Deep Learning for Virtual Screening: Five Reasons to Use ROC Cost
Functions
- URL: http://arxiv.org/abs/2007.07029v1
- Date: Thu, 25 Jun 2020 08:46:37 GMT
- Title: Deep Learning for Virtual Screening: Five Reasons to Use ROC Cost
Functions
- Authors: Vladimir Golkov, Alexander Becker, Daniel T. Plop, Daniel
\v{C}uturilo, Neda Davoudi, Jeffrey Mendenhall, Rocco Moretti, Jens Meiler,
Daniel Cremers
- Abstract summary: deep learning has become an important tool for rapid screening of billions of molecules in silico for potential hits containing desired chemical features.
Despite its importance, substantial challenges persist in training these models, such as severe class imbalance, high decision thresholds, and lack of ground truth labels in some datasets.
We argue in favor of directly optimizing the receiver operating characteristic (ROC) in such cases, due to its robustness to class imbalance.
- Score: 80.12620331438052
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Computer-aided drug discovery is an essential component of modern drug
development. Therein, deep learning has become an important tool for rapid
screening of billions of molecules in silico for potential hits containing
desired chemical features. Despite its importance, substantial challenges
persist in training these models, such as severe class imbalance, high decision
thresholds, and lack of ground truth labels in some datasets. In this work we
argue in favor of directly optimizing the receiver operating characteristic
(ROC) in such cases, due to its robustness to class imbalance, its ability to
compromise over different decision thresholds, certain freedom to influence the
relative weights in this compromise, fidelity to typical benchmarking measures,
and equivalence to positive/unlabeled learning. We also propose new training
schemes (coherent mini-batch arrangement, and usage of out-of-batch samples)
for cost functions based on the ROC, as well as a cost function based on the
logAUC metric that facilitates early enrichment (i.e. improves performance at
high decision thresholds, as often desired when synthesizing predicted hit
compounds). We demonstrate that these approaches outperform standard deep
learning approaches on a series of PubChem high-throughput screening datasets
that represent realistic and diverse drug discovery campaigns on major drug
target families.
Related papers
- YZS-model: A Predictive Model for Organic Drug Solubility Based on Graph Convolutional Networks and Transformer-Attention [9.018408514318631]
Traditional solubility prediction techniques often fail to capture the complex nature of molecular tructures, leading to notable deviations between predictions and actual results.
This research introduces a novel deep learning framework combining attention-based transformers, Long Short-Term Memory (LSTM) networks, and Graph Convolutional Networks (GCN)
Our method achieved a correlation coefficient ($R2$) of 0.59 and a Root Mean Square Error (RMSE) of 0.57, which outperforms the benchmark models' scores of 0.52 ($R2$) and 0.61 (RMSE)
arXiv Detail & Related papers (2024-06-27T12:40:29Z) - MoleculeCLA: Rethinking Molecular Benchmark via Computational Ligand-Target Binding Analysis [18.940529282539842]
We construct a large-scale and precise molecular representation dataset of approximately 140,000 small molecules.
Our dataset offers significant physicochemical interpretability to guide model development and design.
We believe this dataset will serve as a more accurate and reliable benchmark for molecular representation learning.
arXiv Detail & Related papers (2024-06-13T02:50:23Z) - Physical formula enhanced multi-task learning for pharmacokinetics prediction [54.13787789006417]
A major challenge for AI-driven drug discovery is the scarcity of high-quality data.
We develop a formula enhanced mul-ti-task learning (PEMAL) method that predicts four key parameters of pharmacokinetics simultaneously.
Our experiments reveal that PEMAL significantly lowers the data demand, compared to typical Graph Neural Networks.
arXiv Detail & Related papers (2024-04-16T07:42:55Z) - Take the Bull by the Horns: Hard Sample-Reweighted Continual Training
Improves LLM Generalization [165.98557106089777]
A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data.
Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets.
We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
arXiv Detail & Related papers (2024-02-22T04:10:57Z) - Machine Learning Small Molecule Properties in Drug Discovery [44.62264781248437]
We review a wide range of properties, including binding affinities, solubility, and ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity)
We discuss existing popular descriptors and embeddings, such as chemical fingerprints and graph-based neural networks.
Finally, techniques to provide an understanding of model predictions, especially for critical decision-making in drug discovery are assessed.
arXiv Detail & Related papers (2023-08-02T22:18:41Z) - Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning
Approach to Critical Care [68.8204255655161]
We introduce a deep Q-learning approach able to obtain more reliable critical care policies.
We achieve this by first pruning the action set based on all available rewards, and second training a final model based on the sparse main reward but with a restricted action set.
arXiv Detail & Related papers (2023-06-13T18:02:57Z) - Unpaired Deep Learning for Pharmacokinetic Parameter Estimation from
Dynamic Contrast-Enhanced MRI [37.358265461543716]
We present a novel unpaired deep learning method for estimating both pharmacokinetic parameters and the AIF.
Our proposed CycleGAN framework is designed based on the underlying physics model, resulting in a simpler architecture with a single generator and discriminator pair.
Our experimental results indicate that our method, which does not necessitate separate AIF measurements, produces more reliable pharmacokinetic parameters than other techniques.
arXiv Detail & Related papers (2023-06-07T11:10:10Z) - Accurate, reliable and interpretable solubility prediction of druglike
molecules with attention pooling and Bayesian learning [1.8275108630751844]
In silico prediction of solubility has been studied for its utility in virtual screening and lead optimization.
Recently, machine learning (ML) methods using experimental data has been popular because physics-based methods are not suitable for high- throughput tasks.
In this paper, we develop graph neural networks (GNNs) with the self-attention readout layer to improve prediction performance.
arXiv Detail & Related papers (2022-09-29T07:48:10Z) - SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity
Prediction [127.43571146741984]
Drug-Target Affinity (DTA) is of vital importance in early-stage drug discovery.
wet experiments remain the most reliable method, but they are time-consuming and resource-intensive.
Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue.
We present the SSM-DTA framework, which incorporates three simple yet highly effective strategies.
arXiv Detail & Related papers (2022-06-20T14:53:25Z) - Accurate and Robust Feature Importance Estimation under Distribution
Shifts [49.58991359544005]
PRoFILE is a novel feature importance estimation method.
We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
arXiv Detail & Related papers (2020-09-30T05:29:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.