Institute of Quantitative Biology, Biochemistry and Biotechnology, University of Edinburgh, Edinburgh, Scotland EH9 3BF, UK.
Department of Microbiology and Environmental Toxicology, University of California at Santa Cruz, Santa Cruz, CA 95064, USA; Institute for Integrative Systems Biology (I(2)SysBio), Universitat de València and Spanish Research Council (CSIC), 46980 Valencia, Spain.
J Adv Res. 2023 Apr;46:135-147. doi: 10.1016/j.jare.2022.07.001. Epub 2022 Jul 25.
The discovery of a new drug is a costly and lengthy endeavour. The computational prediction of which small molecules can bind to a protein target can accelerate this process if the predictions are fast and accurate enough. Recent machine-learning scoring functions re-evaluate the output of molecular docking to achieve more accurate predictions. However, previous scoring functions were trained on crystalised protein-ligand complexes and datasets of decoys. The limited availability of crystal structures and biases in the decoy datasets can lower the performance of scoring functions.
To address key limitations of previous scoring functions and thus improve the predictive performance of structure-based virtual screening.
A novel machine-learning scoring function was created, named SCORCH (Scoring COnsensus for RMSD-based Classification of Hits). To develop SCORCH, training data is augmented by considering multiple ligand poses and labelling poses based on their RMSD from the native pose. Decoy bias is addressed by generating property-matched decoys for each ligand and using the same methodology for preparing and docking decoys and ligands. A consensus of 3 different machine learning approaches is also used to improve performance.
We find that multi-pose augmentation in SCORCH improves its docking power and screening power on independent benchmark datasets. SCORCH outperforms an equivalent scoring function trained on single poses, with a 1 % enrichment factor (EF) of 13.78 vs. 10.86 on 18 DEKOIS 2.0 targets and a mean native pose rank of 5.9 vs 30.4 on CSAR 2014. Additionally, SCORCH outperforms widely used scoring functions in virtual screening and pose prediction on independent benchmark datasets.
By rationally addressing key limitations of previous scoring functions, SCORCH improves the performance of virtual screening. SCORCH also provides an estimate of its uncertainty, which can help reduce the cost and time required for drug discovery.
发现一种新药是一项昂贵且漫长的工作。如果预测足够快速和准确，那么计算预测哪些小分子可以与蛋白质靶标结合，可以加速这一过程。最近的机器学习打分函数重新评估分子对接的输出，以实现更准确的预测。然而，以前的打分函数是在晶体蛋白-配体复合物和诱饵数据集上进行训练的。晶体结构的有限可用性和诱饵数据集的偏差会降低打分函数的性能。
解决以前打分函数的关键限制问题，从而提高基于结构的虚拟筛选的预测性能。
创建了一种新的机器学习打分函数，名为 SCORCH（基于 RMSD 的命中分类的打分共识）。为了开发 SCORCH，通过考虑多个配体构象并根据它们与天然构象的 RMSD 来标记构象，来扩充训练数据。通过为每个配体生成具有匹配属性的诱饵，并使用相同的方法来准备和对接诱饵和配体，来解决诱饵偏差问题。还使用 3 种不同的机器学习方法的共识来提高性能。
我们发现，SCORCH 中的多构象扩充提高了其在独立基准数据集上的对接能力和筛选能力。SCORCH 的富集因子（EF）为 13.78，比在 18 个 DEKOIS 2.0 靶标上训练的等效打分函数高 1%，在 CSAR 2014 上的天然构象平均排名为 5.9，而不是 30.4。此外，SCORCH 在独立基准数据集上的虚拟筛选和构象预测方面优于广泛使用的打分函数。
通过合理解决以前打分函数的关键限制，SCORCH 提高了虚拟筛选的性能。SCORCH 还提供了其不确定性的估计，这有助于降低药物发现的成本和时间。
