scholarly journals Deep Protein-Ligand Binding Prediction Using Unsupervised Learned Representations

2020 ◽  
Author(s):  
Paul Kim ◽  
Robin Winter ◽  
Djork-Arné Clevert
Keyword(s):  
Machine Learning ◽  
Ligand Binding ◽  
Representation Learning ◽  
Interaction Space ◽  
Extraction Methods ◽  
Binding Prediction ◽  
Ligand Interaction ◽  
Drug Candidates ◽  
Modeling Methodology ◽  
Related Proteins

In-silico protein-ligand binding prediction is an ongoing area of research in computational chemistry and machine learning based drug discovery, as an accurate predictive model could greatly reduce the time and resources necessary for the detection and prioritization of possible drug candidates. Proteochemometric modeling (PCM) attempts to make an accurate model of the protein-ligand interaction space by combining explicit protein and ligand descriptors. This requires the creation of information-rich, uniform and computer interpretable representations of proteins and ligands. Previous work in PCM modeling relies on pre-defined, handcrafted feature extraction methods, and many methods use protein descriptors that require alignment or are otherwise specific to a particular group of related proteins. However, recent advances in representation learning have shown that unsupervised machine learning can be used to generate embeddings which outperform complex, human-engineered representations. We apply this reasoning to propose a novel proteochemometric modeling methodology which, for the first time, uses embeddings generated via unsupervised representation learning for both the protein and ligand descriptors. We evaluate performance on various splits of a benchmark dataset, including a challenging split that tests the model’s ability to generalize to proteins for which bioactivity data is greatly limited, and we find that our method consistently outperforms state-of-the-art methods.

scholarly journals Deep Protein-Ligand Binding Prediction Using Unsupervised Learned Representations

2020 ◽  
Author(s):  
Paul Kim ◽  
Robin Winter ◽  
Djork-Arné Clevert
Keyword(s):  
Machine Learning ◽  
Ligand Binding ◽  
Representation Learning ◽  
Interaction Space ◽  
Extraction Methods ◽  
Binding Prediction ◽  
Ligand Interaction ◽  
Drug Candidates ◽  
Modeling Methodology ◽  
Related Proteins

In-silico protein-ligand binding prediction is an ongoing area of research in computational chemistry and machine learning based drug discovery, as an accurate predictive model could greatly reduce the time and resources necessary for the detection and prioritization of possible drug candidates. Proteochemometric modeling (PCM) attempts to make an accurate model of the protein-ligand interaction space by combining explicit protein and ligand descriptors. This requires the creation of information-rich, uniform and computer interpretable representations of proteins and ligands. Previous work in PCM modeling relies on pre-defined, handcrafted feature extraction methods, and many methods use protein descriptors that require alignment or are otherwise specific to a particular group of related proteins. However, recent advances in representation learning have shown that unsupervised machine learning can be used to generate embeddings which outperform complex, human-engineered representations. We apply this reasoning to propose a novel proteochemometric modeling methodology which, for the first time, uses embeddings generated via unsupervised representation learning for both the protein and ligand descriptors. We evaluate performance on various splits of a benchmark dataset, including a challenging split that tests the model’s ability to generalize to proteins for which bioactivity data is greatly limited, and we find that our method consistently outperforms state-of-the-art methods.

scholarly journals Unsupervised Representation Learning for Proteochemometric Modeling

2021 ◽  
Vol 22 (23) ◽  
pp. 12882
Author(s):  
Paul T. Kim ◽  
Robin Winter ◽  
Djork-Arné Clevert
Keyword(s):  
Machine Learning ◽  
Ligand Binding ◽  
Representation Learning ◽  
Interaction Space ◽  
Extraction Methods ◽  
Binding Prediction ◽  
Ligand Interaction ◽  
Drug Candidates ◽  
Protein Ligand Interaction ◽  
Related Proteins

In silico protein–ligand binding prediction is an ongoing area of research in computational chemistry and machine learning based drug discovery, as an accurate predictive model could greatly reduce the time and resources necessary for the detection and prioritization of possible drug candidates. Proteochemometric modeling (PCM) attempts to create an accurate model of the protein–ligand interaction space by combining explicit protein and ligand descriptors. This requires the creation of information-rich, uniform and computer interpretable representations of proteins and ligands. Previous studies in PCM modeling rely on pre-defined, handcrafted feature extraction methods, and many methods use protein descriptors that require alignment or are otherwise specific to a particular group of related proteins. However, recent advances in representation learning have shown that unsupervised machine learning can be used to generate embeddings that outperform complex, human-engineered representations. Several different embedding methods for proteins and molecules have been developed based on various language-modeling methods. Here, we demonstrate the utility of these unsupervised representations and compare three protein embeddings and two compound embeddings in a fair manner. We evaluate performance on various splits of a benchmark dataset, as well as on an internal dataset of protein–ligand binding activities and find that unsupervised-learned representations significantly outperform handcrafted representations.

Improved ligand-binding- and signaling-competent human NK2R yields in yeast using a chimera with the rat NK2R C-terminus enable NK2R-G protein signaling platform

2019 ◽  
Vol 32 (10) ◽  
pp. 459-469 ◽  
Author(s):  
Abhinav R Jain ◽  
Zachary T Britton ◽  
Chester E Markwalter ◽  
Anne S Robinson
Keyword(s):  
Protein Engineering ◽  
Ligand Binding ◽  
G Protein ◽  
Mammalian Cells ◽  
Protein Signaling ◽  
Ligand Interaction ◽  
Downstream Signaling ◽  
Drug Candidates ◽  
C Terminus ◽  
Engineering Strategy

Abstract The tachykinin 2 receptor (NK2R) plays critical roles in gastrointestinal, respiratory and mental disorders and is a well-recognized target for therapeutic intervention. To date, therapeutics targeting NK2R have failed to meet regulatory agency approval due in large part to the limited characterization of the receptor-ligand interaction and downstream signaling. Herein, we report a protein engineering strategy to improve ligand-binding- and signaling-competent human NK2R that enables a yeast-based NK2R signaling platform by creating chimeras utilizing sequences from rat NK2R. We demonstrate that NK2R chimeras incorporating the rat NK2R C-terminus exhibited improved ligand-binding yields and downstream signaling in engineered yeast strains and mammalian cells, where observed yields were better than 4-fold over wild type. This work builds on our previous studies that suggest exchanging the C-termini of related and well-expressed family members may be a general protein engineering strategy to overcome limitations to ligand-binding and signaling-competent G protein-coupled receptor yields in yeast. We expect these efforts to result in NK2R drug candidates with better characterized signaling properties.

scholarly journals Image-based effective feature generation for protein structural class and ligand binding prediction

2020 ◽  
Vol 6 ◽  
pp. e253
Author(s):  
Nafees Sadique ◽  
Al Amin Neaz Ahmed ◽  
Md Tajul Islam ◽  
Md. Nawshad Pervage ◽  
Swakkhar Shatabda
Keyword(s):  
Machine Learning ◽  
Ligand Binding ◽  
Tertiary Structure ◽  
Learning Algorithms ◽  
Three Dimensional ◽  
Machine Learning Algorithms ◽  
Binding Prediction ◽  
Structural Class ◽  
Protein Structural Class ◽  
Atom Bond

Proteins are the building blocks of all cells in both human and all living creatures of the world. Most of the work in the living organism is performed by proteins. Proteins are polymers of amino acid monomers which are biomolecules or macromolecules. The tertiary structure of protein represents the three-dimensional shape of a protein. The functions, classification and binding sites are governed by the protein’s tertiary structure. If two protein structures are alike, then the two proteins can be of the same kind implying similar structural class and ligand binding properties. In this paper, we have used the protein tertiary structure to generate effective features for applications in structural similarity to detect structural class and ligand binding. Firstly, we have analyzed the effectiveness of a group of image-based features to predict the structural class of a protein. These features are derived from the image generated by the distance matrix of the tertiary structure of a given protein. They include local binary pattern (LBP) histogram, Gabor filtered LBP histogram, separate row multiplication matrix with uniform LBP histogram, neighbor block subtraction matrix with uniform LBP histogram and atom bond. Separate row multiplication matrix and neighbor block subtraction matrix filters, as well as atom bond, are our novels. The experiments were done on a standard benchmark dataset. We have demonstrated the effectiveness of these features over a large variety of supervised machine learning algorithms. Experiments suggest support vector machines is the best performing classifier on the selected dataset using the set of features. We believe the excellent performance of Hybrid LBP in terms of accuracy would motivate the researchers and practitioners to use it to identify protein structural class. To facilitate that, a classification model using Hybrid LBP is readily available for use at http://brl.uiu.ac.bd/PL/. Protein-ligand binding is accountable for managing the tasks of biological receptors that help to cure diseases and many more. Therefore, binding prediction between protein and ligand is important for understanding a protein’s activity or to accelerate docking computations in virtual screening-based drug design. Protein-ligand binding prediction requires three-dimensional tertiary structure of the target protein to be searched for ligand binding. In this paper, we have proposed a supervised learning algorithm for predicting protein-ligand binding, which is a similarity-based clustering approach using the same set of features. Our algorithm works better than the most popular and widely used machine learning algorithms.

scholarly journals Automated In Silico Identification of Drug Candidates for Coronavirus Through a Novel Programmatic Tool and Extensive Computational (MD, DFT) Studies of Select Drug Candidates

2020 ◽  
Author(s):  
Ben Geoffrey A S ◽  
Rafal Madaj ◽  
Akhil Sanker ◽  
Mario Sergio Valdés Tresanco ◽  
Host Antony Davidd ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Drug Discovery ◽  
In Silico ◽  
Density Functional ◽  
Density Functional Theory Calculations ◽  
Ligand Interaction ◽  
Drug Candidates ◽  
Descriptor Selection ◽  
Drug Leads

<p>The work is composed of python based programmatic tool that automates the dry lab drug discovery workflow for coronavirus. Firstly, the python program is written to automate the process of data mining PubChem database to collect data required to perform a machine learning based AutoQSAR algorithm through which drug leads for coronavirus are generated. The data acquisition from PubChem was carried out through python web scrapping techniques. The workflow of the machine learning based AutoQSAR involves feature learning and descriptor selection, QSAR modelling, validation and prediction. The drug leads generated by the program are required to satisfy the Lipinski’s drug likeness criteria as compounds that satisfy Lipinski’s criteria are likely to be an orally active drug in humans. Drug leads generated by the program are fed as programmatic inputs to an In Silico modelling package to computer model the interaction of the compounds generated as drug leads and the coronaviral drug target identified with their PDB ID : 6Y84. The results are stored in the working folder of the user. The program also generates protein-ligand interaction profiling and stores the visualized images in the working folder of the user. Select drug leads were further studied extensively using Molecular Dynamics Simulations and best binders and their reactive profiles were analysed using Molecular Dynamics and Density Functional Theory calculations. Thus our programmatic tool ushers in a new age of automatic ease in drug identification for coronavirus. </p><p><br></p><p><br></p><p>The program is hosted, maintained and supported at the GitHub repository link given below</p><p><br></p><p>https://github.com/bengeof/Programmatic-tool-to-automate-the-drug-discovery-workflow-for-coronavirus</p>

scholarly journals Automated In Silico Identification of Drug Candidates for Coronavirus Through a Novel Programmatic Tool and Extensive Computational (MD, DFT) Studies of Select Drug Candidates

2020 ◽  
Author(s):  
Ben Geoffrey A S ◽  
Rafal Madaj ◽  
Akhil Sanker ◽  
Mario Sergio Valdés Tresanco ◽  
Host Antony Davidd ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Drug Discovery ◽  
In Silico ◽  
Density Functional ◽  
Density Functional Theory Calculations ◽  
Ligand Interaction ◽  
Drug Candidates ◽  
Descriptor Selection ◽  
Drug Leads

<p>The work is composed of python based programmatic tool that automates the dry lab drug discovery workflow for coronavirus. Firstly, the python program is written to automate the process of data mining PubChem database to collect data required to perform a machine learning based AutoQSAR algorithm through which drug leads for coronavirus are generated. The data acquisition from PubChem was carried out through python web scrapping techniques. The workflow of the machine learning based AutoQSAR involves feature learning and descriptor selection, QSAR modelling, validation and prediction. The drug leads generated by the program are required to satisfy the Lipinski’s drug likeness criteria as compounds that satisfy Lipinski’s criteria are likely to be an orally active drug in humans. Drug leads generated by the program are fed as programmatic inputs to an In Silico modelling package to computer model the interaction of the compounds generated as drug leads and the coronaviral drug target identified with their PDB ID : 6Y84. The results are stored in the working folder of the user. The program also generates protein-ligand interaction profiling and stores the visualized images in the working folder of the user. Select drug leads were further studied extensively using Molecular Dynamics Simulations and best binders and their reactive profiles were analysed using Molecular Dynamics and Density Functional Theory calculations. Thus our programmatic tool ushers in a new age of automatic ease in drug identification for coronavirus. </p><p><br></p><p><br></p><p>The program is hosted, maintained and supported at the GitHub repository link given below</p><p><br></p><p>https://github.com/bengeof/Programmatic-tool-to-automate-the-drug-discovery-workflow-for-coronavirus</p>

A Novel Amino Acid Sequence-based Computational Approach to Predicting Cell-penetrating Peptides

2019 ◽  
Vol 15 (3) ◽  
pp. 206-211 ◽  
Author(s):  
Jihui Tang ◽  
Jie Ning ◽  
Xiaoyan Liu ◽  
Baoming Wu ◽  
Rongfeng Hu
Keyword(s):  
Machine Learning ◽  
Amino Acid ◽  
Amino Acid Position ◽  
Cell Penetrating Peptides ◽  
Support Vector ◽  
Cell Penetration ◽  
Drug Candidates ◽  
Machine Learning Model ◽  
Cell Penetrating ◽  
Novel Method

<P>Introduction: Machine Learning is a useful tool for the prediction of cell-penetration compounds as drug candidates. </P><P> Materials and Methods: In this study, we developed a novel method for predicting Cell-Penetrating Peptides (CPPs) membrane penetrating capability. For this, we used orthogonal encoding to encode amino acid and each amino acid position as one variable. Then a software of IBM spss modeler and a dataset including 533 CPPs, were used for model screening. </P><P> Results: The results indicated that the machine learning model of Support Vector Machine (SVM) was suitable for predicting membrane penetrating capability. For improvement, the three CPPs with the most longer lengths were used to predict CPPs. The penetration capability can be predicted with an accuracy of close to 95%. </P><P> Conclusion: All the results indicated that by using amino acid position as a variable can be a perspective method for predicting CPPs membrane penetrating capability.</P>

Digging for the truth: the case for active annotation in evaluating the credibility of online medical information (Preprint)

2020 ◽  
Author(s):  
Mikołaj Morzy ◽  
Bartłomiej Balcerzak ◽  
Adam Wierzbicki ◽  
Adam Wierzbicki
Keyword(s):  
Machine Learning ◽  
Medical Information ◽  
Representation Learning ◽  
Training Dataset ◽  
Highly Qualified ◽  
Human In The Loop ◽  
Annotation Process ◽  
Comprehensive Framework ◽  
Online Sources ◽  
The Web

BACKGROUND With the rapidly accelerating spread of dissemination of false medical information on the Web, the task of establishing the credibility of online sources of medical information becomes a pressing necessity. The sheer number of websites offering questionable medical information presented as reliable and actionable suggestions with possibly harmful effects poses an additional requirement for potential solutions, as they have to scale to the size of the problem. Machine learning is one such solution which, when properly deployed, can be an effective tool in fighting medical disinformation on the Web. OBJECTIVE We present a comprehensive framework for designing and curating of machine learning training datasets for online medical information credibility assessment. We show how the annotation process should be constructed and what pitfalls should be avoided. Our main objective is to provide researchers from medical and computer science communities with guidelines on how to construct datasets for machine learning models for various areas of medical information wars. METHODS The key component of our approach is the active annotation process. We begin by outlining the annotation protocol for the curation of high-quality training dataset, which then can be augmented and rapidly extended by employing the human-in-the-loop paradigm to machine learning training. To circumvent the cold start problem of insufficient gold standard annotations, we propose a pre-processing pipeline consisting of representation learning, clustering, and re-ranking of sentences for the acceleration of the training process and the optimization of human resources involved in the annotation. RESULTS We collect over 10 000 annotations of sentences related to selected subjects (psychiatry, cholesterol, autism, antibiotics, vaccines, steroids, birth methods, food allergy testing) for less than $7 000 employing 9 highly qualified annotators (certified medical professionals) and we release this dataset to the general public. We develop an active annotation framework for more efficient annotation of non-credible medical statements. The results of the qualitative analysis support our claims of the efficacy of the presented method. CONCLUSIONS A set of very diverse incentives is driving the widespread dissemination of medical disinformation on the Web. An effective strategy of countering this spread is to use machine learning for automatically establishing the credibility of online medical information. This, however, requires a thoughtful design of the training pipeline. In this paper we present a comprehensive framework of active annotation. In addition, we publish a large curated dataset of medical statements labelled as credible, non-credible, or neutral.

scholarly journals SMPLIP-Score: predicting ligand binding affinity from simple and interpretable on-the-fly interaction fingerprint pattern descriptors

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Surendra Kumar ◽  
Mi-hyun Kim
Keyword(s):  
Ligand Binding ◽  
Binding Affinity ◽  
Scoring Functions ◽  
Binding Affinities ◽  
Ligand Interaction ◽  
Fingerprint Pattern ◽  
Comparable Performance ◽  
Direct Interpretation ◽  
Benchmark Datasets ◽  
Complex Features

AbstractIn drug discovery, rapid and accurate prediction of protein–ligand binding affinities is a pivotal task for lead optimization with acceptable on-target potency as well as pharmacological efficacy. Furthermore, researchers hope for a high correlation between docking score and pose with key interactive residues, although scoring functions as free energy surrogates of protein–ligand complexes have failed to provide collinearity. Recently, various machine learning or deep learning methods have been proposed to overcome the drawbacks of scoring functions. Despite being highly accurate, their featurization process is complex and the meaning of the embedded features cannot directly be interpreted by human recognition without an additional feature analysis. Here, we propose SMPLIP-Score (Substructural Molecular and Protein–Ligand Interaction Pattern Score), a direct interpretable predictor of absolute binding affinity. Our simple featurization embeds the interaction fingerprint pattern on the ligand-binding site environment and molecular fragments of ligands into an input vectorized matrix for learning layers (random forest or deep neural network). Despite their less complex features than other state-of-the-art models, SMPLIP-Score achieved comparable performance, a Pearson’s correlation coefficient up to 0.80, and a root mean square error up to 1.18 in pK units with several benchmark datasets (PDBbind v.2015, Astex Diverse Set, CSAR NRC HiQ, FEP, PDBbind NMR, and CASF-2016). For this model, generality, predictive power, ranking power, and robustness were examined using direct interpretation of feature matrices for specific targets.

Sign in / Sign up

Export Citation Format

Share Document