Language models hold incredible promise for enabling scientific discovery by synthesizing massive research corpora. Many complex scientific research questions have multiple plausible answers, each supported by evidence of varying strength. However, existing language models lack the capability to quantitatively and faithfully compare answer plausibility in terms of supporting evidence. To address this, we introduce Retrieve to Explain (R2E), a retrieval-based model that scores and ranks all possible answers to a research question based on evidence retrieved from a document corpus. The architecture represents each answer only in terms of its supporting evidence, with the answer itself masked. This allows us to extend feature attribution methods such as Shapley values, to transparently attribute answer scores to supporting evidence at inference time. The architecture also allows incorporation of new evidence without retraining, including non-textual data modalities templated into natural language. We developed R2E for the challenging scientific discovery task of drug target identification, a human-in-the-loop process where failures are extremely costly and explainability paramount. When predicting whether drug targets will subsequently be confirmed as efficacious in clinical trials, R2E not only matches non-explainable literature-based models but also surpasses a genetics-based target identification approach used throughout the pharmaceutical industry.
Deep learning bears promise for drug discovery, including advanced image analysis, prediction of molecular structure and function, and automated generation of innovative chemical entities with bespoke properties. Despite the growing number of successful prospective applications, the underlying mathematical models often remain elusive to interpretation by the human mind. There is a demand for 'explainable' deep learning methods to address the need for a new narrative of the machine language of the molecular sciences. This review summarizes the most prominent algorithmic concepts of explainable …
Building explainable graph neural network by sparse learning for the drug-protein binding prediction
Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington（印第安纳大学伯明顿分校勒迪信息学、计算与工程学院）；School of Medicine, Indiana University（印第安纳大学医学院）
Drug repositioning holds great promise because it can reduce the time and cost of new drug development. While drug repositioning can omit various R&D processes, confirming pharmacological effects on biomolecules is essential for application to new diseases. Biomedical explainability in a drug repositioning model can support appropriate insights in subsequent in-depth studies. However, the validity of the XAI methodology is still under debate, and the effectiveness of XAI in drug repositioning prediction applications remains unclear. In this study, we propose GraphIX, an explainable drug reposi…
Advances in machine learning have led to graph neural network-based methods for drug discovery, yielding promising results in molecular design, chemical synthesis planning, and molecular property prediction. However, current graph neural networks (GNNs) remain of limited acceptance in drug discovery is limited due to their lack of interpretability. Although this major weakness has been mitigated by the development of explainable artificial intelligence (XAI) techniques, the "ground truth" assignment in most explainable tasks ultimately rests with subjective judgments by humans so that the qual…
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学及其应用实验室）；Orange Labs（奥兰治实验室）；LIMICS（LIMICS实验室）；Inserm（法国国家健康与医学研究院）；Université Sorbonne Paris Nord（索邦巴黎北大学）；Sorbonne Université（索邦大学）；CHU de St Etienne（圣艾蒂安大学附属医院）；NGERE（NGERE实验室）；Centre Régional de Pharmacovigilance（区域药物警戒中心）；CHRU de Nancy（南锡大学区域医院中心）；Inria Paris（法国国家信息与自动化研究所巴黎中心）；Université de Paris（巴黎大学）
Adverse Drug Reactions (ADRs) are characterized within randomized clinical trials and postmarketing pharmacovigilance, but their molecular mechanism remains unknown in most cases. Aside from clinical trials, many elements of knowledge about drug ingredients are available in open-access knowledge graphs. In addition, drug classifications that label drugs as either causative or not for several ADRs, have been established. We propose to mine knowledge graphs for identifying biomolecular features that may enable reproducing automatically expert classifications that distinguish drug causative or no…
University of Western Australia（西澳大学）；Fiona Stanley Hospital（菲奥娜·斯坦利医院）；Harry Perkins Institute of Medical Research（哈里·珀金斯医学研究所）
Explainable Artificial Intelligence (XAI) has been identified as a viable method for determining the importance of features when making predictions using Machine Learning (ML) models. In this study, we created models that take an individual's health information (e.g. their drug history and comorbidities) as inputs, and predict the probability that the individual will have an Acute Coronary Syndrome (ACS) adverse outcome. Using XAI, we quantified the contribution that specific drugs had on these ACS predictions, thus creating an XAI-based technique for pharmacovigilance monitoring, using ACS as…
Navigating Healthcare Insights: A Birds Eye View of Explainability with Knowledge Graphs
Hajim School of Engineering and Applied Sciences, University of Rochester（罗切斯特大学哈吉米工程与应用科学学院）；College of Engineering and Applied Sciences, University at Albany, State University of New York（纽约州立大学奥尔巴尼分校工程与应用科学学院）；Deloitte LLC（德勤有限责任公司）
IBM Research Zurich（IBM苏黎世研究院）；ETH Zurich（苏黎世联邦理工学院）；University of Zurich（苏黎世大学）；RWTH Aachen University（亚琛工业大学）；Heidelberg University（海德堡大学）
In line with recent advances in neural drug design and sensitivity prediction, we propose a novel architecture for interpretable prediction of anticancer compound sensitivity using a multimodal attention-based convolutional encoder. Our model is based on the three key pillars of drug sensitivity: compounds' structure in the form of a SMILES sequence, gene expression profiles of tumors and prior knowledge on intracellular interactions from protein-protein interaction networks. We demonstrate that our multiscale convolutional attention-based (MCA) encoder significantly outperforms a baseline mod…
University of Michigan（密歇根大学）；University of California San Francisco（加利福尼亚大学旧金山分校）
In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast, humans learn language by grounding concepts in perception and action and the brain encodes grounded semantics for cognition. Inspired by this notion and recent work in vision-language learning, we design a two-stream model for grounding language learning in vision. The model includes a VGG-based visual stream and a Bert-based language stream. The two stream…
RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation
Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东省计算机科学中心（国家济南超级计算中心））；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））；Shandong Fundamental Research Center for Computer Science（山东省计算机科学基础研究中心）；University of Technology Sydney（悉尼科技大学）
Assay2Mol: large language model-based drug design using BioAssay context
Department of Computer Sciences, University of Wisconsin-Madison（威斯康星大学麦迪逊分校计算机科学系）；Morgridge Institute for Research（摩尔格德研究所）；Drug Development Core, Small Molecule Screening Facility, University of Wisconsin Carbone Cancer Center, University of Wisconsin-Madison（威斯康星大学卡本癌症中心药物开发核心、小分子筛选设施）；Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison（威斯康星大学麦迪逊分校生物统计学与医学信息学系）
Predictive Modeling and Explainable AI for Veterinary Safety Profiles, Residue Assessment, and Health Outcomes Using Real-World Data and Physicochemical Properties
DATA Consortium and FARAD Program, Kansas State University, Olathe, KS, USA（1DATA Consortium和FARAD计划，堪萨斯州立大学）；Department of Computer Science, Kansas State University, Manhattan, KS, USA（计算机科学系，堪萨斯州立大学）；Department of Statistics, Kansas State University, Manhattan, KS, USA（统计学系，堪萨斯州立大学）；Department of Mathematics, Kansas State University, Olathe, KS, USA（数学系，堪萨斯州立大学）
Applied Artificial Intelligence Institute, Deakin University（迪肯大学应用人工智能研究所）；Deakin University（迪肯大学）
Motivation: Many high-performance DTA models have been proposed, but they are mostly black-box and thus lack human interpretability. Explainable AI (XAI) can make DTA models more trustworthy, and can also enable scientists to distill biological knowledge from the models. Counterfactual explanation is one popular approach to explaining the behaviour of a deep neural network, which works by systematically answering the question "How would the model output change if the inputs were changed in this way?". Most counterfactual explanation methods only operate on single input data. It remains an open…
Department of Electrical；Computer Engineering, Texas A\&M University, College Station, TX 77843, United States；Department of Computer Science；Engineering, Texas A\&M University, College Station, TX 77843, United States
Predicting compound-protein affinity is critical for accelerating drug discovery. Recent progress made by machine learning focuses on accuracy but leaves much to be desired for interpretability. Through molecular contacts underlying affinities, our large-scale interpretability assessment finds commonly-used attention mechanisms inadequate. We thus formulate a hierarchical multi-objective learning problem whose predicted contacts form the basis for predicted affinities. We further design a physics-inspired deep relational network, DeepRelations, with intrinsically explainable architecture. Spec…
DrugAgent: Reliable Multi-Agent Integration of Conflicting Biomedical Evidence for Drug-Target Interaction Assessment
Department of Computer Science and Engineering, University of Minnesota（计算机科学与工程系，明尼苏达大学）；Computational Biology Branch, National Library of Medicine（国家医学图书馆计算生物学分支）；Khoury College of Computer Sciences, Northeastern University（东北大学计算机科学学院）；State Key Laboratory for Novel Software Technology at Nanjing University, School of Computer Science, Nanjing University（南京大学新型软件技术国家重点实验室，南京大学计算机科学学院）；Developmental Therapeutics Branch, National Cancer Institute（国家癌症研究所发育治疗分支）
Large Language Model Agent for Modular Task Execution in Drug Discovery
Department of Chemical Engineering, Carnegie Mellon University（化学工程系，卡内基梅隆大学）；Department of Material Science and Engineering, Carnegie Mellon University（材料科学与工程系，卡内基梅隆大学）；Department of Mechanical Engineering, Carnegie Mellon University（机械工程系，卡内基梅隆大学）
DPD-Cancer: Explainable Graph-based Deep Learning for Small Molecule Anti-Cancer Activity Prediction
The Australian Centre for Ecogenomics, School of Chemistry and Molecular Biosciences, The University of Queensland（澳大利亚生态基因组学中心，化学与分子生物科学学院，昆士兰大学）；Computational Biology and Clinical Informatics, Baker Heart and Diabetes Institute（计算生物学与临床信息学，贝克心脏与糖尿病研究所）
Chongqing University of Posts and Telecommunications（重庆邮电大学）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）；Paris-Saclay University（巴黎萨克雷大学）；CentraleSupélec（巴黎中央理工-高等电力学院）；Inria（法国国家信息与自动化研究所）
The discovery of drug-target interactions (DTIs) is a very promising area of research with great potential. The accurate identification of reliable interactions among drugs and proteins via computational methods, which typically leverage heterogeneous information retrieved from diverse data sources, can boost the development of effective pharmaceuticals. Although random walk and matrix factorization techniques are widely used in DTI prediction, they have several limitations. Random walk-based embedding generation is usually conducted in an unsupervised manner, while the linear similarity combi…
Technical University of Munich（慕尼黑工业大学）；University of Alberta（阿尔伯塔大学）
Drug-mediated blockade of the voltage-gated potassium channel(hERG) and the voltage-gated sodium channel (Nav1.5) can lead to severe cardiovascular complications. This rising concern has been reflected in the drug development arena, as the frequent emergence of cardiotoxicity from many approved drugs led to either discontinuing their use or, in some cases, their withdrawal from the market. Predicting potential hERG and Nav1.5 blockers at the outset of the drug discovery process can resolve this problem and can, therefore, decrease the time and expensive cost of developing safe drugs. One fast …
Explainable Molecular Property Prediction: Aligning Chemical Concepts with Predictions via Language Models
Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学）；Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University（数据科学与人工智能系，香港理工大学）；Department of Computing and Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University（计算系和数据科学与人工智能系，香港理工大学）；Department of Applied Physics, The Hong Kong Polytechnic University（应用物理系，香港理工大学）；Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR)（高性能计算研究所，科技研究局（A*STAR））
Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization
Department of Biostatistics & Health Data Science（生物统计学与健康数据科学系）；Indiana University（印第安纳大学）；Department of Computer Science（计算机科学系）；Indiana University Bloomington（印第安纳大学布卢明顿分校）；Division of Clinical Pharmacology（临床药理学部）；Indiana University School of Medicine（印第安纳大学医学院）；IUSM-Purdue TREAT-AD Center（IUSM-普渡大学TREAT-AD中心）；Department of Medical and Molecular Genetics（医学与分子遗传学系）
Contextual Representation Anchor Network to Alleviate Selection Bias in Few-Shot Drug Discovery
College of computer science and technology, Zhejiang University（浙江大学计算机科学与技术学院）；Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；Zhejiang Lab（之江实验室）；ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙江大学杭州国际科技创新中心）；Antai College of Economics and Management, Shanghai Jiao Tong University（上海交通大学安泰经济与管理学院）
Fraunhofer Institute for Applied Information Technology FIT（弗劳恩霍夫应用信息技术研究所FIT）；RWTH Aachen University（亚琛工业大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
The discovery of important biomarkers is a significant step towards understanding the molecular mechanisms of carcinogenesis; enabling accurate diagnosis for, and prognosis of, a certain cancer type. Before recommending any diagnosis, genomics data such as gene expressions(GE) and clinical outcomes need to be analyzed. However, complex nature, high dimensionality, and heterogeneity in genomics data make the overall analysis challenging. Convolutional neural networks(CNN) have shown tremendous success in solving such problems. However, neural network models are perceived mostly as `black box' m…
Protein Language Model-Powered 3D Ligand Binding Site Prediction from Protein Sequence
Hunter College, City University of New York（纽约市立大学亨特学院）；Weill Cornell Medicine, Cornell University（康奈尔大学威尔康奈尔医学院）；Graduate Center, City University of New York（纽约市立大学研究生中心）
