A chronological archive of papers and research work.

Selected papers, write-ups, and formal research-oriented publications.

30 MAR 2026

RNA Secondary Structure Prediction using a Transformer Encoder

Marcel Arian Hadi, Peregrin Wahle

Predicting RNA secondary structure from nucleotide sequence is an important problem in computational biology. In this work, we study the task of translating RNA sequences into dot-bracket secondary structure representations using a Transformer encoder model. We systematically evaluate multiple model configurations and training settings, and assess their performance using both token-level and structure-aware metrics, including sequence-level exact match, paired F1 score, and structural validity. In addition, we analyze the impact of simple postprocessing strategies for correcting invalid structures and perform a downstream structure-level analysis based on the repaired dot-bracket outputs. Our findings show that Transformer encoders are capable of capturing relevant structural patterns in RNA sequences, but that standard token-level objectives alone are insufficient for producing valid structures. Incorporating structure-aware evaluation and lightweight postprocessing significantly improves the quality and validity of the predicted outputs.

30 SEP 2025

The relevance of LIME to SHAP and Anchors: A literature-based analysis

Marcel Arian Hadi

With the increasing use of complex machine learning models in sensitive fields such as medicine, finance or justice, there is a growing demand for transparency and traceability of automated decisions. Explainable Artificial Intelligence (XAI) has therefore become a central research field. This work supports LIME's relevance to more modern methods like SHAP and Anchors.