sequence-classification

music genre classification using 2D CNN, 1D CNN - LSTM and Librosa

Saccharomyces cerevisiae information, gene calling and ORF identification assistant

Custom PyTorch Transformer on behavioral event sequences. AUC-PR 0.269 · AUC-ROC 0.928 · MLflow · Kafka · AWS S3 · Airflow · Live demo included.

A useful repository for calculating classification baselines using Bert

End-to-end NLP pipeline for sequence classification using DistilBERT and Hugging Face Transformers on AG News and custom Wikipedia datasets.

Educational malware classifier comparing BiGRU, 1D CNN, and Transformer models on Windows API-call sequences.

Source code and details about implementation and datasets for EDEN: Multiscale Expected Density of Nucleotide Encoding for Enhanced DNA Sequence Classification with Hybrid Deep Learning

Identify algorithmic structures in source code using Abstract Syntax Trees (ASTs) and a CodeBERTa-based classifier. Combines syntactic analysis with transformer embeddings for structure classification from small datasets.

Schematic Blueprint for Finetuning LLM (e.g. Qwen or Llama) for text classification using LORA. Output model can have original or modified head (e.g. for SequenceClassification).

Experimental genomics AI for learning biological representations from DNA sequences.

Research software and evidence package for sequence-only antimicrobial peptide classification

This is the repository to my bachelor's thesis. The aim was to classify antisemitic comments. A custom dataset was created with the 4chan API and labeled. Different DistilBERT models for sequence-classification were trained and compared. A case study was then conducted.

This is a repository with the assignments of IE678 Deep Learning course at University of Mannheim.

Genomics ML case study using GENA-LM for DNA sequence classification, transformer fine-tuning, evaluation, attention analysis, and t-SNE representations.

StableDNAm: stable and efficient DNA methylation prediction with adaptive feature correction learning (BMC Genomics, 2023)

Multilabel Text Sequence Classification

Computational toolkit for DNA sequence analysis.

Developed system for the "Climate Activism Stance and Hate Event Detection" Shared Task at CASE 2024

Multi-task Orthohantavirus classification by fine-tuning DNABERT-2 — species, host, and geographic origin in a single forward pass.

Production-ready ML repo for early sepsis risk prediction from ICU time-series. Covers GRU/LSTM/PatchTST sequence modeling, deterministic preprocessing, calibration analysis, manifest-backed threshold modes, FastAPI serving, and a deployment-safe public Streamlit demo. Research use only.