Ioannis Ch. Paschalidis

Preferential CDR masking in paired antibody language models improves binding affinity prediction

This paper shows that focusing on complementarity-determining regions (CDRs) in antibody sequences improves binding affinity prediction using region-aware pretraining strategies.

ITNR: Inversion Transformer-based Neural Ranking for Cancer Drug Recommendations

The paper introduces ITNR, a transformer-based model for predicting cancer drug responses using genomic data, showing improved performance over existing methods.

Improved Predictions Of MHC-Peptide Binding Using Protein Language Models

The paper fine-tunes protein language models on peptide-MHC sequences to predict MHC-peptide binding, outperforming the existing NetMHCpan4.1 method.

Prediction of representative phenotypes using Multi-Attribute Subset Selection

This paper introduces MASS, an algorithm for selecting representative phenotypes from complex datasets, applied to microbial data to identify predictive environmental conditions.

Designing metabolic division of labor in microbial communities

The paper uses in silico models to study metabolic division of labor in microbial communities, finding nonintuitive strategies like splitting the TCA cycle between strains.