Biology subjects

Buendia, A.

Publications and source records attributed to Buendia, A..

6 recordsLinked to original sources

bioRxiv2026

BenchRep-T: A Systematic Evaluation of T-Cell Repertoire-Based Disease Diagnostics

Adaptive immune receptor repertoire sequencing data has emerged as a promising potential modality for disease diagnosis, relying on computational methods to analyze T-cell receptor (TCR) sequences from an individuals blood sample. Published methods rely on different cohorts, data preprocessing pipelines, and evaluation metrics, making direct comparison across methods challenging. We present BenchRep-T, a unified benchmark that standardizes multiple publicly available TCR repertoire datasets and evaluates nine computational approaches, spanning statistical enrichment of shared sequences, feature-engineered ensembles, deep learning, and sequence clustering. BenchRep-T evaluates methods on four tasks: disease classification across conditions, performance scaling under restricted sequence-sampling depth, recovery of known antigen-specific driver sequences, and evaluation of sensitivity to demographic confounding. Under controlled evaluation, simple baselines prove competitive, with tree-based models trained on V- and J-gene usage and short sequence motifs approaching the classification performance of more complex methods. Our findings underscore the complexity of modeling TCR repertoire data, and show that no single method dominates across all tasks. BenchRep-T provides a framework for rigorous and reproducible evaluation of TCR repertoire classification methods to accelerate the development of immune repertoire-based diagnostics.

immunology↗

bioRxiv2026

Bio-BLIP: A Multimodal Architecture for Transferable Reasoning in Genomic Variant Interpretation

Developing scientific hypotheses in biology requires integrating heterogeneous evidence across DNA sequence, gene context, protein function, and prior literature. Existing multimodal AI systems expose biological evidence to reasoning models through textification or by projecting biological embeddings into fine-tuned language models. However, these models are typically highly optimized the specific set of tasks for which they are fine-tuned. Here we present Bio-BLIP, a multimodal Q-former based architecture which leverages biological embeddings and a LLM to generalize to complex reasoning tasks without task-specific fine-tuning. The key to Bio-BLIP is a new neural network architecture that integrates four data modalities - DNA, genes, proteins, and text - through a master Qformer model, which integrates the modality-specific information into a fixed-length prefix for the LLM backbone. Bio-BLIP is pretrained on the task of human genetic variant annotation and achieves a 29.8% increase in generating accurate variant features over frontier LLMs. We evaluate Bio-BLIP zero-shot on downstream genomic tasks of variant prioritization and target gene prediction. Bio-BLIP outperforms two alignment-free genomic language models on regulatory variant prioritization for Mendelian disease. Across the target gene prediction task, Bio-BLIP improves accuracy over LLMs by leveraging learned genomic variant knowledge in difficult cases. Our model produces rich, transparent reasoning traces. In biological domains characterized by multiple scales of data and varied downstream tasks, Bio-BLIP offers a step toward natively multimodal, generalizable reasoning.

genomics↗

bioRxiv2025

SpatialProp: tissue perturbation modeling with spatially resolved single-cell transcriptomics

Perturbational studies are the gold standard for identifying causal relationships between components of biological systems. Recent technological advances, including Perturb-seq and related assays, have enabled high-throughput screening of genetic perturbation effects on single cells. Several machine learning tools have also been developed to infer the effect of single-cell perturbations. However, both approaches are generally limited to dissociated cells, and the effect of genetic perturbations on neighboring cells within intact tissue has not yet been explored. Here we introduce a computational framework using graph neural networks for predicting the effect of multi-gene, multi-cell type perturbations on cells in whole tissue sections. We leverage the natural heterogeneity in tissue microenvironments across spatially resolved single-cell transcriptomics datasets to train SpatialProp (Spatial Propagation of Single-cell Perturbations). We show that SpatialProp can predict gene expression from the tissue microenvironment and map fine-grained steering of tissue microenvironments to new target states. To assess for causal enrichment in spatial perturbation predictions, we propose CausalInteractionBench, a bidirectional benchmarking approach using curated cell-cell interactions. Under this benchmark, we evaluate the causal utility of SpatialProp in predicting the spatial effects of different perturbations. SpatialProp provides a framework towards rapid hypothesis generation and in silico perturbation experiments, particularly in the study of spatially patterned tissue biology.

bioinformatics↗

bioRxiv2024

The expression of integron arrays is shaped by the translation rate of cassettes

Integrons are key elements in the rise and spread of multidrug resistance in Gram-negative bacteria. These genetic platforms capture cassettes containing promoterless genes and stockpile them in arrays of variable length. In the current integron model, expression of cassettes is granted by the Pc promoter in the platform and is assumed to decrease as a function of its distance. Here we explored this model using a large collection of 136 antibiotic resistance cassettes and show that the effect of distance is in fact negligible. Instead, cassettes have a strong impact in the expression of downstream genes because their translation rate affects the stability of the whole polycistronic mRNA molecule. Hence, poorly translated cassettes decrease the expression and resistance phenotype of cassettes downstream. Our data puts forward a novel integron model in which expression is contingent on the translation of cassettes upstream, rather than on the distance to the Pc.

microbiology↗

bioRxiv2023

A Deep Dive into Single-Cell RNA Sequencing Foundation Models

Large-scale foundation models, which are pre-trained on massive, unlabeled datasets and subsequently fine-tuned on specific tasks, have recently achieved unparalleled success on a wide array of applications, including in healthcare and biology. In this paper, we explore two foundation models recently developed for single-cell RNA sequencing data, scBERT and scGPT. Focusing on the fine-tuning task of cell type annotation, we explore the relative performance of pre-trained models compared to a simple baseline, L1-regularized logistic regression, including in the few-shot setting. We perform ablation studies to understand whether pretraining improves model performance and to better understand the difficulty of the pre-training task in scBERT. Finally, using scBERT as an example, we demonstrate the potential sensitivity of fine-tuning to hyperparameter settings and parameter initializations. Taken together, our results highlight the importance of rigorously testing foundation models against well established baselines, establishing challenging fine-tuning tasks on which to benchmark foundation models, and performing deep introspection into the embeddings learned by the model in order to more effectively harness these models to transform single-cell data analysis. Code is available at https://github.com/clinicalml/sc-foundation-eval.

genomics↗

bioRxiv2023

GET: a foundation model of transcription across human cell types

Transcriptional regulation, involving the complex interplay between regulatory sequences and proteins, directs all biological processes. Computational models of transcription lack generalizability to accurately extrapolate in unseen cell types and conditions. Here, we introduce GET, an interpretable foundation model designed to uncover regulatory grammars across 213 human fetal and adult cell types. Relying exclusively on chromatin accessibility data and sequence information, GET achieves experimental-level accuracy in predicting gene expression even in previously unseen cell types. GET showcases remarkable adaptability across new sequencing platforms and assays, enabling regulatory inference across a broad range of cell types and conditions, and uncovering universal and cell type specific transcription factor interaction networks. We evaluated its performance on prediction of regulatory activity, inference of regulatory elements and regulators, and identification of physical interactions between transcription factors. Specifically, we show GET outperforms current models in predicting lentivirus-based massive parallel reporter assay readout with reduced input data. In fetal erythroblasts, we identify distal (>1Mbp) regulatory regions that were missed by previous models. In B cells, we identified a lymphocyte-specific transcription factor-transcription factor interaction that explains the functional significance of a leukemia-risk predisposing germline mutation. In sum, we provide a generalizable and accurate model for transcription together with catalogs of gene regulation and transcription factor interactions, all with cell type specificity.

bioinformatics↗