contamination-detection

Outlier Detection Thresholding

GroundWater Spatiotemporal Data Analysis Tool (GWSDAT) R-Shiny implementation.

CroCoDeEL detects cross-sample contamination in shotgun metagenomic data

A simple pipeline for bacterial assembly and quality control

[ICML 2026] CapBencher toolkit: Give your LLM benchmark a built-in alarm for leakage and gaming

DecontaMiner is a tool designed and developed to investigate the presence of contaminating sequences in unmapped NGS data. It can suggest the presence of contaminating organisms in sequenced samples, that might derive either from laboratory contamination or from their biological source, and in both cases can be considered as worthy of further in…

Python package to calculate various sample contamination metrics.

Fast microbial species identification (16S rRNA gene-based approach) and contamination check using whole genome assemblies

Multimodal evaluation benchmark for AI agents in real-world field operations across 16 trades (HVAC, electrical, plumbing, roofing, solar, mining, oil & gas, marine, telecom, automotive, construction, and more). 194 cases; scores retrieval, code citation, jurisdiction, safety, trajectory, multi-turn, speed; 5-layer contamination defense.

Epidemic Modeling Study: This study analyzes with Linear Algebra the progression of disease contagion within a population. Covid-19 Dashboard: We have created an interactive dashboard to analyze the data on the behavior of the Coronavirus in Brazil. The project is powered by a public CSV dataset.

In this repository I backup the pipelines I write for the project I am involved

Generate Coverage, Quality and Contamination metrics for Sequence data.

Production-honest small language model training factory: data import, pretraining, SFT, eval gates, contamination checks, and GPU runbooks.

Containerized Snakemake workflow that diagnoses why short-read samples align poorly — contamination, vector/transgene, rRNA, adapter, and spike-in multimapping — and identifies the unaligned reads in a self-contained HTML report.

Leaderboard reproduzível de LLMs em provas médicas brasileiras (Revalida, INEP) — zero-shot, 3 execuções, análise de contaminação

Unified bacterial genome QC: BUSCO-style completeness, contamination detection that tells plasmids from contaminants, and comparative gene content with a permutation null for genomic islands.

Evidence-first benchmark contamination and dataset integrity auditor

AI/ML-based system to predict radioactive contamination in groundwater using basic water quality parameters, enabling early detection and safer water management.