Deep Learning in Drug Discovery and Medicine; Scratching the Surface

Dibyendu Dana; Satishkumar Gadhiya; Luce St. Surin; David Li; Farha Naaz; Quaisar Ali; Latha Paka; Michael Yamin; Mahesh Narayan; Itzhak Goldberg; Prakash Narayan

doi:10.3390/molecules23092384

Deep Learning in Drug Discovery and Medicine; Scratching the Surface

Molecules ◽

10.3390/molecules23092384 ◽

2018 ◽

Vol 23 (9) ◽

pp. 2384 ◽

Cited By ~ 19

Author(s):

Dibyendu Dana ◽

Satishkumar Gadhiya ◽

Luce St. Surin ◽

David Li ◽

Farha Naaz ◽

...

Keyword(s):

Drug Discovery ◽

Precision Medicine ◽

A Priori ◽

Treatment Strategies ◽

Molecular Therapy ◽

Molecular Profile ◽

Drug Candidates ◽

Practice Of Medicine ◽

New Chemical Entities ◽

Novel Drug

The practice of medicine is ever evolving. Diagnosing disease, which is often the first step in a cure, has seen a sea change from the discerning hands of the neighborhood physician to the use of sophisticated machines to use of information gleaned from biomarkers obtained by the most minimally invasive of means. The last 100 or so years have borne witness to the enormous success story of allopathy, a practice that found favor over earlier practices of medical purgatory and homeopathy. Nevertheless, failures of this approach coupled with the omics and bioinformatics revolution spurred precision medicine, a platform wherein the molecular profile of an individual patient drives the selection of therapy. Indeed, precision medicine-based therapies that first found their place in oncology are rapidly finding uses in autoimmune, renal and other diseases. More recently a new renaissance that is shaping everyday life is making its way into healthcare. Drug discovery and medicine that started with Ayurveda in India are now benefiting from an altogether different artificial intelligence (AI)—one which is automating the invention of new chemical entities and the mining of large databases in health-privacy-protected vaults. Indeed, disciplines as diverse as language, neurophysiology, chemistry, toxicology, biostatistics, medicine and computing have come together to harness algorithms based on transfer learning and recurrent neural networks to design novel drug candidates, a priori inform on their safety, metabolism and clearance, and engineer their delivery but only on demand, all the while cataloging and comparing omics signatures across traditionally classified diseases to enable basket treatment strategies. This review highlights inroads made and being made in directed-drug design and molecular therapy.

Download Full-text

Machine Learning Methods in Drug Discovery

Molecules ◽

10.3390/molecules25225277 ◽

2020 ◽

Vol 25 (22) ◽

pp. 5277

Author(s):

Lauv Patel ◽

Tripti Shukla ◽

Xiuzhen Huang ◽

David W. Ussery ◽

Shanzhi Wang

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Drug Discovery ◽

High Throughput Screening ◽

Drug Targets ◽

Learning Algorithms ◽

Machine Learning Techniques ◽

Online Information ◽

Drug Candidates ◽

Novel Drug

The advancements of information technology and related processing techniques have created a fertile base for progress in many scientific fields and industries. In the fields of drug discovery and development, machine learning techniques have been used for the development of novel drug candidates. The methods for designing drug targets and novel drug discovery now routinely combine machine learning and deep learning algorithms to enhance the efficiency, efficacy, and quality of developed outputs. The generation and incorporation of big data, through technologies such as high-throughput screening and high through-put computational analysis of databases used for both lead and target discovery, has increased the reliability of the machine learning and deep learning incorporated techniques. The use of these virtual screening and encompassing online information has also been highlighted in developing lead synthesis pathways. In this review, machine learning and deep learning algorithms utilized in drug discovery and associated techniques will be discussed. The applications that produce promising results and methods will be reviewed.

Download Full-text

Precision medicine in colorectal cancer: the molecular profile alters treatment strategies

Therapeutic Advances in Medical Oncology ◽

10.1177/1758834015591952 ◽

2015 ◽

Vol 7 (5) ◽

pp. 252-262 ◽

Cited By ~ 41

Author(s):

Nguyen H. Tran ◽

Ludmila L. Cavalcante ◽

Sam J. Lubner ◽

Daniel L. Mulkerin ◽

Noelle K. LoConte ◽

...

Keyword(s):

Colorectal Cancer ◽

Precision Medicine ◽

Treatment Strategies ◽

Molecular Profile

Download Full-text

Functional patient-derived cellular models for neuropsychiatric drug discovery

Translational Psychiatry ◽

10.1038/s41398-021-01243-8 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Santiago G. Lago ◽

Jakub Tomasik ◽

Sabine Bahn

Keyword(s):

Drug Discovery ◽

Mononuclear Cells ◽

Induced Pluripotent Stem Cell ◽

Functional Responses ◽

Peripheral Blood Mononuclear ◽

Disease Heterogeneity ◽

Drug Candidates ◽

Cellular Models ◽

Novel Strategy ◽

Novel Drug

AbstractMental health disorders are a leading cause of disability worldwide. Challenges such as disease heterogeneity, incomplete characterization of the targets of existing drugs and a limited understanding of functional interactions of complex genetic risk loci and environmental factors have compromised the identification of novel drug candidates. There is a pressing clinical need for drugs with new mechanisms of action which address the lack of efficacy and debilitating side effects of current medications. Here we discuss a novel strategy for neuropsychiatric drug discovery which aims to address these limitations by identifying disease-related functional responses (‘functional cellular endophenotypes’) in a variety of patient-derived cells, such as induced pluripotent stem cell (iPSC)-derived neurons and organoids or peripheral blood mononuclear cells (PBMCs). Disease-specific alterations in cellular responses can subsequently yield novel drug screening targets and drug candidates. We discuss the potential of this approach in the context of recent advances in patient-derived cellular models, high-content single-cell screening of cellular networks and changes in the diagnostic framework of neuropsychiatric disorders.

Download Full-text

A phenotypic screening platform utilising human spermatozoa identifies new compounds with contraceptive activity

10.1101/808105 ◽

2019 ◽

Author(s):

Franz Gruber ◽

Christopher L.R. Barratt ◽

Paul D. Andrews

Keyword(s):

Drug Discovery ◽

Target Identification ◽

Human Sperm ◽

Phenotypic Screening ◽

Major Barrier ◽

Drug Candidates ◽

Critical Gap ◽

Comprehensive Collection ◽

Screening Platform ◽

Novel Drug

AbstractThere is an urgent need to develop new methods for male contraception, however a major barrier to drug discovery has been the lack of validated targets and the absence of an effective high-throughput phenotypic screening system. To address this deficit, we developed a fully-automated robotic screening platform that provided quantitative evaluation of compound activity against two key attributes of human sperm function: motility and acrosome reaction. In order to accelerate contraceptive development, we screened the comprehensive collection of 12,000 molecules that make up the ReFRAME repurposing library, comprising nearly all the small molecules that have been approved or have undergone clinical development, or have significant preclinical profiling. We identified several compounds that potently inhibit motility representing either novel drug candidates or routes to target identification. This platform will now allow for major drug discovery programmes that address the critical gap in the contraceptive portfolio as well as uncover novel human sperm biology.

Download Full-text

Drug Targeting approaches and use of Drug Delivery systems in management of Cancer

Current Pharmaceutical Design ◽

10.2174/1381612827666210728105017 ◽

2021 ◽

Vol 27 ◽

Author(s):

Alka Ahuja ◽

Gurpreet K. Narde ◽

Nida Mohammed Ali Wadi ◽

Dhanalekshmi Unnikrishnan Meenakshi

Keyword(s):

Drug Delivery ◽

Precision Medicine ◽

Scientific Evidence ◽

Treatment Strategies ◽

Multi Drug Resistance ◽

Individual Treatment ◽

Treatment Needs ◽

Advantages And Disadvantages ◽

Novel Drug ◽

Methods Of Treatment

: Mutations and their manifestations in the form of various diseases and disorders result in Cancer which is a major cause of human death worldwide. A considerable amount of information is available at the cellular, molecular and genetic level about the occurrence and spread of the precarious cancer and yet there is no cure. The traditional methods of treatment such as chemotherapy, radiotherapy and surgical intervention have shown to be moderately effective and keep some types of cancer under control but each modality has its own advantages and disadvantages. In recent years, more advanced methods such as targeted therapies, immunotherapy, and precision medicine are shown to be promising and these fields continue to expand rapidly along with the conventional methods. This review focuses on the reports of advanced methods of treatment from a scientific standpoint to recognize many new and modern approaches. Selective targeting of the tumour cells by nanoparticle based novel drug delivery approaches, includes latest innovations in their preparation strategies and applications. The concept of precision medicine and its impact on treatment are highlighted here with a hope of individualised therapy with minimum side effects as a part of ever-expanding treatment strategies. Additional challenges related to cancer treatment like multi-drug resistance and toxicity are also deliberated in brief. Based on the available reports and scientific evidence, better targeted approaches with better quality clinical outcomes and more precise drug delivery to fit individual treatment needs are anticipated in the near future to control this deadly disease.

Download Full-text

A Network-Based Cancer Drug Discovery: From Integrated Multi-Omics Approaches to Precision Medicine

Current Pharmaceutical Design ◽

10.2174/1381612824666181106095959 ◽

2019 ◽

Vol 24 (32) ◽

pp. 3778-3790 ◽

Cited By ~ 15

Author(s):

Beste Turanli ◽

Kubra Karagoz ◽

Gizem Gulfidan ◽

Raghu Sinha ◽

Adil Mardinoglu ◽

...

Keyword(s):

Drug Discovery ◽

Precision Medicine ◽

Effective Treatment ◽

Biological Networks ◽

Drug Targeting ◽

Treatment Strategies ◽

Molecular Networks ◽

Cancer Drug ◽

Omics Data ◽

Data Types

A complex framework of interacting partners including genetic, proteomic, and metabolic networks that cooperate to mediate specific functional phenotypes drives human biological processes. Recent technological and analytical advances in “omic” sciences allow the identification and elucidation of reprogramming biological functions in response to perturbations in cells and tissues. To understand such a complex system, biological networks are generated to reduce the complexity into relatively simple models, and the integration of these molecular networks from different perspectives is implemented for a holistic interpretation of the entire system. Ultimately, network-based methods will effectively facilitate the development and improvement of precision medicine by directing therapies based on the underlying biology of a given patient’s disease. The goal of precision medicine is to identify novel therapeutic strategies that can be optimized for each disease type or each patient based on the underlying genetic, environmental, and lifestyle factors. Pharmaco-omics analyses based on an integration of pharmacology and various “omics” data types can be employed to develop effective treatment strategies using particular drugs and doses that are tailored to each individual. In the current review, we first present the core elements of network-based systems biology in the context of pharmaco-omics followed by integration of multi-omics data using various biological networks. Next, we provide an opening into precise medicine and drug targeting based on network approaches. Lastly, we review the current significant efforts as well as the accomplishments and limitations in precise drug targeting with the utility of network-based guided drug discovery methods for effective treatment of breast cancer.

Download Full-text

A phenotypic screening platform utilising human spermatozoa identifies compounds with contraceptive activity

eLife ◽

10.7554/elife.51739 ◽

2020 ◽

Vol 9 ◽

Cited By ~ 2

Author(s):

Franz S Gruber ◽

Zoe C Johnston ◽

Christopher LR Barratt ◽

Paul D Andrews

Keyword(s):

Drug Discovery ◽

Target Identification ◽

Human Sperm ◽

Phenotypic Screening ◽

Major Barrier ◽

Drug Candidates ◽

Critical Gap ◽

Comprehensive Collection ◽

Screening Platform ◽

Novel Drug

There is an urgent need to develop new methods for male contraception, however a major barrier to drug discovery has been the lack of validated targets and the absence of an effective high-throughput phenotypic screening system. To address this deficit, we developed a fully-automated robotic screening platform that provided quantitative evaluation of compound activity against two key attributes of human sperm function: motility and acrosome reaction. In order to accelerate contraceptive development, we screened the comprehensive collection of 12,000 molecules that make up the ReFRAME repurposing library, comprising nearly all the small molecules that have been approved or have undergone clinical development, or have significant preclinical profiling. We identified several compounds that potently inhibit motility representing either novel drug candidates or routes to target identification. This platform will now allow for major drug discovery programmes that address the critical gap in the contraceptive portfolio as well as uncover novel human sperm biology.

Download Full-text

Update on MicroRNA-based Treatment Strategies

Osteologie/Osteology ◽

10.1055/a-1545-7927 ◽

2021 ◽

Vol 30 (03) ◽

pp. 243-250

Author(s):

Eric Hesse ◽

Franz Jakob ◽

Hanna Taipaleenmäki

Keyword(s):

Treatment Strategies ◽

Protein Coding ◽

Therapeutic Implications ◽

The Public ◽

Drug Candidates ◽

Diagnostic Use ◽

Recent Success ◽

Novel Approach ◽

Novel Drugs ◽

Novel Drug

AbstractThe family of RNAs comprises several members, protein coding mRNAs and a larger group of non-coding RNAs, which include small, approximately 21-25 nucleotides long microRNAs (miRNAs). In addition to an evolving diagnostic use of RNAs, RNA-based drugs are emerging very rapidly in medicine, which is not only -but currently very prominently visible- due to the impressive success of the first-in-class Covid-19 vaccines such as Comirnaty and Moderna (marketed by the companies Biontech/Pfizer and Moderna, respectively). Although administration of RNA-based drugs comes along with several technical obstacles including delivery approaches, the technology is experiencing a breakthrough and technical and conceptual hurdles that may still remain are very likely to be overcome within the near future. It is therefore highly likely that RNA-based pharmacotherapies may revolutionize medicine by improving vaccination concepts but also by providing novel drugs to treat many other conditions like cancer, metabolic- and degenerative diseases and beyond. It is fascinating to witness the rise of such milestones in medicine and is tempting to elaborate which additional accomplishments can be made using this technology towards personalized medicine comprising diagnostic and therapeutic aspects as well as individual drug design.Although the most recent success with mRNA-based and therefore protein coding vaccines currently takes center stage in media and people’s life, other types of RNAs that are less prominent to the public, like non-coding miRNAs, also develop very successfully towards diagnostic and therapeutic purposes. While the diagnostic use of miRNAs was reviewed in another article in this issue (see article from Hackl et al., this issue), this brief review will provide an update on the emerging therapeutic implications of miRNAs. Despite the fact that no miRNA-based drug has yet reached clinical approval, several compounds are in pre-clinical and clinical development for the treatment of various diseases and great progress has been made during the recent years, which also facilitated the establishment of several innovative biotech companies.Several obstacles associated with this novel approach including off-target effects, tissue specificity and delivery systems exist. However, important improvements have already been made and will continue to be made. It can therefore be assumed that treatments using this class of RNA will also further progress and stimulate additional stakeholders to enter the field to develop novel drug candidates as first-in-class medicinal products to address highly unmet clinical needs. This technology is still at its infancy given that miRNAs were uncovered just about 20 years ago but the conditions are promising for the development of next generation miRNA-based drugs.

Download Full-text