Explaining Multiclass Compound Activity Predictions Using Counterfactuals and Shapley Values

Artificial Intelligence Models and Tools for the Assessment of Drug-Herb Interactions

Artificial intelligence (AI) has emerged as a powerful tool in medical sciences that is revolutionizing various fields of drug research. AI algorithms can analyze large-scale biological data and identify molecular targets and pathways advancing pharmacological knowledge. An especially promising area is the assessment of drug interactions. The AI analysis of large datasets, such as drugs' chemical structure, pharmacological properties, molecular pathways, and known interaction patterns, can provide mechanistic insights and identify potential associations by integrating all this complex information and returning potential risks associated with these interactions. In this context, an area where AI may prove valuable is in the assessment of the underlying mechanisms of drug interactions with natural products (i.e., herbs) that are used as dietary supplements. These products pose a challenging problem since they are complex mixtures of constituents with diverse and limited information regarding their pharmacological properties, especially their pharmacokinetic data. As the use of herbal products and supplements continues to grow, it becomes increasingly important to understand the potential interactions between them and conventional drugs and the associated adverse drug reactions. This review will discuss AI approaches and how they can be exploited in providing valuable mechanistic insights regarding the prediction of interactions between drugs and herbs, and their potential exploitation in experimental validation or clinical utilization.

Systematic generation and analysis of counterfactuals for compound activity predictions using multi-task models

Most machine learning (ML) methods produce predictions that are hard or impossible to understand. The black box nature of predictive models obscures potential learning bias and makes it difficult to recognize and trace problems. Moreover, the inability to rationalize model decisions causes reluctance to accept predictions for experimental design. For ML, limited trust in predictions presents a substantial problem and continues to limit its impact in interdisciplinary research, including early-phase drug discovery. As a desirable remedy, approaches from explainable artificial intelligence (XAI) are increasingly applied to shed light on the ML black box and help to rationalize predictions. Among these is the concept of counterfactuals (CFs), which are best understood as test cases with small modifications yielding opposing prediction outcomes (such as different class labels in object classification). For ML applications in medicinal chemistry, for example, compound activity predictions, CFs are particularly intuitive because these hypothetical molecules enable immediate comparisons with actual test compounds that do not require expert ML knowledge and are accessible to practicing chemists. Such comparisons often reveal structural moieties in compounds that determine their predictions and can be further investigated. Herein, we adapt and extend a recently introduced concept for the systematic generation of molecular CFs to multi-task predictions of different classes of protein kinase inhibitors, analyze CFs in detail, rationalize the origins of CF formation in multi-task modeling, and present exemplary explanations of predictions.

Generation of Molecular Counterfactuals for Explainable Machine Learning Based on Core-Substituent Recombination

The use of black box machine learning models whose decisions cannot be understood limits the acceptance of predictions in interdisciplinary research and camouflages artificial learning characteristics leading to predictions for other than anticipated reasons. Consequently, there is increasing interest in explainable artificial intelligence to rationalize predictions and uncover potential pitfalls. Among others, relevant approaches include feature attribution methods to identify molecular structures determining predictions and counterfactuals (CFs) or contrastive explanations. CFs are defined as variants of test instances with minimal modifications leading to opposing predictions. In medicinal chemistry, CFs have thus far only been little investigated although they are particularly intuitive from a chemical perspective. We introduce a new methodology for the systematic generation of CFs that is centered on well-defined structural analogues of test compounds. The approach is transparent, computationally straightforward, and shown to provide a wealth of CFs for test sets. The method is made freely available.

Improved motor imagery classification using adaptive spatial filters based on particle swarm optimization algorithm

Background

As a typical self-paced brain-computer interface (BCI) system, the motor imagery (MI) BCI has been widely applied in fields such as robot control, stroke rehabilitation, and assistance for patients with stroke or spinal cord injury. Many studies have focused on the traditional spatial filters obtained through the common spatial pattern (CSP) method. However, the CSP method can only obtain fixed spatial filters for specific input signals. In addition, the CSP method only focuses on the variance difference of two types of electroencephalogram (EEG) signals, so the decoding ability of EEG signals is limited.

Methods

To make up for these deficiencies, this study introduces a novel spatial filter-solving paradigm named adaptive spatial pattern (ASP), which aims to minimize the energy intra-class matrix and maximize the inter-class matrix of MI-EEG after spatial filtering. The filter bank adaptive and common spatial pattern (FBACSP), our proposed method for MI-EEG decoding, amalgamates ASP spatial filters with CSP features across multiple frequency bands. Through a dual-stage feature selection strategy, it employs the Particle Swarm Optimization algorithm for spatial filter optimization, surpassing traditional CSP approaches in MI classification. To streamline feature sets and enhance recognition efficiency, it first prunes CSP features in each frequency band using mutual information, followed by merging these with ASP features.

Results

Comparative experiments are conducted on two public datasets (2a and 2b) from BCI competition IV, which show the outstanding average recognition accuracy of FBACSP. The classification accuracy of the proposed method has reached 74.61 and 81.19% on datasets 2a and 2b, respectively. Compared with the baseline algorithm, filter bank common spatial pattern (FBCSP), the proposed algorithm improves by 11.44 and 7.11% on two datasets, respectively (p < 0.05).

Conclusion

It is demonstrated that FBACSP has a strong ability to decode MI-EEG. In addition, the analysis based on mutual information, t-SNE, and Shapley values further proves that ASP features have excellent decoding ability for MI-EEG signals and explains the improvement of classification performance by the introduction of ASP features. These findings may provide useful information to optimize EEG-based BCI systems and further improve the performance of non-invasive BCI.