scholarly journals Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Christian Feldmann ◽  
Jürgen Bajorath
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Molecular Basis ◽  
Structural Characteristics ◽  
Structural Features ◽  
Test System ◽  
Feature Weighting ◽  
Compelling Evidence ◽  
Single Target ◽  
Target Activity

AbstractCompounds with defined multi-target activity (promiscuity) play an increasingly important role in drug discovery. However, the molecular basis of multi-target activity is currently only little understood. In particular, it remains unclear whether structural features exist that generally characterize promiscuous compounds and set them apart from compounds with single-target activity. We have devised a test system using machine learning to systematically examine structural features that might characterize compounds with multi-target activity. Using this system, more than 860,000 diagnostic predictions were carried out. The analysis provided compelling evidence for the presence of structural characteristics of promiscuous compounds that were dependent on given target combinations, but not generalizable. Feature weighting and mapping identified characteristic substructures in test compounds. Taken together, these findings are relevant for the design of compounds with desired multi-target activity.

scholarly journals Analysis of Biological Screening Compounds with Single- or Multi-Target Activity via Diagnostic Machine Learning

Biomolecules ◽  
2020 ◽  
Vol 10 (12) ◽  
pp. 1605
Author(s):  
Christian Feldmann ◽  
Dimitar Yonchev ◽  
Jürgen Bajorath
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Nearest Neighbor ◽  
Structural Features ◽  
Biological Screening ◽  
Large Scale Analysis ◽  
Structural Relationships ◽  
Single Target ◽  
Neighbor Relationship ◽  
Target Activity

Predicting compounds with single- and multi-target activity and exploring origins of compound specificity and promiscuity is of high interest for chemical biology and drug discovery. We present a large-scale analysis of compound promiscuity including two major components. First, high-confidence datasets of compounds with multi- and corresponding single-target activity were extracted from biological screening data. Positive and negative assay results were taken into account and data completeness was ensured. Second, these datasets were investigated using diagnostic machine learning to systematically distinguish between compounds with multi- and single-target activity. Models built on the basis of chemical structure consistently produced meaningful predictions. These findings provided evidence for the presence of structural features differentiating promiscuous and non-promiscuous compounds. Machine learning under varying conditions using modified datasets revealed a strong influence of nearest neighbor relationship on the predictions. Many multi-target compounds were found to be more similar to other multi-target compounds than single-target compounds and vice versa, which resulted in consistently accurate predictions. The results of our study confirm the presence of structural relationships that differentiate promiscuous and non-promiscuous compounds.

scholarly journals Combined free energy calculation and machine learning methods for understanding ligand unbinding kinetics

2021 ◽  
Author(s):  
Magd Badaoui ◽  
Pedro J Buigues ◽  
Dénes Berta ◽  
Gaurav M. Mandana ◽  
Hankang Gu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Free Energy ◽  
Drug Discovery ◽  
Energy Barrier ◽  
Structural Features ◽  
Supervised Machine Learning ◽  
Energy Calculation ◽  
Free Energy Barrier ◽  
Residence Times ◽  
Design Strategies

ABSTRACTThe determination of drug residence times, which define the time an inhibitor is in complex with its target, is a fundamental part of the drug discovery process. Synthesis and experimental pharmacokinetics measurements are, however, expensive, and time-consuming. In this work, we aimed to obtain drug residence times computationally. Furthermore, we propose a novel algorithm to identify molecular design objectives based on ligand unbinding kinetics. We designed an enhanced sampling technique to accurately predict the free energy profiles of the ligand unbinding process, focusing on the free energy barrier for unbinding. Our method first identifies unbinding paths determining a corresponding set of internal coordinates (IC) that form contacts between the protein and the ligand, then iteratively updates these interactions during a series of biased molecular-dynamics (MD) simulations to reveal the ICs important for the whole of the unbinding process. Subsequently, we performed finite temperature string simulations to obtain the free energy barrier for unbinding using the set of ICs as a complex reaction coordinate. Importantly, we also aimed to enable further design of drugs focusing on improved residence times. To this end, we developed a supervised machine learning (ML) approach that uses as input unbiased “downhill” trajectories from the transition state (TS) ensemble of the string unbinding path. We demonstrate that our ML method can identify key ligand-protein interactions driving the system through the TS. Some of the most important drugs for cancer treatment are kinase inhibitors. One of these kinase targets is Cyclin Dependent Kinase 2 (CDK2), an appealing target for anticancer drug development. Here, we tested our method using three different CDK2 inhibitors for potential further development of these compounds. We compared the free energy barriers obtained from our calculations with those observed in available experimental data. We highlighted important interactions at the distal ends of the ligands that can be targeted for improved residence times. Our method provides a new tool to determine unbinding rates, and to identify key structural features of the inhibitors that can be used as starting points for novel design strategies in drug discovery.

scholarly journals Predicting Protein Thermostability Upon Mutation Using Molecular Dynamics Timeseries Data

2016 ◽  
Author(s):  
Noah Fleming ◽  
Benjamin Kinsella ◽  
Christopher Ing
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Molecular Dynamics ◽  
Protein Structure ◽  
Protein Stability ◽  
Recurrent Neural Network ◽  
Molecular Basis ◽  
Sequence Data ◽  
Structural Features ◽  
Machine Learning Algorithms

AbstractA large number of human diseases result from disruptions to protein structure and function caused by missense mutations. Computational methods are frequently employed to assist in the prediction of protein stability upon mutation. These methods utilize a combination of protein sequence data, protein structure data, empirical energy functions, and physicochemical properties of amino acids. In this work, we present the first use of dynamic protein structural features in order to improve stability predictions upon mutation. This is achieved through the use of a set of timeseries extracted from microsecond timescale atomistic molecular dynamics simulations of proteins. Standard machine learning algorithms using mean, variance, and histograms of these timeseries were found to be 60-70% accurate in stability classification based on experimental ΔΔGor protein-chaperone interaction measurements. A recurrent neural network with full treatment of timeseries data was found to be 80% accurate according the F1 score. The performance of our models was found to be equal or better than two recently developed machine learning methods for binary classification as well as two industry-standard stability prediction algorithms. In addition to classification, understanding the molecular basis of protein stability disruption due to disease-causing mutations is a significant challenge that impedes the development of drugs and therapies that may be used treat genetic diseases. The use of dynamic structural features allows for novel insight into the molecular basis of protein disruption by mutation in a diverse set of soluble proteins. To assist in the interpretation of machine learning results, we present a technique for determining the importance of features to a recurrent neural network using Garson’s method. We propose a novel extension of neural interpretation diagrams by implementing Garson’s method to scale each node in the neural interpretation diagram according to its relative importance to the network.

Protein Interaction Domains and Post-Translational Modifications: Structural Features and Drug Discovery Applications

2020 ◽  
Vol 27 (37) ◽  
pp. 6306-6355 ◽  
Author(s):  
Marian Vincenzi ◽  
Flavia Anna Mercurio ◽  
Marilisa Leone
Keyword(s):  
Drug Discovery ◽  
Protein Interaction ◽  
Protein Interactions ◽  
Structural Information ◽  
Protein Complexes ◽  
Structural Features ◽  
Protein Protein Interactions ◽  
Modular Architecture ◽  
Post Translational Modifications ◽  
Interaction Domains

Background:: Many pathways regarding healthy cells and/or linked to diseases onset and progression depend on large assemblies including multi-protein complexes. Protein-protein interactions may occur through a vast array of modules known as protein interaction domains (PIDs). Objective:: This review concerns with PIDs recognizing post-translationally modified peptide sequences and intends to provide the scientific community with state of art knowledge on their 3D structures, binding topologies and potential applications in the drug discovery field. Method:: Several databases, such as the Pfam (Protein family), the SMART (Simple Modular Architecture Research Tool) and the PDB (Protein Data Bank), were searched to look for different domain families and gain structural information on protein complexes in which particular PIDs are involved. Recent literature on PIDs and related drug discovery campaigns was retrieved through Pubmed and analyzed. Results and Conclusion:: PIDs are rather versatile as concerning their binding preferences. Many of them recognize specifically only determined amino acid stretches with post-translational modifications, a few others are able to interact with several post-translationally modified sequences or with unmodified ones. Many PIDs can be linked to different diseases including cancer. The tremendous amount of available structural data led to the structure-based design of several molecules targeting protein-protein interactions mediated by PIDs, including peptides, peptidomimetics and small compounds. More studies are needed to fully role out, among different families, PIDs that can be considered reliable therapeutic targets, however, attacking PIDs rather than catalytic domains of a particular protein may represent a route to obtain selective inhibitors.

Applications of Quantitative Structure-Activity Relationships (QSAR) based Virtual Screening in Drug Design: A Review

2020 ◽  
Vol 20 (14) ◽  
pp. 1375-1388 ◽  
Author(s):  
Patnala Ganga Raju Achary
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Virtual Screening ◽  
Model Building ◽  
Chemical Space ◽  
Qsar Model ◽  
Quantitative Structure ◽  
Efficient Manner ◽  
Qsar Analysis ◽  
Structure Activity

The scientists, and the researchers around the globe generate tremendous amount of information everyday; for instance, so far more than 74 million molecules are registered in Chemical Abstract Services. According to a recent study, at present we have around 1060 molecules, which are classified as new drug-like molecules. The library of such molecules is now considered as ‘dark chemical space’ or ‘dark chemistry.’ Now, in order to explore such hidden molecules scientifically, a good number of live and updated databases (protein, cell, tissues, structure, drugs, etc.) are available today. The synchronization of the three different sciences: ‘genomics’, proteomics and ‘in-silico simulation’ will revolutionize the process of drug discovery. The screening of a sizable number of drugs like molecules is a challenge and it must be treated in an efficient manner. Virtual screening (VS) is an important computational tool in the drug discovery process; however, experimental verification of the drugs also equally important for the drug development process. The quantitative structure-activity relationship (QSAR) analysis is one of the machine learning technique, which is extensively used in VS techniques. QSAR is well-known for its high and fast throughput screening with a satisfactory hit rate. The QSAR model building involves (i) chemo-genomics data collection from a database or literature (ii) Calculation of right descriptors from molecular representation (iii) establishing a relationship (model) between biological activity and the selected descriptors (iv) application of QSAR model to predict the biological property for the molecules. All the hits obtained by the VS technique needs to be experimentally verified. The present mini-review highlights: the web-based machine learning tools, the role of QSAR in VS techniques, successful applications of QSAR based VS leading to the drug discovery and advantages and challenges of QSAR.

Recent Progress in Machine Learning-based Prediction of Peptide Activity for Drug Discovery

2019 ◽  
Vol 19 (1) ◽  
pp. 4-16 ◽  
Author(s):  
Qihui Wu ◽  
Hanzhong Ke ◽  
Dongli Li ◽  
Qi Wang ◽  
Jiansong Fang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Large Scale ◽  
Recent Progress ◽  
High Specificity ◽  
Learning Approaches ◽  
Anticancer Peptides ◽  
The Past ◽  
Traditional Approaches ◽  
Large Scale Screening

Over the past decades, peptide as a therapeutic candidate has received increasing attention in drug discovery, especially for antimicrobial peptides (AMPs), anticancer peptides (ACPs) and antiinflammatory peptides (AIPs). It is considered that the peptides can regulate various complex diseases which are previously untouchable. In recent years, the critical problem of antimicrobial resistance drives the pharmaceutical industry to look for new therapeutic agents. Compared to organic small drugs, peptide- based therapy exhibits high specificity and minimal toxicity. Thus, peptides are widely recruited in the design and discovery of new potent drugs. Currently, large-scale screening of peptide activity with traditional approaches is costly, time-consuming and labor-intensive. Hence, in silico methods, mainly machine learning approaches, for their accuracy and effectiveness, have been introduced to predict the peptide activity. In this review, we document the recent progress in machine learning-based prediction of peptides which will be of great benefit to the discovery of potential active AMPs, ACPs and AIPs.

scholarly journals Descriptors of Cytochrome Inhibitors and Useful Machine Learning Based Methods for the Design of Safer Drugs

2021 ◽  
Vol 14 (5) ◽  
pp. 472
Author(s):  
Tyler C. Beck ◽  
Kyle R. Beck ◽  
Jordan Morningstar ◽  
Menny M. Benjamin ◽  
Russell A. Norris
Keyword(s):  
United States ◽  
Machine Learning ◽  
Drug Interactions ◽  
The United States ◽  
Structural Features ◽  
Physiochemical Properties ◽  
Drug Dosing ◽  
Therapeutic Outcomes ◽  
Cyp Inhibition ◽  
Cyp Inhibitors

Roughly 2.8% of annual hospitalizations are a result of adverse drug interactions in the United States, representing more than 245,000 hospitalizations. Drug–drug interactions commonly arise from major cytochrome P450 (CYP) inhibition. Various approaches are routinely employed in order to reduce the incidence of adverse interactions, such as altering drug dosing schemes and/or minimizing the number of drugs prescribed; however, often, a reduction in the number of medications cannot be achieved without impacting therapeutic outcomes. Nearly 80% of drugs fail in development due to pharmacokinetic issues, outlining the importance of examining cytochrome interactions during preclinical drug design. In this review, we examined the physiochemical and structural properties of small molecule inhibitors of CYPs 3A4, 2D6, 2C19, 2C9, and 1A2. Although CYP inhibitors tend to have distinct physiochemical properties and structural features, these descriptors alone are insufficient to predict major cytochrome inhibition probability and affinity. Machine learning based in silico approaches may be employed as a more robust and accurate way of predicting CYP inhibition. These various approaches are highlighted in the review.

The Drug Factory: Industrializing How New Drugs Are Found

2021 ◽  
pp. 247255522110281
Author(s):  
August Allen ◽  
Lina Nilsson
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Feedback Loops ◽  
New Drugs

In this perspective, the authors paint a vision for industrializing drug discovery with an “atoms and bits” approach. This approach leverages advancements in machine learning, automation, and biological tools to create a platform for drug discovery that de-specializes the output of insights and generates feedback loops to iterate on each success and failure. Recursion Pharmaceuticals, where the authors work, is provided as an example of how one company is attempting to achieve this vision.

scholarly journals Predicting Isoform-Selective Carbonic Anhydrase Inhibitors via Machine Learning and Rationalizing Structural Features Important for Selectivity

ACS Omega ◽  
2021 ◽  
Vol 6 (5) ◽  
pp. 4080-4089
Author(s):  
Salvatore Galati ◽  
Dimitar Yonchev ◽  
Raquel Rodríguez-Pérez ◽  
Martin Vogt ◽  
Tiziano Tuccinardi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Carbonic Anhydrase ◽  
Structural Features ◽  
Carbonic Anhydrase Inhibitors

scholarly journals Fine-tuning of a generative neural network for designing multi-target compounds

2021 ◽  
Author(s):  
Thomas Blaschke ◽  
Jürgen Bajorath
Keyword(s):  
Neural Network ◽  
Small Molecules ◽  
De Novo ◽  
Pharmaceutical Research ◽  
Generative Models ◽  
Fine Tuning ◽  
Data Sets ◽  
Single Target ◽  
Fine Tune ◽  
Target Activity

AbstractExploring the origin of multi-target activity of small molecules and designing new multi-target compounds are highly topical issues in pharmaceutical research. We have investigated the ability of a generative neural network to create multi-target compounds. Data sets of experimentally confirmed multi-target, single-target, and consistently inactive compounds were extracted from public screening data considering positive and negative assay results. These data sets were used to fine-tune the REINVENT generative model via transfer learning to systematically recognize multi-target compounds, distinguish them from single-target or inactive compounds, and construct new multi-target compounds. During fine-tuning, the model showed a clear tendency to increasingly generate multi-target compounds and structural analogs. Our findings indicate that generative models can be adopted for de novo multi-target compound design.

Sign in / Sign up

Export Citation Format

Share Document