1
|
Gao K, Nguyen DD, Tu M, Wei GW. Generative Network Complex for the Automated Generation of Drug-like Molecules. J Chem Inf Model 2020; 60:5682-5698. [PMID: 32686938 PMCID: PMC8142330 DOI: 10.1021/acs.jcim.0c00599] [Citation(s) in RCA: 72] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Abstract
Current drug discovery is expensive and time-consuming. It remains a challenging task to create a wide variety of novel compounds that not only have desirable pharmacological properties but also are cheaply available to low-income people. In this work, we develop a generative network complex (GNC) to generate new drug-like molecules based on the multiproperty optimization via the gradient descent in the latent space of an autoencoder. In our GNC, both multiple chemical properties and similarity scores are optimized to generate drug-like molecules with desired chemical properties. To further validate the reliability of the predictions, these molecules are reevaluated and screened by independent 2D fingerprint-based predictors to come up with a few hundreds of new drug candidates. As a demonstration, we apply our GNC to generate a large number of new BACE1 inhibitors, as well as thousands of novel alternative drug candidates for eight existing market drugs, including Ceritinib, Ribociclib, Acalabrutinib, Idelalisib, Dabrafenib, Macimorelin, Enzalutamide, and Panobinostat.
Collapse
Affiliation(s)
- Kaifu Gao
- Department of Mathematics, Michigan State University, East Lansing, Michigan 48824, United States
| | - Duc Duy Nguyen
- Department of Mathematics, Michigan State University, East Lansing, Michigan 48824, United States
| | - Meihua Tu
- Pfizer Medicine Design, 610 Main Street, Cambridge, Massachusetts 02139, United States
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, East Lansing, Michigan 48824, United States
- Department of Electrical and Computer Engineering, Michigan State University, East Lansing, Michigan 48824, United States
- Department of Biochemistry and Molecular Biology, Michigan State University, East Lansing, Michigan 48824, United States
| |
Collapse
|
2
|
Grow C, Gao K, Nguyen DD, Wei GW. Generative network complex (GNC) for drug discovery. COMMUNICATIONS IN INFORMATION AND SYSTEMS 2019; 19:241-277. [PMID: 34257523 PMCID: PMC8274326 DOI: 10.4310/cis.2019.v19.n3.a2] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
It remains a challenging task to generate a vast variety of novel compounds with desirable pharmacological properties. In this work, a generative network complex (GNC) is proposed as a new platform for designing novel compounds, predicting their physical and chemical properties, and selecting potential drug candidates that fulfill various druggable criteria such as binding affinity, solubility, partition coefficient, etc. We combine a SMILES string generator, which consists of an encoder, a drug-property controlled or regulated latent space, and a decoder, with verification deep neural networks, a target-specific three-dimensional (3D) pose generator, and mathematical deep learning networks to generate new compounds, predict their drug properties, construct 3D poses associated with target proteins, and reevaluate druggability, respectively. New compounds were generated in the latent space by either randomized output, controlled output, or optimized output. In our demonstration, 2.08 million and 2.8 million novel compounds are generated respectively for Cathepsin S and BACE targets. These new compounds are very different from the seeds and cover a larger chemical space. For potentially active compounds, their 3D poses are generated using a state-of-the-art method. The resulting 3D complexes are further evaluated for druggability by a championing deep learning algorithm based on algebraic topology, differential geometry, and algebraic graph theories. Performed on supercomputers, the whole process took less than one week. Therefore, our GNC is an efficient new paradigm for discovering new drug candidates.
Collapse
Affiliation(s)
- Christopher Grow
- Department of Mathematics, Michigan State University, East Lansing, MI 48824, USA
| | - Kaifu Gao
- Department of Mathematics, Michigan State University, East Lansing, MI 48824, USA
| | - Duc Duy Nguyen
- Department of Mathematics, Michigan State University, East Lansing, MI 48824, USA
| | - Guo-Wei Wei
- Department of Mathematics, Michigan State University, East Lansing, MI 48824, USA
| |
Collapse
|
3
|
Putin E, Asadulaev A, Ivanenkov Y, Aladinskiy V, Sanchez-Lengeling B, Aspuru-Guzik A, Zhavoronkov A. Reinforced Adversarial Neural Computer for de Novo Molecular Design. J Chem Inf Model 2018; 58:1194-1204. [PMID: 29762023 DOI: 10.1021/acs.jcim.7b00690] [Citation(s) in RCA: 174] [Impact Index Per Article: 29.0] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
Abstract
In silico modeling is a crucial milestone in modern drug design and development. Although computer-aided approaches in this field are well-studied, the application of deep learning methods in this research area is at the beginning. In this work, we present an original deep neural network (DNN) architecture named RANC (Reinforced Adversarial Neural Computer) for the de novo design of novel small-molecule organic structures based on the generative adversarial network (GAN) paradigm and reinforcement learning (RL). As a generator RANC uses a differentiable neural computer (DNC), a category of neural networks, with increased generation capabilities due to the addition of an explicit memory bank, which can mitigate common problems found in adversarial settings. The comparative results have shown that RANC trained on the SMILES string representation of the molecules outperforms its first DNN-based counterpart ORGANIC by several metrics relevant to drug discovery: the number of unique structures, passing medicinal chemistry filters (MCFs), Muegge criteria, and high QED scores. RANC is able to generate structures that match the distributions of the key chemical features/descriptors (e.g., MW, logP, TPSA) and lengths of the SMILES strings in the training data set. Therefore, RANC can be reasonably regarded as a promising starting point to develop novel molecules with activity against different biological targets or pathways. In addition, this approach allows scientists to save time and covers a broad chemical space populated with novel and diverse compounds.
Collapse
Affiliation(s)
- Evgeny Putin
- Pharma.AI Department , Insilico Medicine, Inc , Baltimore , Maryland 21218 , United States.,Computer Technologies Lab , ITMO University , St. Petersburg 197101 , Russia
| | - Arip Asadulaev
- Computer Technologies Lab , ITMO University , St. Petersburg 197101 , Russia
| | - Yan Ivanenkov
- Pharma.AI Department , Insilico Medicine, Inc , Baltimore , Maryland 21218 , United States.,Moscow Institute of Physics and Technology (State University) , 9 Institutskiy lane , Dolgoprudny City, Moscow Region , 141700 , Russian Federation.,Institute of Biochemistry and Genetics Russian Academy of Science (IBG RAS) , Ufa Scientific Centre, Oktyabrya Prospekt 71 , 450054 , Ufa , Russian Federation
| | - Vladimir Aladinskiy
- Pharma.AI Department , Insilico Medicine, Inc , Baltimore , Maryland 21218 , United States.,Moscow Institute of Physics and Technology (State University) , 9 Institutskiy lane , Dolgoprudny City, Moscow Region , 141700 , Russian Federation
| | - Benjamin Sanchez-Lengeling
- Chemistry and Chemical Biology Department , Harvard University , 12 Oxford Street , Cambridge , Massachusetts 02143 , United States
| | - Alán Aspuru-Guzik
- Chemistry and Chemical Biology Department , Harvard University , 12 Oxford Street , Cambridge , Massachusetts 02143 , United States.,Biologically-Inspired Solar Energy Program , Canadian Institute for Advanced Research (CIFAR) , Toronto , Ontario M5S 1M1 , Canada
| | - Alex Zhavoronkov
- Pharma.AI Department , Insilico Medicine, Inc , Baltimore , Maryland 21218 , United States.,The Buck Institute for Research on Aging , 8001 Redwood Boulevard , Novato , California 94945 , United States
| |
Collapse
|
4
|
Putin E, Asadulaev A, Vanhaelen Q, Ivanenkov Y, Aladinskaya AV, Aliper A, Zhavoronkov A. Adversarial Threshold Neural Computer for Molecular de Novo Design. Mol Pharm 2018; 15:4386-4397. [PMID: 29569445 DOI: 10.1021/acs.molpharmaceut.7b01137] [Citation(s) in RCA: 107] [Impact Index Per Article: 17.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022]
Abstract
In this article, we propose the deep neural network Adversarial Threshold Neural Computer (ATNC). The ATNC model is intended for the de novo design of novel small-molecule organic structures. The model is based on generative adversarial network architecture and reinforcement learning. ATNC uses a Differentiable Neural Computer as a generator and has a new specific block, called adversarial threshold (AT). AT acts as a filter between the agent (generator) and the environment (discriminator + objective reward functions). Furthermore, to generate more diverse molecules we introduce a new objective reward function named Internal Diversity Clustering (IDC). In this work, ATNC is tested and compared with the ORGANIC model. Both models were trained on the SMILES string representation of the molecules, using four objective functions (internal similarity, Muegge druglikeness filter, presence or absence of sp3-rich fragments, and IDC). The SMILES representations of 15K druglike molecules from the ChemDiv collection were used as a training data set. For the different functions, ATNC outperforms ORGANIC. Combined with the IDC, ATNC generates 72% of valid and 77% of unique SMILES strings, while ORGANIC generates only 7% of valid and 86% of unique SMILES strings. For each set of molecules generated by ATNC and ORGANIC, we analyzed distributions of four molecular descriptors (number of atoms, molecular weight, logP, and tpsa) and calculated five chemical statistical features (internal diversity, number of unique heterocycles, number of clusters, number of singletons, and number of compounds that have not been passed through medicinal chemistry filters). Analysis of key molecular descriptors and chemical statistical features demonstrated that the molecules generated by ATNC elicited better druglikeness properties. We also performed in vitro validation of the molecules generated by ATNC; results indicated that ATNC is an effective method for producing hit compounds.
Collapse
Affiliation(s)
- Evgeny Putin
- Pharma.AI Department , Insilico Medicine, Inc. , Baltimore , Maryland 21218 , United States.,Computer Technologies Lab , ITMO University , St. Petersburg 197101 , Russia
| | - Arip Asadulaev
- Computer Technologies Lab , ITMO University , St. Petersburg 197101 , Russia
| | - Quentin Vanhaelen
- Pharma.AI Department , Insilico Medicine, Inc. , Baltimore , Maryland 21218 , United States
| | - Yan Ivanenkov
- Pharma.AI Department , Insilico Medicine, Inc. , Baltimore , Maryland 21218 , United States.,Moscow Institute of Physics and Technology (State University) , 9 Institutskiy Lane , Dolgoprudny City , Moscow Region 141700 , Russian Federation.,Institute of Biochemistry and Genetics Russian Academy of Science (IBG RAS) Ufa Scientific Centre , Oktyabrya Prospekt 71 , 450054 Ufa , Russian Federation
| | - Anastasia V Aladinskaya
- Pharma.AI Department , Insilico Medicine, Inc. , Baltimore , Maryland 21218 , United States.,Moscow Institute of Physics and Technology (State University) , 9 Institutskiy Lane , Dolgoprudny City , Moscow Region 141700 , Russian Federation
| | - Alex Aliper
- Pharma.AI Department , Insilico Medicine, Inc. , Baltimore , Maryland 21218 , United States
| | - Alex Zhavoronkov
- Pharma.AI Department , Insilico Medicine, Inc. , Baltimore , Maryland 21218 , United States.,The Biogerontology Research Foundation , OX1 1RU Oxford , U.K
| |
Collapse
|
5
|
Corbi-Verge C, Kim PM. Motif mediated protein-protein interactions as drug targets. Cell Commun Signal 2016; 14:8. [PMID: 26936767 PMCID: PMC4776425 DOI: 10.1186/s12964-016-0131-4] [Citation(s) in RCA: 64] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2015] [Accepted: 02/25/2016] [Indexed: 12/17/2022] Open
Abstract
Protein-protein interactions (PPI) are involved in virtually every cellular process and thus represent an attractive target for therapeutic interventions. A significant number of protein interactions are frequently formed between globular domains and short linear peptide motifs (DMI). Targeting these DMIs has proven challenging and classical approaches to inhibiting such interactions with small molecules have had limited success. However, recent new approaches have led to the discovery of potent inhibitors, some of them, such as Obatoclax, ABT-199, AEG-40826 and SAH-p53-8 are likely to become approved drugs. These novel inhibitors belong to a wide range of different molecule classes, ranging from small molecules to peptidomimetics and biologicals. This article reviews the main reasons for limited success in targeting PPIs, discusses how successful approaches overcome these obstacles to discovery promising inhibitors for human protein double minute 2 (HDM2), B-cell lymphoma 2 (Bcl-2), X-linked inhibitor of apoptosis protein (XIAP), and provides a summary of the promising approaches currently in development that indicate the future potential of PPI inhibitors in drug discovery.
Collapse
Affiliation(s)
- Carles Corbi-Verge
- Terrence Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, ON, M5S 3E1, Canada.
| | - Philip M Kim
- Terrence Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, ON, M5S 3E1, Canada.
- Department of Molecular Genetics, University of Toronto, Toronto, ON, M5S 3E1, Canada.
- Department of Computer Science, University of Toronto, Toronto, ON, M5S 3E1, Canada.
| |
Collapse
|
6
|
Ivanenkov YA, Veselov MS, Chufarova NV, Majouga AG, Kudryavceva AA, Ivachtchenko AV. Non-dopamine receptor ligands for the treatment of Parkinson's disease. Insight into the related chemical/property space. Mol Divers 2015; 20:345-65. [PMID: 25956815 DOI: 10.1007/s11030-015-9598-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2014] [Accepted: 04/06/2015] [Indexed: 10/23/2022]
Abstract
Extensive biochemical and clinical studies have increasingly recognized Parkinson's disease as a highly complex and multi-faceted neurological disorder having branched non-motor symptoms including sleep disorders, pain, constipation, psychosis, depression, and fatigue. A wide range of biological targets in the brain deeply implicated in this pathology resulted in a plethora of novel small-molecule compounds with promising activity. This review thoroughly describes the chemical space of non-dopamine receptor ligands in terms of diversity, isosteric/bioisosteric morphing, and molecular descriptors.
Collapse
Affiliation(s)
- Yan A Ivanenkov
- Moscow Institute of Physics and Technology (State University), 9 Institutskiy Lane, Dolgoprudny, Moscow Region, 141700, Russian Federation. .,ChemDiv, 6605 Nancy Ridge Drive, San Diego, CA, 92121, USA. .,Chemistry Department, Moscow State University, Leninskie Gory, Building 1/3, Moscow, 119991, Russian Federation.
| | - Mark S Veselov
- Moscow Institute of Physics and Technology (State University), 9 Institutskiy Lane, Dolgoprudny, Moscow Region, 141700, Russian Federation.,Chemistry Department, Moscow State University, Leninskie Gory, Building 1/3, Moscow, 119991, Russian Federation.,National University of Science and Technology MISiS, 9 Leninskiy pr., Moscow, 119049, Russian Federation
| | - Nina V Chufarova
- Moscow Institute of Physics and Technology (State University), 9 Institutskiy Lane, Dolgoprudny, Moscow Region, 141700, Russian Federation.,National University of Science and Technology MISiS, 9 Leninskiy pr., Moscow, 119049, Russian Federation
| | - Alexander G Majouga
- Chemistry Department, Moscow State University, Leninskie Gory, Building 1/3, Moscow, 119991, Russian Federation.,National University of Science and Technology MISiS, 9 Leninskiy pr., Moscow, 119049, Russian Federation
| | - Anna A Kudryavceva
- Moscow Institute of Physics and Technology (State University), 9 Institutskiy Lane, Dolgoprudny, Moscow Region, 141700, Russian Federation
| | | |
Collapse
|
7
|
Sahin H, Berres ML, Wasmuth HE. Therapeutic potential of chemokine receptor antagonists for liver disease. Expert Rev Clin Pharmacol 2014; 4:503-13. [DOI: 10.1586/ecp.11.24] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/11/2022]
|
8
|
Tambov KV, Voevodina IV, Manaev AV, Ivanenkov YA, Neamati N, Traven VF. Structures and biological activity of cinnamoyl derivatives of coumarins and dehydroacetic acid and their boron difluoride complexes. Russ Chem Bull 2012. [DOI: 10.1007/s11172-012-0012-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/24/2023]
|
9
|
Fjell CD, Hiss JA, Hancock REW, Schneider G. Designing antimicrobial peptides: form follows function. Nat Rev Drug Discov 2011; 11:37-51. [PMID: 22173434 DOI: 10.1038/nrd3591] [Citation(s) in RCA: 1344] [Impact Index Per Article: 103.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Multidrug-resistant bacteria are a severe threat to public health. Conventional antibiotics are becoming increasingly ineffective as a result of resistance, and it is imperative to find new antibacterial strategies. Natural antimicrobials, known as host defence peptides or antimicrobial peptides, defend host organisms against microbes but most have modest direct antibiotic activity. Enhanced variants have been developed using straightforward design and optimization strategies and are being tested clinically. Here, we describe advanced computer-assisted design strategies that address the difficult problem of relating primary sequence to peptide structure, and are delivering more potent, cost-effective, broad-spectrum peptides as potential next-generation antibiotics.
Collapse
Affiliation(s)
- Christopher D Fjell
- Centre for Microbial Diseases and Immunity Research, University of British Columbia, 2259 Lower Mall, Vancouver, British Columbia V6T 1Z4, Canada
| | | | | | | |
Collapse
|
10
|
Abstract
This chapter provides a brief overview of chemoinformatics and its applications to chemical library design. It is meant to be a quick starter and to serve as an invitation to readers for more in-depth exploration of the field. The topics covered in this chapter are chemical representation, chemical data and data mining, molecular descriptors, chemical space and dimension reduction, quantitative structure-activity relationship, similarity, diversity, and multiobjective optimization.
Collapse
|
11
|
Jacoby E. Computational chemogenomics. WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE 2011. [DOI: 10.1002/wcms.11] [Citation(s) in RCA: 26] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
Affiliation(s)
- Edgar Jacoby
- Novartis Institutes for BioMedical Research, Center for Proteomic Chemistry, Forum 1, Novartis Campus, Basel, Switzerland
| |
Collapse
|