Biology subjects

Batra, P.

Publications and source records attributed to Batra, P..

5 recordsLinked to original sources

bioRxiv2026

TM-Vec 2: Accelerated Protein Homology Detection for Structural Similarity

Understanding protein function is an essential aspect of many biological applications. The exponential growth of protein sequence data has created a critical throughput bottleneck for structural homology detection: While billions of protein sequences have been identified from DNA sequencing data, the number of protein folds underlying biology is surprisingly limited, likely numbering tens of thousands. The "sequence-fold gap" limits the success of functional annotation methods that rely on sequence homology, especially for newly sequenced genomes. TM-Vec is a deep learning architecture that can predict TM-scores as a metric of structural similarity directly from sequence pairs, bypassing true structural alignment. However, the computational demands of its protein language model (PLM) embeddings create a significant bottleneck for large-scale database searches. In this work we present TM-Vec 2s, a highly efficient model created through distillation from a foundational teacher model. Benchmarks on the CATH and SCOPe domains for large-scale database queries showed that TM-Vec 2s is 185x faster than the original TM-Vec, while achieving higher TM-score prediction accuracy. It is even more efficient than the structure-informed search implemented in Foldseek, while showing strong competition in identifying remote homology between protein molecules. TM-Vec 2s significantly expands scalable, efficient exploration of protein structural homology space.

bioinformatics↗

bioRxiv2022

Cross-Modal Autoencoder Framework Learns Holistic Representations of Cardiovascular State

A fundamental challenge in diagnostics is integrating multiple modalities to develop a joint characterization of physiological state. Using the heart as a model system, we develop a cross-modal autoencoder framework for integrating distinct data modalities and constructing a holistic representation of cardio-vascular state. In particular, we use our framework to construct such cross-modal representations from cardiac magnetic resonance images (MRIs), containing structural information, and electrocardiograms (ECGs), containing myoelectric information. We leverage the learned cross-modal representation to (1) improve phenotype prediction from a single, accessible phenotype such as ECGs; (2) enable imputation of hard-to-acquire cardiac MRIs from easy-to-acquire ECGs; and (3) develop a framework for performing genome-wide association studies in an unsupervised manner. Our results provide a framework for integrating distinct diagnostic modalities into a common representation that better characterizes physiologic state.

bioinformatics↗

bioRxiv2021

Genetic Analysis of Right Heart Structure and Function in 40,000 People

The heart evolved hundreds of millions of years ago. During mammalian evolution, the cardiovascular system developed with complete separation between pulmonary and systemic circulations incorporated into a single pump with chambers dedicated to each circulation. A lower pressure right heart chamber supplies deoxygenated blood to the lungs, while a high pressure left heart chamber supplies oxygenated blood to the rest of the body. Due to the complexity of morphogenic cardiac looping and septation required to form these two chambers, congenital heart diseases often involve maldevelopment of the evolutionarily recent right heart chamber. Additionally, some diseases predominantly affect structures of the right heart, including arrhythmogenic right ventricular cardiomyopathy (ARVC) and pulmonary hypertension. To gain insight into right heart structure and function, we fine-tuned deep learning models to recognize the right atrium, the right ventricle, and the pulmonary artery, and then used those models to measure right heart structures in over 40,000 individuals from the UK Biobank with magnetic resonance imaging. We found associations between these measurements and clinical disease including pulmonary hypertension and dilated cardiomyopathy. We then conducted genome-wide association studies, identifying 104 distinct loci associated with at least one right heart measurement. Several of these loci were found near genes previously linked with congenital heart disease, such as NKX2-5, TBX3, WNT9B, and GATA4. We also observed interesting commonalities and differences in association patterns at genetic loci linked with both right and left ventricular measurements. Finally, we found that a polygenic predictor of right ventricular end systolic volume was associated with incident dilated cardiomyopathy (HR 1.28 per standard deviation; P = 2.4E-10), and remained a significant predictor of disease even after accounting for a left ventricular polygenic score. Harnessing deep learning to perform large-scale cardiac phenotyping, our results yield insights into the genetic and clinical determinants of right heart structure and function.

genetics↗

bioRxiv2020

Deep learning enables genetic analysis of the human thoracic aorta

The aorta is the largest blood vessel in the body, and enlargement or aneurysm of the aorta can predispose to dissection, an important cause of sudden death. While rare syndromes have been identified that predispose to aortic aneurysm, the common genetic basis for the size of the aorta remains largely unknown. By leveraging a deep learning architecture that was originally developed to recognize natural images, we trained a model to evaluate the dimensions of the ascending and descending thoracic aorta in cardiac magnetic resonance imaging. After manual annotation of just 116 samples, we applied this model to 3,840,140 images from the UK Biobank. We then conducted a genome-wide association study in 33,420 individuals, revealing 68 loci associated with ascending and 35 with descending thoracic aortic diameter, of which 10 loci overlapped. Integration of common variation with transcriptome-wide analyses, rare-variant burden tests, and single nucleus RNA sequencing prioritized SVIL, a gene highly expressed in vascular smooth muscle, that was significantly associated with the diameter of the ascending and descending aorta. A polygenic score for ascending aortic diameter was associated with a diagnosis of thoracic aortic aneurysm in the remaining 391,251 UK Biobank participants who did not undergo imaging (HR = 1.44 per standard deviation; P = 3.7{middle dot}10-12). Defining the genetic basis of the diameter of the aorta may enable the identification of asymptomatic individuals at risk for aneurysm or dissection and facilitate the prioritization of potential therapeutic targets for the prevention or treatment of aortic aneurysm. Finally, our results illustrate the potential for rapidly defining novel quantitative traits derived from a deep learning model, an approach that can be more broadly applied to biomedical imaging data.

genomics↗

bioRxiv2019

A Genotype Concordance Study between Consumer Genetic Testing Services

The consumer genomics industry is steadily growing and delivering genetic information to over 10 million individuals. Yet, the implications of using data from different services remain unclear. We investigated the genotyped sites, concordance, and genetic risk estimation using data from three major consumer services. We found low overlap among reported genotyped sites (2.7% across all three). While there was a high concordance between overlapping sites of the two SNP-array services (99.6%), there was a lower concordance between them and a low-pass whole-genome service (73.0%). Finally, we demonstrated that the discrepancy resulted in distinct APOE genotypes and genetic risk scores of Alzheimers disease determined using these data. Our results demonstrate genotype results across consumer genomics platforms may lead to different genetic risk estimates, highlighting the need for careful quality control and interpretation.

genetics↗