The discovery of peptides having high biological activity is very challenging mainly because there is an enormous diversity of compounds and only a minority have the desired properties. To lower cost and reduce the time to obtain promising compounds, machine learning approaches can greatly assist in the process and even replace expensive laboratory experiments by learning a predictor with existing data. Unfortunately, selecting ligands having the greatest predicted bioactivity requires a prohibitive amount of computational time. For this combinatorial problem, heuristics and stochastic optimization methods are not guaranteed to find adequate compounds.
We propose an efficient algorithm based on De Bruijn graphs, guaranteed to find the peptides of maximal predicted bioactivity. We demonstrate how this algorithm can be part of an iterative combinatorial chemistry procedure to speed up the discovery and the validation of peptide leads. Moreover, the proposed approach does not require the use of known ligands for the target protein since it can leverage recent multi-target machine learning predictors where ligands for similar targets can serve as initial training data. Finally, we validated the proposed approach in vitro with the discovery of new cationic anti-microbial peptides.
Source code is freely available at http://graal.ift.ulaval.ca/peptide-design/.
Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides
Xinjiang Key Laboratory of Biological Resources and Genetic Engineering（新疆生物资源与基因工程重点实验室）；College of Life Science and Technology, Xinjiang University（新疆大学生命科学与技术学院）；School of Mathematics and System Sciences, Xinjiang University（新疆大学数学与系统科学学院）
Integrated omics reveals actionable drivers of bioactive variation in US milk
University of California, Davis（加州大学戴维斯分校）；USDA/NSF AI Institute for Next Generation Food Systems (AIFS)（美国农业部/国家科学基金会人工智能下一代食品系统研究所）；Innovation Institute for Food and Health（食品与健康创新研究所）；Process Integration and Predictive Analytics, PIPA LLC（流程整合与预测分析，PIPA有限责任公司）；USDA ARS Western Human Nutrition Research Center（美国农业部农业研究局西方人类营养研究中心）；Graduate School of Agricultural Science, Tohoku University（东北大学农学研究科）
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）
BioChemInsight: An Online Platform for Automated Extraction of Chemical Structures and Activity Data from Patents
Zhejiang University（浙江大学）；Huadong Medicine Co., Ltd.（华东医药股份有限公司）；Hangzhou VicrobX Biotech Co., Ltd.（杭州维康信生物科技有限公司）；Shanghai University（上海大学）；ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙江大学杭州国际科创中心）；Jiangxi University of Chinese Medicine（江西中医药大学）；Second Military Medical University（第二军医大学）
Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3
University of Vermont（弗吉尼亚大学）；Larner College of Medicine, University of Vermont（弗吉尼亚大学医学学院）；Purdue University（普渡大学）；Department of Comparative Pathobiology（比较病理科部门）；Department of Horticulture and Landscape Architecture（园艺与景观建筑部门）；Department of Industrial and Molecular Pharmaceutics（工业与分子药学部门）
Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics
IBM Thomas J Watson Research Center（IBM托马斯·J·沃森研究中心）；Harvard John A. Paulson School of Engineering and Applied Sciences（哈佛大学约翰·A·保尔森工程与应用科学学院）；IBM Research Europe（IBM欧洲研究院）；STFC Laboratory（科学与技术设施委员会实验室）；IBM Research（IBM研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Institute of Bioengineering and Nanotechnology（生物工程与纳米技术研究所）；IBM Research, Almaden Research Center（IBM阿尔马登研究院）；Department of Applied Physics and Mathematics, Columbia University（哥伦比亚大学应用物理与数学系）；Department of Biochemistry, University of Oxford（牛津大学生物化学系）
