DBS planning protocol. Our approach benefits from a large database of 7T MRI and its clinical MRI pairs. We first model in the 7T database, using efficient machine learning algorithms, the spatial and geometric dependency between the STN and its adjacent structures (predictors). Given a standard clinical MRI, our method automatically computes the predictors and uses the learned information to predict the patient-specific STN. We validate our proposed method on clinical T2W MRI of 80 subjects, comparing with experts-segmented STNs from the corresponding 7T MRI pairs. The experimental results show that our framework provides more accurate and robust patient-specific STN localization than using state-of-the-art atlases. We also demonstrate the clinical feasibility of the proposed technique assessing the post-operative electrode active contact locations.

neuroscience↗

bioRxiv2018

Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentations

ObjectiveOverlapping measures are often utilized to quantify the similarity between two binary regions. However, modern segmentation algorithms output a probability or confidence map with continuous values in the zero-to-one interval. Moreover, these binary overlapping measures are biased to structures size. Addressing these challenges is the objective of this work.\n\nMethodsWe extend the definition of the classical Dice coefficient (DC) overlap to facilitate the direct comparison of a ground truth binary image with a probabilistic map. We call the extended method continuous Dice coefficient (cDC) and show that 1) cDC [≤]1 and cDC = 1 if-and-only-if the structures overlap is complete, and; 2) cDC is monotonically decreasing with the amount of overlap. We compare the classical DC and the cDC in a simulation of partial volume effects that incorporates segmentations of common targets for deep-brain-stimulation. Lastly, we investigate the cDC for an automatic segmentation of the subthalamic-nucleus.\n\nResultsPartial volume effect simulation on thalamus (large structure) resulted with DC and cDC averages (SD) of 0.98 (0.006) and 0.99 (0.001), respectively. For subthalamic-nucleus (small structure) DC and cDC were 0.86 (0.025) and 0.97 (0.006), respectively. The DC and cDC for automatic STN segmentation were 0.66 and 0.80, respectively.\n\nConclusionThe cDC is well defined for probabilistic segmentation, less biased to structures size and more robust to partial volume effects in comparison to DC. Significance: The proposed method facilitates a better evaluation of segmentation algorithms. As a better measurement tool, it opens the door for the development of better segmentation methods.

bioengineering↗

bioRxiv2018

Active Learning of Cortical Connectivity from Two-Photon Imaging Data

Understanding how groups of neurons interact within a network is a fundamental question in system neuroscience. Instead of passively observing the ongoing activity of a network, we can typically perturb its activity, either by external sensory stimulation or directly via techniques such as two-photon optogenetics. A natural question is how to use such perturbations to identify the connectivity of the network efficiently. Here we introduce a method to infer sparse connectivity graphs from in-vivo, two-photon imaging of population activity in response to external stimuli. A novel aspect of the work is the introduction of a recommended distribution, incrementally learned from the data, to optimally refine the inferred network.. Unlike existing system identification techniques, this \"active learning\" method automatically focuses its attention on key undiscovered areas of the network, instead of targeting global uncertainty indicators like parameter variance. We show how active learning leads to faster inference while, at the same time, provides confidence intervals for the network parameters. We present simulations on artificial small-world networks to validate the methods and apply the method to real data. Analysis of frequency of motifs recovered show that cortical networks are consistent with a small-world topology model.

neuroscience↗

bioRxiv2018

Automated Antibody Characterization and Screening for Array Tomography via Probabilistic Synapse Detection

Application-specific validation of antibodies is a critical prerequisite for their successful use. Here we introduce an automated framework for characterization and screening of antibodies against synaptic molecules for high-resolution immunofluorescence array tomography (AT). The proposed Synaptic Antibody Screening Tool (SACT), is designed to provide an automatic, robust, flexible, and efficient tool for antibody characterization at scale. By allowing the user to define the molecular composition and size of synapses expected to contain the antigen, the method detects and characterizes puncta and synapses, and outputs automatically computed characteristics such as synapse density and target specificity ratio, which reflect the sensitivity and specificity of immunolabeling with a given antibody. These measurements provide an objective way to characterize and compare the performance of different antibodies against the same target, and can be used to objectively select the antibodies best suited for AT and potentially for other immunolabeling applications.

neuroscience↗