Kai Wang

This study evaluates if pre-training chemical language models on large compound datasets improves compound representation, finding that standard masked language modeling is insufficient.

TNER improves mutation detection in ctDNA by reducing background errors, outperforming existing methods on simulated and real data.

The paper identifies UBE2G1 as a critical E2 ubiquitin-conjugating enzyme required for the degradation of CRL4CRBN neomorphic substrates, showing its role in drug resistance and potential for overcoming it with next-generation compounds.