Gehad Youssef

Non-exonic read content reorganises lncRNA co-expression networks in renal and other cancers

The paper shows that non-exonic read fractions reorganize lncRNA co-expression networks in renal and other cancers, with varying impacts across cancer types.

Malignant and stromal partial EMT programmes and cetuximab outcome in head and neck cancer

The paper identifies malignant and stromal partial EMT programs in head and neck cancer and shows that malignant measures correlate with better cetuximab outcomes.

Single-cell foundation models reveal context-sensitive cancer programmes under subtype shift

The paper fine-tunes two scFMs on cancer subtypes and shows they outperform LightGBM on out-of-domain subtypes, with context-sensitive adaptation supported by interpretability analysis.

A systems-level machine learning approach uncovers therapeutic targets in clear cell renal cell carcinoma

This paper develops a machine learning framework for therapeutic target discovery in ccRCC, identifying 16 targets and novel mechanisms with superior efficacy to standard-of-care drugs.

Combined stem cell and predictive models reveal flavin cofactors as targets in metabolic liver dysfunction

The paper combines stem cell models and computational predictions to identify flavin cofactors as therapeutic targets for metabolic liver dysfunction.

dialogi: Utilising NLP with chemical and disease similarities to drive the identification of Drug-Induced Liver Injury literature

The paper presents an automated pipeline using NLP and chemical/disease embeddings to classify DILI-related literature, achieving high F1-scores in distinguishing DILI-positive from negative papers.

DILIc: An AI-based classifier to search for Drug-Induced Liver Injury literature

This paper introduces DILIc, an AI classifier that identifies Drug-Induced Liver Injury literature using NLP and ML, achieving high accuracy in cross-validation and external validation.