GAIL L. ROSEN

The paper identifies a germline KDM3C polymorphism linked to impaired DNA repair and increased sensitivity to chemoradiotherapy in cancers like rectal and head and neck squamous cell carcinomas.

Nevermore improves lead optimization by balancing binding affinity and developability constraints using a database-grounded framework with interpretable molecular edits.

This study evaluates uncertainty quantification methods to improve reliability of genomic language models under distribution shift in genomic and metagenomic tasks.

This paper evaluates transcriptomic similarities between liver cancer cell lines and primary tumors to guide model selection and identify authentication issues.

This study uses the Naïve Bayes Classifier++ to detect novel taxa in metagenomic data by analyzing log-likelihood scores across simulated and real datasets.

The paper describes a comprehensive genomic dataset from a tumor-normal pair with broad consent, generated using multiple sequencing technologies for benchmarking somatic variant detection.

This study evaluates NBC++'s query performance across different parameters and shows its efficiency in training but longer query times, with challenges in classifying full diversity of life.

The paper introduces iMMseqs2 and iDiamond, incremental search tools for protein sequence databases, which maintain high accuracy while reducing computational resources.

Scorpio improves DNA sequence embeddings using contrastive learning, enhancing performance in taxonomic classification, AMR gene detection, and promoter identification across diverse datasets.

This paper introduces a novel fragment-based drug discovery method that uses evolutionary optimization and ligand-based virtual prescreening to efficiently identify high-affinity ligands.

The paper evaluates metagenomic software tools using realistic datasets, highlighting improvements in assembly and taxon profiling while identifying remaining challenges in virus/archaea detection and reproducibility.

MetaMutationalSigs aggregates and compares mutational signature refitting results from different tools to facilitate comparison across cancer types.

The paper introduces a deep learning model for microbial DNA sequence analysis, achieving phenotypic prediction and sequence visualization with performance comparable to conventional methods.

The paper investigates how tilling affects microbial communities in TNT and DNT contaminated soils and identifies potential degradation pathways for these contaminants.

The paper demonstrates that incremental learning improves metagenomic classification accuracy over time by updating classifiers with new genomic data without retraining from scratch.

This paper introduces a framework for efficient SARS-CoV-2 subtyping using Informative Subtype Markers (ISMs) to track spatiotemporal dynamics of the virus.

The paper identifies frequent RRM2B amplification in multiple tumors, links it to DNA repair defects and poor outcomes, and suggests therapeutic opportunities.

The paper introduces a topic modeling approach to analyze 16S rRNA amplicon data, linking microbial co-occurrence patterns to functional and environmental features.

The paper develops sequence embeddings for 16S rRNA data to create numeric representations suitable for machine learning, showing they preserve biological information and perform well in downstream tasks.

Deep learning rivals or beats baselines across imaging, health records, genomics and drug discovery but is not yet transformative; scarce labels, privacy and opacity remain hurdles.

This study benchmarks eleven metagenomic classifiers using 846 species and evaluates strategies to reduce false positives in taxonomic classification.

This paper evaluates a topic model approach for analyzing microbiome data, showing it captures dynamic behavior and identifies gut configurations in time-series data.

The paper tests nanopore sequencing in microgravity using a parabolic flight simulator and proposes new computational methods to address sequencing challenges in reduced gravity.