Can human experts predict solubility better than computers?
Can human experts predict solubility better than computers?
复制标题
DOI：
10.1186/s13321-017-0250-y
复制
发表时间：
2017-12-13
影响因子：
8.6
通讯作者：
Mitchell JBO
中科院分区：
文献类型：
--
作者：
Boobier S;Osbourn A;Mitchell JBO
在这项研究中，我们设计并进行了一项调查，要求人类专家预测类药物有机化合物的水溶性。我们调查这些主要来自制药行业和学术界的专家是否能够匹配或超过算法的预测能力。除此之外，我们还在同一数据集上实现了 10 种典型的机器学习算法。最好的算法是一种称为多层感知器的神经网络，其 RMSE 为 0.985 log S 单位，R2 为 0.706。我们不会提前预测这个特定算法的相对成功。我们发现，最好的人类预测器产生了几乎相同的预测质量，RMSE 为 0.942 log S 单位，R2 为 0.723。算法集合包含较高比例的相当好的预测器，十分之九，而人类的预测器比例大约为一半。我们发现，无论是对于人类还是算法，通过采用中值将个体预测组合成共识预测器会产生出色的预测性。虽然我们的共识人类预测器在各种统计指标上取得了稍微好一些的总体数据，但它与共识机器学习预测器之间的差异很小并且在统计上不显着。我们的结论是，人类专家可以与机器学习算法基本相同地预测药物分子的水溶性。我们发现，无论对于人类还是算法来说，通过取中位数将个体预测组合成共识预测器是从群体智慧中受益的有效方式。本文的在线版本 (10.1186/s13321-017-0250-y) 包含补充材料，可供授权用户使用。
In this study, we design and carry out a survey, asking human experts to predict the aqueous solubility of druglike organic compounds. We investigate whether these experts, drawn largely from the pharmaceutical industry and academia, can match or exceed the predictive power of algorithms. Alongside this, we implement 10 typical machine learning algorithms on the same dataset. The best algorithm, a variety of neural network known as a multi-layer perceptron, gave an RMSE of 0.985 log S units and an R2 of 0.706. We would not have predicted the relative success of this particular algorithm in advance. We found that the best individual human predictor generated an almost identical prediction quality with an RMSE of 0.942 log S units and an R2 of 0.723. The collection of algorithms contained a higher proportion of reasonably good predictors, nine out of ten compared with around half of the humans. We found that, for either humans or algorithms, combining individual predictions into a consensus predictor by taking their median generated excellent predictivity. While our consensus human predictor achieved very slightly better headline figures on various statistical measures, the difference between it and the consensus machine learning predictor was both small and statistically insignificant. We conclude that human experts can predict the aqueous solubility of druglike molecules essentially equally well as machine learning algorithms. We find that, for either humans or algorithms, combining individual predictions into a consensus predictor by taking their median is a powerful way of benefitting from the wisdom of crowds. The online version of this article (10.1186/s13321-017-0250-y) contains supplementary material, which is available to authorized users.
登录
查看更多内容
影响因子：
4.8
作者：
Guenther, Nick;Schonlau, Matthias
通讯作者：
Schonlau, Matthias
DOI：
10.1109/101.8118
发表时间：
1988-09-01
期刊：
IEEE CIRCUITS AND DEVICES MAGAZINE
影响因子：
--
作者：
HOPFIELD, JJ
通讯作者：
HOPFIELD, JJ
影响因子：
7.3
作者：
Charifson, PS;Corkery, JJ;Walters, WP
通讯作者：
Walters, WP
影响因子：
7.5
作者：
Geurts, P;Ernst, D;Wehenkel, L
通讯作者：
Wehenkel, L
admetSAR：用于评估化学 ADMET 特性的综合来源和免费工具
影响因子：
5.6
作者：
Cheng, Feixiong;Li, Weihua;Tang, Yun
通讯作者：
Tang, Yun