@BarakRaveh 🧰 Source code and benchmark data are openly available:

@BarakRaveh This study introduces the TEMPO integrator, a temporally multiscale method that reduces the number of force evaluations in Brownian dynamics simulations. Benchmarked on IDP models and nucleocytoplasmic transport, TEMPO-enabled simulations achieved 27–32x speedups while preserving.

🧮 Explore the latest from Bioinformatics Advances: “The TEMPO integrator: Accelerating molecular simulations by Temporally Multiscale Force Prediction” . Full article available: . Authors include: @BarakRaveh

🖥️ Source code and sample data can be found here: 

It implements both maxT and adaptive permutation methods, achieving speedups of up to 447x over PLINK on large datasets. The tool is deployable via AWS EC2 and requires no prior FPGA expertise.

This paper presents an FPGA-based tool that accelerates genome-wide association study (#GWAS) permutation testing for continuous #phenotypes.

🧠 Just out in Bioinformatics Advances: “FPGA acceleration of GWAS permutation testing” . Explore the full study:

@pietermonsieurs 💻 The DAPCy software is available #opensource: .Find code, documentation, and tutorials here:

@pietermonsieurs DAPCy reimplements the DAPC method in #Python using scikit-learn to enhance scalability for large #genomic datasets. It applies truncated SVD for dimensionality reduction, supports sparse matrices, and introduces cross-validation strategies to improve accuracy and efficiency over.

🐍 Now published in Bioinformatics Advances: “DAPCy: a Python package for the Discriminant Analysis of Principal Components method for population genetic analyses” . Full article available: . Authors include: @pietermonsieurs

@RishadShafik 🛠️ Tools and visualizations available at:

@RishadShafik This study applies logic-based Tsetlin Machines to predict bacterial pathogens in PD-related peritonitis from effluent immune profiles. A hierarchical classification strategy achieved up to 100% validation accuracy at key stages, outperforming neural networks while enabling full.

🔍 Just out in Bioinformatics Advances: “Prediction of the infecting organism in peritoneal dialysis patients with acute peritonitis using interpretable Tsetlin Machines” . Explore the full study: . Authors include: @RishadShafik

🧰 Installation guide, tutorials, and resources are available here:

NRGSuite-Qt integrates multiple computational tools—FlexAID, NRGRank, Surfaces, NRGTEN, and IsoMIF—into a single PyMOL plugin for docking, screening, cavity detection, binding-site comparison, and normal mode analysis. Benchmarking confirms both speed and accuracy across use.

🧪 Just out in Bioinformatics Advances: "NRGSuite-Qt: A PyMOL plugin for high-throughput virtual screening, molecular docking, normal-mode analysis, the study of molecular interactions and the detection of binding-site similarities"  . Explore the full study:

🧾 Source code, documentation, and implementation details available at:

Tested on 8 benchmark datasets, it consistently outperformed BioBERT, PubMedBERT, and other SOTA models in both precision and F1-score without relying on large-scale pretraining.

GRU-SCANET introduces a GRU-based architecture integrating positional encoding, BiGRUs, multi-head attention, and a CRF decoder for biomedical NER.

🧠 Explore the latest from Bioinformatics Advances: "GRU-SCANET: Unleashing the Power of GRU-based Sinusoidal CApture Network for Precision-driven Named Entity Recognition" . Full article available: