Skip to main content

Papers & preprints

11: Publications
4: Journal articles
3: Conference papers
4: Preprints

2026

Scikit-fingerprints: Python library for scikit-learn compatible molecular fingerprints and chemoinformatics

J. Adamczyk, A. Staniszewski

arXiv preprint2026

Molecular fingerprints are strong models for peptide function prediction

J. Adamczyk, P. Ludynia, W. Czech

Bioinformatics2026

Paper arXiv Code

Evaluating machine learning models for predicting pesticide toxicity to honey bees

J. Adamczyk, J. Poziemski, P. Siedlecki

Ecotoxicology and Environmental Safety, vol. 3122026

Application of machine learning to monster level prediction in tabletop RPG game design

J. Śliwa, J. Adamczyk

arXiv preprint2026

2025

Towards Rational Pesticide Design with Graph Machine Learning Models for Ecotoxicology

J. Adamczyk

Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM)2025

MolPILE - large-scale, diverse dataset for molecular representation learning

J. Adamczyk, J. Poziemski, F. Job, M. Król, M. Makowski

arXiv preprint2025

arXiv Code Dataset

Benchmarking pretrained molecular embedding models for molecular representation learning

M. Praski, J. Adamczyk, W. Czech

arXiv preprint2025

ApisTox: a new benchmark dataset for the classification of small molecules toxicity on honey bees

J. Adamczyk, J. Poziemski, P. Siedlecki

Scientific Data, vol. 12, article 52025

Paper arXiv Code UCI

2024

Scikit-fingerprints: easy and efficient computation of molecular fingerprints in Python

J. Adamczyk, P. Ludynia

SoftwareX, vol. 28, 1019442024

Paper arXiv Code

Molecular Topological Profile (MOLTOP) - simple and strong baseline for molecular graph classification

J. Adamczyk, W. Czech

27th European Conference on Artificial Intelligence (ECAI)2024

Paper arXiv Code

2023

Strengthening structural baselines for graph classification using Local Topological Profile

J. Adamczyk, W. Czech

International Conference on Computational Science (ICCS)2023

Paper arXiv Code