Rajgopal Srinivasan

Wnt stimulation and inhibition in the development and phenotype of patient-derived gallbladder organoids

This study compares the effects of Wnt activation and inhibition on gallbladder organoid development, phenotype, and drug response using patient-derived tissues.

Insights into gallbladder cancer pathogenesis from a living organoid gallbladder cholangiocyte biorepository

The paper develops and characterizes patient-derived gallbladder organoids to study gallbladder cancer pathogenesis, finding that XGC samples cluster with malignant subtypes and show neoplastic changes through chronic inflammation.

An improved deep learning model for immunogenic B epitope prediction

This study improves B epitope prediction by combining protein embeddings with structural features, showing better performance than models using embeddings alone.

SKiD: A Structure-Oriented Kinetics Database of Enzyme-Substrate Interactions

This paper introduces SKiD, a database linking enzyme kinetics parameters with 3D structural data of enzyme-substrate complexes, enhancing understanding of enzymatic function.

Evaluation of enzyme activity predictions for variants of unknown significance in Arylsulfatase A

The paper evaluates variant effect predictions for ARSA gene variants, finding that a bootcamp-trained model outperformed others and that deep learning slightly improved performance over simpler methods.

Critical assessment of variant prioritization methods for rare disease diagnosis within the Rare Genomes Project

The paper evaluates variant prioritization methods for rare disease diagnosis using data from the Rare Genomes Project, finding that top models identify causal variants in most solved families and uncover potential candidates in unsolved ones.

Identifying Factors Important for Conservation at Sites of Synonymous Variations

The paper uses machine learning to identify factors influencing conservation at synonymous variant sites, finding that non-allele-dependent features significantly impact conservation scores.

MAGE: Strain Level Profiling of Metagenome Samples

MAGE accurately identifies microbial strains and quantifies their abundances using read mapping information without relying on strain-specific markers.

Cell-to-cell and type-to-type heterogeneity of signaling networks: Insights from the crowd

The paper organizes a DREAM challenge to benchmark predictive models of single-cell signaling using mass cytometry data from breast cancer cell lines.

Perturbation robustness analyses reveal important parameters in variant interpretation pipelines

The paper evaluates how parameter choices affect variant interpretation pipelines by systematically perturbing parameters and shows that certain choices significantly impact sensitivity and specificity.

DNA from dried blood spots yields high quality sequences for exome analysis

This study evaluates the quality of exome sequencing from DNA extracted from dried blood spots (DBS) and finds it comparable to whole blood, with similar variant calling accuracy.

Sequence Alignment On Directed Graphs

This paper introduces V-ALIGN, a new sequence alignment algorithm for directed graphs that avoids DAGification steps, improving efficiency for aligning sequences on genomic variation graphs.

GPhase: Greedy Approach for Accurate Haplotype Inferencing

GPhase is a fast and accurate haplotype inference tool that outperforms existing methods on real and simulated datasets.