Back

Development of Machine Learning-based QSAR Models for the Designing of Novel Anti-cancer Therapeutics Against Malignant Glioma

Asaad, F.; Zaka, M.; Durdagi, S.

2024-08-19 bioinformatics
10.1101/2024.08.19.608549 bioRxiv
Show abstract

In the early drug design and discovery phase, virtual screening of diverse small molecule libraries is crucial. Machine learning (ML)-based algorithms have made this process easier and faster. In this study, we have applied ML-based algorithms to generate the QSAR models for virtual screening. The aim of study is to design the statistically significant models for the screening of small molecule libraries to identify the novel hits against IDH1 mutant receptor crucial for glioblastoma multiforme (GBM). To construct the models, we have used both cell lines data (U87 and U251 cells) and the inhibitors of IDH1 mutant reported in the literature and used the pIC50 activity data to train our models. Furthermore, ligand-based 3D QSAR models and structure-based pharmacophore models were also constructed and validated.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.