Activity and property prediction models are the central workhorses in drug discovery and materials sciences, but currently they have to be trained or fine-tuned for new tasks. Without training or fine-tuning, scientific language models could be used for such low-data tasks through their announced zero- and few-shot capabilities. However, their predictive quality at activity prediction is lacking. In this work, we envision a novel type of activity prediction model that is able to adapt to new prediction tasks at inference time, via understanding textual information describing the task. To this end, we propose a new architecture with separate modules for chemical and natural language inputs, and a contrastive pre-training objective on data from large biochemical databases. In extensive experiments, we show that our method CLAMP yields improved predictive performance on few-shot learning benchmarks and zero-shot problems in drug discovery. We attribute the advances of our method to the modularized architecture and to our pre-training objective.
DrugGen 2: A disease-aware language model for enhancing drug discovery
Regenerative Medicine Research Center（再生医学研究中心）；Isfahan University of Medical Sciences（伊斯法罕医科大学）；Isfahan Neuroscience Research Center（伊斯法罕神经科学研究中心）；School of Pharmacy（药学院）；Department of Medicinal Chemistry（药理化学系）；Cardiovascular Research Institute（心血管研究学院）；Department of Genetics and Molecular Biology（基因与分子生物学系）；Bioinformatics Research Center（生物信息学研究中心）
The first step in drug discovery is finding drug molecule moieties with medicinal activity against specific targets. Therefore, it is crucial to investigate the interaction between drug-target proteins and small chemical molecules. However, traditional experimental methods for discovering potential small drug molecules are labor-intensive and time-consuming. There is currently a lot of interest in building computational models to screen small drug molecules using drug molecule-related databases. In this paper, we propose a method for predicting drug-target binding affinity using deep learning …
In silico prediction of cardiotoxicity with high sensitivity and specificity for potential drug molecules can be of immense value. Hence, building machine learning classification models, based on some features extracted from the molecular structure of drugs, which are capable of efficiently predicting cardiotoxicity is critical. In this paper, we consider the application of various machine learning approaches, and then propose an ensemble classifier for the prediction of molecular activity on a Drug Discovery Hackathon (DDH) (1st reference) dataset. We have used only 2-D descriptors of SMILE n…
Self-supervised pre-training is gaining increasingly more popularity in AI-aided drug discovery, leading to more and more pre-trained models with the promise that they can extract better feature representations for molecules. Yet, the quality of learned representations have not been fully explored. In this work, inspired by the two phenomena of Activity Cliffs (ACs) and Scaffold Hopping (SH) in traditional Quantitative Structure-Activity Relationship (QSAR) analysis, we propose a method named Representation-Property Relationship Analysis (RePRA) to evaluate the quality of the representations e…
MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling
University of California San Diego（加利福尼亚大学圣迭戈分校）；Universidade Federal de Santa Catarina（圣卡塔琳娜联邦大学）；Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego（加利福尼亚大学圣迭戈分校斯卡格斯药学与制药科学学院）
MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning
Department of Computer Science and Engineering（计算机科学与工程系）；Department of Chemistry and Biochemistry（化学与生物化学系）；Skaggs School of Pharmacy and Pharmaceutical Sciences（斯卡格斯药学与药学科学学校）
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen University Health Science Center（深圳大学医学部）
The identification of protein-ligand interaction plays a key role in biochemical research and drug discovery. Although deep learning has recently shown great promise in discovering new drugs, there remains a gap between deep learning-based and experimental approaches. Here we propose a novel framework, named AIMEE, integrating AI Model and Enzymology Experiments, to identify inhibitors against 3CL protease of SARS-CoV-2, which has taken a significant toll on people across the globe. From a bioactive chemical library, we have conducted two rounds of experiments and identified six novel inhibito…
Virus infection is one of the major diseases that seriously threaten human health. To meet the growing demand for mining and sharing data resources related to antiviral drugs and to accelerate the design and discovery of new antiviral drugs, we presented an open-access antiviral drug resource and machine learning platform (VDDB), which, to the best of our knowledge, is the first comprehensive dedicated resource for experimentally verified potential drugs/molecules based on manually curated data. Currently, VDDB highlights 848 clinical vaccines, 199 clinical antibodies, as well as over 710,000 …
ByteDance AI Lab（字节跳动AI实验室）；University of Michigan（密歇根大学）；Montréal Institute of Learning Algorithms（蒙特利尔学习算法研究所）；Shanghai Jiao Tong University（上海交通大学）
Searching for novel molecules with desired chemical properties is crucial in drug discovery. Existing work focuses on developing neural models to generate either molecular sequences or chemical graphs. However, it remains a big challenge to find novel and diverse compounds satisfying several properties. In this paper, we propose MARS, a method for multi-objective drug molecule discovery. MARS is based on the idea of generating the chemical candidates by iteratively editing fragments of molecular graphs. To search for high-quality candidates, it employs Markov chain Monte Carlo sampling (MCMC) …
ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback
Mila-Québec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）；Arizona State University（亚利桑那州立大学）；Princeton University（普林斯顿大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Université de Montréal（蒙特利尔大学）；National Research Council Canada（加拿大国家研究委员会）
FusionDTI: Fine-grained Binding Discovery with Token-level Fusion for Drug-Target Interaction
School of Computing Science（计算科学学院）；School of Cancer Sciences（癌症科学学院）；Cancer Research UK Scotland Institute（英国癌症研究苏格兰研究所）；University of Glasgow（格拉斯哥大学）
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
Drug discovery is vitally important for protecting human against disease. Target-based screening is one of the most popular methods to develop new drugs in the past several decades. This method efficiently screens candidate drugs inhibiting target protein in vitro, but it often fails due to inadequate activity of the selected drugs in vivo. Accurate computational methods are needed to bridge this gap. Here, we propose a novel graph multi task deep learning model to identify compounds carrying both target inhibitory and cell active (MATIC) properties. On a carefully curated SARS-CoV-2 dataset, …
Latent Chemical Space Searching for Plug-in Multi-objective Molecule Generation
State Key Laboratory of Natural and Biomimetic Drugs, School of Pharmaceutical Sciences, Peking University（北京大学药学院天然药物及仿生药物国家重点实验室）；State Key Laboratory of Pharmaceutical Biotechnology, Nanjing University（南京大学医药生物技术国家重点实验室）
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）
European Molecular Biology Laboratory（欧洲分子生物学实验室）；European Bioinformatics Institute（欧洲生物信息研究所）；University of Cambridge（剑桥大学）
Estimating the reliability of individual predictions is key to increase the adoption of computational models and artificial intelligence in preclinical drug discovery, as well as to foster its application to guide decision making in clinical settings. Among the large number of algorithms developed over the last decades to compute prediction errors, Conformal Prediction (CP) has gained increasing attention in the computational drug discovery community. A major reason for its recent popularity is the ease of interpretation of the computed prediction errors in both classification and regression t…
AssayMatch: Learning to Select Data for Molecular Activity Models
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, 02139（计算机科学与人工智能实验室，麻省理工学院，剑桥，马萨诸塞州，02139）
SculptDrug : A Spatial Condition-Aware Bayesian Flow Model for Structure-based Drug Design
School of Data Science and Engineering, East China Normal University（东华大学数据科学与工程学院）；School of Chemistry and Molecular Engineering, East China Normal University（东华大学化学与分子工程学院）；School of Science, Engineering & Environment, University of Salford（萨尔福德大学科学、工程与环境学院）；Department of Computer Science, Aalborg University（奥胡斯大学计算机科学系）
By studying the literature about Tetracyclines (TCs), it becomes clearly evident that TCs are very dynamic molecules. In some cases, their structure-activity-relationship (SAR) are known, especially against bacteria, while against other targets, they are virtually unknown. In other diverse yields of research, such as neurology, oncology and virology the utility and activity of the tetracyclines are being discovered and are also emerging as new technological fronts. The first aim of this paper is classify the compounds already used in therapy and prepare the schematic structure in which include…
For fast development of COVID-19, it is only feasible to use drugs (off label use) or approved natural products that are already registered or been assessed for safety in previous human trials. These agents can be quickly assessed in COVID-19 patients, as their safety and pharmacokinetics should already be well understood. Computational methods offer promise for rapidly screening such products for potential SARS-CoV-2 activity by predicting and ranking the affinities of these compounds for specific virus protein targets. The RNA-dependent RNA polymerase (RdRP) is a promising target for SARS-Co…
DrugLLM: Open Large Language Model for Few-shot Molecule Generation
College of Computer Science, Sichuan University（四川大学计算机学院）；West China Hospital, Sichuan University（四川大学华西医院）；Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences（北京农林科学院信息技术研究中心）
Small molecules are often found to exhibit extraordinarily diverse biological activities. Metformin is one of them. It is widely used as anti-diabetic drug for type-two diabetes. In addition to that, metformin hydrochloride shows anti-tumour activities and increases the survival rate of patients suffering from certain types of cancer namely colorectal, breast, pancreas and prostate cancer. However, theoretical studies of structure and dynamics of metformin have not yet been fully explored. In this work, we investigate the characteristic structural and dynamical features of three mono-protonate…
Activity cliffs (ACs), which are generally defined as pairs of structurally similar molecules that are active against the same bio-target but significantly different in the binding potency, are of great importance to drug discovery. Up to date, the AC prediction problem, i.e., to predict whether a pair of molecules exhibit the AC relationship, has not yet been fully explored. In this paper, we first introduce ACNet, a large-scale dataset for AC prediction. ACNet curates over 400K Matched Molecular Pairs (MMPs) against 190 targets, including over 20K MMP-cliffs and 380K non-AC MMPs, and provide…
Drug-target interaction (DTI) prediction plays a crucial role in drug discovery, and deep learning approaches have achieved state-of-the-art performance in this field. We introduce an ensemble of deep learning models (EnsembleDLM) for DTI prediction. EnsembleDLM only uses the sequence information of chemical compounds and proteins, and it aggregates the predictions from multiple deep neural networks. This approach not only achieves state-of-the-art performance in Davis and KIBA datasets but also reaches cutting-edge performance in the cross-domain applications across different bio-activity typ…
Structure-Based Drug Design via 3D Molecular Generative Pre-training and Sampling
ByteDance Research（字节跳动研究院）；Carnegie Mellon University（卡内基梅隆大学）；Guanghua Law School（光华法学院）；Zhejiang University（浙江大学）；Shanghai Institute of Materia Medica（上海药物研究所）；Chinese Academy of Sciences（中国科学院）；Institute of AI Industrial Research（人工智能产业研究院）；Tsinghua University（清华大学）
Kinase-targeted drug design is challenging. It requires designing inhibitors that can bind to specific kinases when all kinase catalytic domains share a common folding scaffold that binds ATP. Thus, obtaining the desired selectivity, given the whole human kinome, is a fundamental task during early-stage drug discovery. This begins with deciphering the kinase-ligand characteristics, analyzing the structure-activity relationships, and prioritizing the desired drug molecules across the whole kinome. Currently, there are more than 300 kinases with released PDB structures, which provides a substant…
GALUX inc.（GALUX公司）；Seoul National University（首尔国立大学）
In drug discovery, aqueous solubility is an important pharmacokinetic property which affects absorption and assay availability of drug. Thus, 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 like quantum mechanics and molecular dynamics are not suitable for high-throughput tasks due to its computational costs. However, ML method can exhibit over-fitting problem in a data-deficient condition, and this is the case for most c…
New York University（纽约大学）；Colton Center for Autoimmunity（科尔顿自身免疫中心）；NYU Grossman School of Medicine（纽约大学格罗斯曼医学院）
Rheumatoid arthritis (RA) is an autoimmune condition caused when patients' immune system mistakenly targets their own tissue. Machine learning (ML) has the potential to identify patterns in patient electronic health records (EHR) to forecast the best clinical treatment to improve patient outcomes. This study introduced a Drug Response Prediction (DRP) framework with two main goals: 1) design a data processing pipeline to extract information from tabular clinical data, and then preprocess it for functional use, and 2) predict RA patient's responses to drugs and evaluate classification models' p…
The Coronavirus Disease (COVID-19) pandemic caused by the SARS-coronavirus 2 (SARS-CoV-2) urgently calls for the design of drugs directed against this new virus. Given its essential role in proteolytic processing, the main protease Mpro has been identified as an attractive candidate for drugs against SARS-CoV-2 and similar coronaviruses. Recent high-throughput screening studies have identified a set of existing, small-molecule drugs as potent Mpro inhibitors. Amongst these, Ebselen (2-Phenyl-1,2-benzoselenazol-3-one), a glutathione peroxidase mimetic seleno-organic compound, is particularly at…
Since the epidemic began in November 2019, no viable medicine against SARS-CoV-2 has been discovered. The typical medication discovery strategy requires several years of rigorous research and development as well as a significant financial commitment, which is not feasible in the face of the current epidemic. Through molecular docking and dynamic simulation studies, we used the FDA-approved drug mezonavir against the most important viral targets, including spike (S) glycoprotein, Transmembrane serine protease 2 (TMPRSS2), RNA-dependent RNA polymerase (RdRp), Main protease (Mpro), human angioten…
Structure-Aware Contrastive Learning with Fine-Grained Binding Representations for Drug Discovery
Department of Health Technology and Informatics, The Hong Kong Polytechnic University（健康科技与信息学系，香港理工大学）；Department of Nuclear Medicine and PET, Hong Kong Sanatorium and Hospital（核医学与PET部，香港疗养院及医院）；Nuclear Medicine Unit, Department of Diagnostic and Interventional Radiology, Queen Elizabeth Hospital（核医学科，诊断与介入放射科，伊丽莎白女王医院）
In the drug repurposing approach, the chemically diverse and potentially safe molecules can be explored as therapeutic potential out of those originally targeted indications. However, the intellectual property rights, and competitive over-heating issue from sharing the same drug pipeline information are drawback of the approach. In current paradigm of drug discovery, despite approval of new chemical entity, the finding of a new ring system for drug discovery have stagnated. In addition, there are still rarely used ring systems from FDA approved drug that can be optimized and used for repurposi…
AMPCliff: quantitative definition and benchmarking of activity cliffs in antimicrobial peptides
Jilin University（吉林大学）；Columbia University（哥伦比亚大学）；Guizhou Medical University（贵州医科大学）；Changchun University of Engineering（长春工程学院）；Changchun Wenli High School（长春文理高级中学）
Exploring Drug Safety Through Knowledge Graphs: Protein Kinase Inhibitors as a Case Study
David Jackson Institute of Informatics University of Amsterdam（大卫·杰克逊信息学研究所 阿姆斯特丹大学）；Michael Gertz Institute of Computer Science Heidelberg University（迈克尔·格茨计算机科学研究所海德堡大学）；Jürgen Hesser Data Analysis and Modeling in Medicine Mannheim Institute for Intelligent Systems in Medicine (MIISM) Medical Faculty Mannheim, Heidelberg University（朱尔根·赫瑟医学数据分析与建模 马尔姆研究所（MIISM）海德堡大学医学系）
Bacteria produce a range of proteolytic enzymes, for which a number human equivalent or structurally similar examples exist and the primary focus of this study was to analyse the published literature to find proteolytic enzymes, specifically endoproteses and to examine the similarity in the substrates that they act on so as to predict a suitable structural motif which can be used as the basis for preparation of useful prodrug carriers against diseases caused by specific bacteria like Salmonella. Also, the similarities between the bacterial proteases and the action of human matrix metalloprotei…
The steep climbing of victims caused by the new coronavirus disease 2019 (COVID-19) throughout the planet is sparking an unprecedented effort to identify effective therapeutic regimens to tackle the pandemic. The SARS-CoV-2 virus is known to gain entry into various cell types through the binding of one of its surface proteins (spike) to the host Angiotensin-Converting Enzyme 2 (ACE2). Thus, spike-ACE2 interaction represents a major target for vaccines and antiviral drugs. A novel method has been recently described by some of the authors to pharmacologically downregulate the expression of targe…
