software / tool

This paper introduces eVAE, a discrete-latent model for single-cell perturbation prediction, achieving state-of-the-art results on multiple metrics and outperforming existing methods in perturbation ranking.

BIOINF-farma integrates epitope prediction and developability assessment to prioritize vaccine candidates by combining antigenicity and expression feasibility scores.

miRBind2 is a deep learning model that predicts miRNA binding and transcript repression from sequence, outperforming existing methods with fewer parameters.

The paper develops a deep-learning model to translate spatial topography maps into individualized connectomes, confirming its accuracy and ability to retain brain-cognition associations.

ScriptManager v1.0 provides a unified framework for reproducible and scalable analysis of genomics and epigenomics data across diverse assays.

This paper develops a cloud-connected stem cell platform to enhance scientific identity in underrepresented students, showing improved outcomes in competence and research readiness.

novelBGC assesses BGC novelty and prioritizes candidates using two scores, outperforming single-axis tools in identifying novel clusters.

The paper introduces FORGE-KI, a modular framework for endogenous knock-in engineering that supports multiple repair pathways and provides software for automated design.

AMaNITA provides an end-to-end workflow for analyzing nanopore native tRNA sequencing data, enabling differential abundance and modification stoichiometry analysis.

This study compares transparency reporting in two neurotrauma journals, finding that a required rigor section improves some reporting practices but not all.

FlowBench evaluates agentic bioinformatics systems by decomposing performance into planning, fault recovery, interpretation, and output fidelity, revealing limitations in toolchain inference and fault handling.

IAN is an R package that integrates and interprets omics data using a multi-agent AI system with LLMs, demonstrating its ability to avoid hallucination and support biological discovery.

The paper uses Monte Carlo simulations to model neutron protein crystallography experiments for the NMX instrument at ESS, improving event formation and analyzing scattering effects.

MartiniSurf automates the setup of surface-immobilized biomolecular systems for Martini simulations, enabling systematic in silico studies of immobilization strategies.

The paper introduces a Transformer-based VAE for molecular encoding and generation, achieving high reconstruction accuracy and a well-structured latent space aligned with chemical similarity.

This study shows that motor and fear learning in mice do not require newly formed myelin sheaths or rapid saltatory conduction, as Mbp-cKO mice with impaired myelination still learned and remembered normally.

RetroMol converts natural product structures and biosynthetic gene clusters into shared primary sequences to enable biosynthetic similarity comparisons.

AutoZyme optimizes bioinformatics software by autonomously identifying and applying code changes to improve runtime without significant memory use.

TWIST is a framework that models tree water deficit dynamics using dendrometer data, showing good agreement with observed patterns and enabling integration into forest models.

scIsoAgent improves long-read single-cell RNA-seq analysis by creating reproducible, isoform-resolved workflows and linking sequence data to functional hypotheses.

The paper presents tools to harmonize viral genomic data across repositories and mask lab-specific artifacts, improving phylogenetic analysis accuracy.

The paper introduces FORGE-CRISPR, a system for constructing CRISPR libraries using modular components, enabling flexible and reusable library generation for functional genomics studies.

GSPlot visualizes gene set similarity in enrichment results by displaying gene sets in a 2D space based on their enriched content similarity.

oxo-flow is a Rust-based workflow engine that compiles to a native binary, offering faster execution and lower memory usage compared to existing tools like Snakemake and Nextflow.

The paper presents a generative AI pipeline for discovering antifungal peptides, identifying five with activity against fungal pathogens and low cytotoxicity.

The paper develops lrSAGA, a tool to improve genome assembly from long-read MDA sequencing of single cells, achieving higher completeness and fewer misassemblies.

This paper introduces a GreenGate-compatible vector toolkit for efficient recombinant protein purification from E. coli by enabling modular assembly of affinity tags.

OrganScaleR provides a Shiny tool for size-adjusted organ-weight analysis in mice, avoiding misleading ratios by using ANCOVA or causal mediation based on body-weight overlap.

This paper introduces an AI-assisted framework for rapid prototyping of multicellular mechanistic models using LLMs and MCP servers to integrate multiple modeling tools.

The paper introduces IMCell, a method for predicting optimized transcription factor sets for cell fate engineering, showing improved performance over existing tools on synthetic and curated data.