scholarly journals ChemPLAN-Net: A deep learning framework to find novel inhibitor fragments for proteins

2021 ◽  
Author(s):  
Michael Alexander Suarez Vasquez ◽  
Mingyi Xue ◽  
Jordy Homing Lam ◽  
Eshani C Goonetilleke ◽  
Xin Gao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Crystal Structures ◽  
Drug Targets ◽  
Binary Classification ◽  
Learning Framework ◽  
Cell Assays ◽  
Physicochemical Features ◽  
Hiv 1 ◽  
Fragment Docking

Fragment-based drug design plays an important role in the drug discovery process by reducing the complex small-molecule space into a more manageable fragment space. We leverage the power of deep learning to design ChemPLAN-Net; a model that incorporates the pairwise association of physicochemical features of both the protein drug targets and the inhibitor and learns from thousands of protein co-crystal structures in the PDB database to predict previously unseen inhibitor fragments. Our novel protocol handles the computationally challenging multi-label, multi-class problem, by defining a fragment database and using an iterative feature-pair binary classification approach. By training ChemPLAN-Net on available co-crystal structures of the protease protein family, excluding HIV-1 protease as a target, we are able to outperform fragment docking and recover the target's inhibitor fragments found in co-crystal structures or identified by in-vitro cell assays.

scholarly journals Molecular insights into the inhibition of plasmepsins by HIV-1 protease inhibitors: Implications for antimalarial drug discovery

2021 ◽  
Author(s):  
Vandana Mishra ◽  
Ishan Rathore ◽  
Anuradha Deshmukh ◽  
Swati Patankar ◽  
Alla Gustchina ◽  
...  
Keyword(s):  
Protease Inhibitors ◽  
Drug Targets ◽  
Drug Repurposing ◽  
Binding Mode ◽  
Ic50 Values ◽  
Multiple Regions ◽  
Potential Drug Targets ◽  
Hiv 1 ◽  
Micromolar Range

Malaria is a deadly disease, and the worldwide emergence of drug resistance in the Plasmodium parasites demands the development of novel and potent antimalarials. HIV-1 protease inhibitors (HIV-1 PIs) alleviate the Plasmodium pathogenesis during malaria/HIV-1 co-infection plausibly by inhibiting vacuolar plasmepsins (PMs), the hemoglobin degrading proteases from P. falciparum. All five FDA-approved HIV-1 PIs tested against PMII exhibit the Ki values in the low micromolar range of which RTV and LPV display the highest inhibition activity. Both inhibitors impede in vitro growth of P. falciparum at low micromolar IC50 values. We report the first crystal structures of PMII complexed with RTV and LPV that reveal the binding mode and interactions of the inhibitors in the active site as well as elucidate the mechanism underlying their differential potency. The conformational flexibility of the P4 group in RTV allows it to explore multiple regions of the S4 pocket. The present study establishes vacuolar PMs as potential drug targets of HIV-1 PIs. The molecular details explaining the inhibitory mechanism of HIV-1 PIs might be crucial in designing novel and potent antimalarial analogs. This work strengthens the prospect of drug repurposing as an alternative strategy towards antimalarial treatments and provides an opportunity to tackle malaria and HIV-1 co-infection.

scholarly journals X-Ray Crystal Structures of Human Immunodeficiency Virus Type 1 Protease Mutants Complexed with Atazanavir

2007 ◽  
Vol 81 (17) ◽  
pp. 9525-9535 ◽  
Author(s):  
Herbert E. Klei ◽  
Kevin Kish ◽  
Pin-Fang M. Lin ◽  
Qi Guo ◽  
Jacques Friborg ◽  
...  
Keyword(s):  
Human Immunodeficiency Virus ◽  
Crystal Structures ◽  
Human Immunodeficiency Virus Type ◽  
Virus Type ◽  
Resistant Mutant ◽  
X Ray ◽  
Immunodeficiency Virus ◽  
Hiv 1

ABSTRACT Atazanavir, which is marketed as REYATAZ, is the first human immunodeficiency virus type 1 (HIV-1) protease inhibitor approved for once-daily administration. As previously reported, atazanavir offers improved inhibitory profiles against several common variants of HIV-1 protease over those of the other peptidomimetic inhibitors currently on the market. This work describes the X-ray crystal structures of complexes of atazanavir with two HIV-1 protease variants, namely, (i) an enzyme optimized for resistance to autolysis and oxidation, referred to as the cleavage-resistant mutant (CRM); and (ii) the M46I/V82F/I84V/L90M mutant of the CRM enzyme, which is resistant to all approved HIV-1 protease inhibitors, referred to as the inhibitor-resistant mutant. In these two complexes, atazanavir adopts distinct bound conformations in response to the V82F substitution, which may explain why this substitution, at least in isolation, has yet to be selected in vitro or in the clinic. Because of its nearly symmetrical chemical structure, atazanavir is able to make several analogous contacts with each monomer of the biological dimer.

scholarly journals A Two-Stage Deep Neural Network Framework for Precipitation Estimation from Bispectral Satellite Information

2018 ◽  
Vol 19 (2) ◽  
pp. 393-408 ◽  
Author(s):  
Yumeng Tao ◽  
Kuolin Hsu ◽  
Alexander Ihler ◽  
Xiaogang Gao ◽  
Soroosh Sorooshian
Keyword(s):  
Deep Learning ◽  
Binary Classification ◽  
Precipitation Amount ◽  
Skewed Distribution ◽  
Stage Model ◽  
Two Stage ◽  
Learning Framework ◽  
Second Stage ◽  
Satellite Information ◽  
Precipitation Estimation

Abstract Compared to ground precipitation measurements, satellite-based precipitation estimation products have the advantage of global coverage and high spatiotemporal resolutions. However, the accuracy of satellite-based precipitation products is still insufficient to serve many weather, climate, and hydrologic applications at high resolutions. In this paper, the authors develop a state-of-the-art deep learning framework for precipitation estimation using bispectral satellite information, infrared (IR), and water vapor (WV) channels. Specifically, a two-stage framework for precipitation estimation from bispectral information is designed, consisting of an initial rain/no-rain (R/NR) binary classification, followed by a second stage estimating the nonzero precipitation amount. In the first stage, the model aims to eliminate the large fraction of NR pixels and to delineate precipitation regions precisely. In the second stage, the model aims to estimate the pointwise precipitation amount accurately while preserving its heavily skewed distribution. Stacked denoising autoencoders (SDAEs), a commonly used deep learning method, are applied in both stages. Performance is evaluated along a number of common performance measures, including both R/NR and real-valued precipitation accuracy, and compared with an operational product, Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Cloud Classification System (PERSIANN-CCS). For R/NR binary classification, the proposed two-stage model outperforms PERSIANN-CCS by 32.56% in the critical success index (CSI). For real-valued precipitation estimation, the two-stage model is 23.40% lower in average bias, is 44.52% lower in average mean squared error, and has a 27.21% higher correlation coefficient. Hence, the two-stage deep learning framework has the potential to serve as a more accurate and more reliable satellite-based precipitation estimation product. The authors also provide some future directions for development of satellite-based precipitation estimation products in both incorporating auxiliary information and improving retrieval algorithms.

scholarly journals DeepHINT: Understanding HIV-1 integration via deep learning with attention

2018 ◽  
Author(s):  
Hailin Hu ◽  
An Xiao ◽  
Sai Zhang ◽  
Yangyang Li ◽  
Xuanling Shi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Dna Sequences ◽  
Mechanistic Study ◽  
Sequence Information ◽  
Genomic Context ◽  
Learning Framework ◽  
Integration Sites ◽  
Hiv Integration ◽  
Hiv 1 ◽  
Selection Of

AbstractMotivationHuman immunodeficiency virus type 1 (HIV-1) genome integration is closely related to clinical latency and viral rebound. In addition to human DNA sequences that directly interact with the integration machinery, the selection of HIV integration sites has also been shown to depend on the heterogeneous genomic context around a large region, which greatly hinders the prediction and mechanistic studies of HIV integration.ResultsWe have developed an attention-based deep learning framework, named DeepHINT, to simultaneously provide accurate prediction of HIV integration sites and mechanistic explanations of the detected sites. Extensive tests on a high-density HIV integration site dataset showed that DeepHINT can outperform conventional modeling strategies by automatically learning the genomic context of HIV integration solely from primary DNA sequence information. Systematic analyses on diverse known factors of HIV integration further validated the biological relevance of the prediction result. More importantly, in-depth analyses of the attention values output by DeepHINT revealed intriguing mechanistic implications in the selection of HIV integration sites, including potential roles of several basic helix-loop-helix (bHLH) transcription factors and zinc-finger proteins. These results established DeepHINT as an effective and explainable deep learning framework for the prediction and mechanistic study of HIV integration.AvailabilityDeepHINT is available as an open-source software and can be downloaded fromhttps://github.com/nonnerdling/[email protected]@tsinghua.edu.cn

scholarly journals Discovery of novel dual adenosine A1/A2A receptor antagonists using deep learning, pharmacophore modeling and molecular docking

2021 ◽  
Vol 17 (3) ◽  
pp. e1008821
Author(s):  
Mukuo Wang ◽  
Shujing Hou ◽  
Yu Wei ◽  
Dongmei Li ◽  
Jianping Lin
Keyword(s):  
Deep Learning ◽  
Molecular Docking ◽  
Drug Targets ◽  
Radioligand Binding ◽  
Md Simulations ◽  
Pharmacophore Modeling ◽  
Functional Assay ◽  
Receptor Antagonists ◽  
Screening Approach

Adenosine receptors (ARs) have been demonstrated to be potential therapeutic targets against Parkinson’s disease (PD). In the present study, we describe a multistage virtual screening approach that identifies dual adenosine A1 and A2A receptor antagonists using deep learning, pharmacophore models, and molecular docking methods. Nineteen hits from the ChemDiv library containing 1,178,506 compounds were selected and further tested by in vitro assays (cAMP functional assay and radioligand binding assay); of these hits, two compounds (C8 and C9) with 1,2,4-triazole scaffolds possessing the most potent binding affinity and antagonistic activity for A1/A2A ARs at the nanomolar level (pKi of 7.16–7.49 and pIC50 of 6.31–6.78) were identified. Further molecular dynamics (MD) simulations suggested similarly strong binding interactions of the complexes between the A1/A2A ARs and two compounds (C8 and C9). Notably, the 1,2,4-triazole derivatives (compounds C8 and C9) were identified as the most potent dual A1/A2A AR antagonists in our study and could serve as a basis for further development. The effective multistage screening approach developed in this study can be utilized to identify potent ligands for other drug targets.

scholarly journals PolypharmDB, a Deep Learning-Based Resource, Quickly Identifies Repurposed Drug Candidates for COVID-19

2020 ◽  
Author(s):  
Dar'ya S. Redka ◽  
Stephen S. MacKinnon ◽  
Melissa Landon ◽  
Andreas Windemuth ◽  
Naheed Kurji ◽  
...  
Keyword(s):  
Deep Learning ◽  
Small Molecule ◽  
Drug Targets ◽  
Therapeutic Potential ◽  
Host Cells ◽  
Therapeutic Interventions ◽  
Clinical Environment ◽  
Drug Candidates ◽  
Small Molecule Drugs

<p>There is an immediate need to discover treatments for COVID-19, the pandemic caused by the SARS-CoV-2 virus. Standard small molecule drug discovery workflows that start with library screens are an impractical path forward given the timelines to discover, develop, and test clinically. To accelerate the time to patient testing, here we explored the therapeutic potential of small molecule drugs that have been tested to some degree in a clinical environment, including approved medications, as possible therapeutic interventions for COVID-19. Motivating our process is a concept termed polypharmacology, i.e. off-target interactions that may hold therapeutic potential. In this work, we used Ligand Design, our deep learning drug design platform, to interrogate the polypharmacological profiles of an internal collection of small molecule drugs with federal approval or going through clinical trials, with the goal of identifying molecules predicted to modulate targets relevant for COVID-19 treatment. Resulting from our efforts is PolypharmDB, a resource of drugs and their predicted binding of protein targets across the human proteome. Mining PolypharmDB yielded molecules predicted to interact with human and viral drug targets for COVID-19, including host proteins linked to viral entry and proliferation and key viral proteins associated with the virus life-cycle. Further, we assembled a collection of prioritized approved drugs for two specific host-targets, TMPRSS2 and cathepsin B, whose joint inhibition was recently shown to block SARS-CoV-2 virus entry into host cells. Overall, we demonstrate that our approach facilitates rapid response, identifying 30 prioritized candidates for testing for their possible use as anti-COVID drugs. Using the PolypharmDB resource, it is possible to identify repurposed drug candidates for newly discovered targets within a single work day. We are making a complete list of the molecules we identified available at no cost to partners with the ability to test them for efficacy, in vitro and/or clinically.</p><div><br></div>

scholarly journals CSGBBNet: An Explainable Deep Learning Framework for COVID-19 Detection

Diagnostics ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 1712
Author(s):  
Xu-Jing Yao ◽  
Zi-Quan Zhu ◽  
Shui-Hua Wang ◽  
Yu-Dong Zhang
Keyword(s):  
Deep Learning ◽  
Binary Classification ◽  
Global Epidemic ◽  
Learning Framework ◽  
The World ◽  
Previous State ◽  
Missed Diagnosis ◽  
Polymerase Chain ◽  
Nucleic Acid Polymerase ◽  
Combined Detection

The COVID-19 virus has swept the world and brought great impact to various fields, gaining wide attention from all walks of life since the end of 2019. At present, although the global epidemic situation is leveling off and vaccine doses have been administered in a large amount, confirmed cases are still emerging around the world. To make up for the missed diagnosis caused by the uncertainty of nucleic acid polymerase chain reaction (PCR) test, utilizing lung CT examination as a combined detection method to improve the diagnostic rate becomes a necessity. Our research considered the time-consuming and labor-intensive characteristics of the traditional CT analyzing process, and developed an efficient deep learning framework named CSGBBNet to solve the binary classification task of COVID-19 images based on a COVID-Seg model for image preprocessing and a GBBNet for classification. The five runs with random seed on the test set showed our novel framework can rapidly analyze CT scan images and give out effective results for assisting COVID-19 detection, with the mean accuracy of 98.49 ± 1.23%, the sensitivity of 99.00 ± 2.00%, the specificity of 97.95 ± 2.51%, the precision of 98.10 ± 2.61%, and the F1 score of 98.51 ± 1.22%. Moreover, our model CSGBBNet performs better when compared with seven previous state-of-the-art methods. In this research, the aim is to link together biomedical research and artificial intelligence and provide some insights into the field of COVID-19 detection.

scholarly journals Antiviral Efficacy of the Novel Compound BIT225 against HIV-1 Release from Human Macrophages

2009 ◽  
Vol 54 (2) ◽  
pp. 835-845 ◽  
Author(s):  
Gabriela Khoury ◽  
Gary Ewart ◽  
Carolyn Luscombe ◽  
Michelle Miller ◽  
John Wilkinson
Keyword(s):  
Drug Targets ◽  
De Novo ◽  
Late Phase ◽  
The Novel ◽  
Peripheral Tissues ◽  
Toxic Concentration ◽  
Virus Integration ◽  
Anti Hiv ◽  
Hiv 1

ABSTRACT Building on previous findings that amiloride analogues inhibit HIV-1 replication in monocyte-derived macrophages (MDM), Biotron Limited has generated a library of over 300 small-molecule compounds with significant improvements in anti-HIV-1 activity. Our lead compound, BIT225, blocks Vpu ion channel activity and also shows anti-HIV-1 activity, with a 50% effective concentration of 2.25 ± 0.23 μM (mean ± the standard error) and minimal in vitro toxicity (50% toxic concentration, 284 μM) in infected MDM, resulting in a selectivity index of 126. In this study, we define the antiretroviral efficacy of BIT225 activity in macrophages, which are important drug targets because cells of the monocyte lineage are key reservoirs of HIV-1, disseminating virus to the peripheral tissues as they differentiate into macrophages. In assays with acutely and chronically HIV-1Ba-L-infected MDM, BIT225 resulted in significant reductions in viral integration and virus release as measured by real-time PCR and a reverse transcriptase (RT) activity assay at various stages of monocyte-to-macrophage differentiation. Further, the TZM-bl assay showed that the de novo virus produced at low levels in the presence of BIT225 was less infectious than virus produced in the absence of the compound. No antiviral activity was observed in MDM chronically infected with HIV-2, which lacks Vpu, confirming our initial targeting of and screening against this viral protein. The activity of BIT225 is post-virus integration, with no direct effects on the HIV-1 enzymes RT and protease. The findings of this study suggest that BIT225 is a late-phase inhibitor of the viral life cycle, targeting Vpu, and is a drug capable of significantly inhibiting HIV-1 release from both acute and chronically infected macrophages.

Prediction of biomarker status, diagnosis and outcome from histology slides using deep learning-based hypothesis free feature extraction.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. 3140-3140
Author(s):  
Eldad Klaiman ◽  
Jacob Gildenblat ◽  
Ido Ben-Shaul ◽  
Astrid Heller ◽  
Konstanty Korski ◽  
...  
Keyword(s):  
Deep Learning ◽  
Binary Classification ◽  
Pathologic Complete Response ◽  
Area Under The Curve ◽  
Response Prediction ◽  
Complete Response ◽  
Algorithm Performance ◽  
New Approach ◽  
Predictive Algorithm ◽  
Learning Framework

3140 Background: Recently, histological pattern signatures obtained from diagnostic H&E images have been found to predict mutation, biomarker status or outcome. We report here on a novel deep learning based framework designed to identify and extract predictive histological signatures. We have applied this framework in 3 experiments, predicting specifically the microsatellite status (MSS) of colorectal cancer (CRC), breast cancer (BC) micrometastasis in Lymph nodes (LN) and Pathologic Complete Response (pCR) in BC diagnostic biopsies. Methods: Our deep learning based algorithm was trained on histology images at 20X magnification. Algorithms were trained for binary classification for each of the three cohorts. We used 75% of the images for training and test our algorithm on the remaining 25% of the images. Cohort details are as follows: MSS for CRC: 94 patients’ H&E stained tissue images from the Roche internal CRC80 dataset (MSS n =24; MSI n = 70) were used. BC LN: 270 patients’ H&E stained tissue images from the CAMELYON16 dataset ( LN(+) n = 110 ; LN(-), n =160) were used. pCR for BC: 225 patients’ H&E stained tissue images from the Tryphaena Study BO22280, neoadjuvant, Trastuzumab/Pertuzumab chemotherapy combination trial. (pCR=111, non-pCR n=114). Results: We report and assess algorithm performance on each of the cohorts by Area Under the Curve (AUC). Prediction of MSS in the CRC80 status yielded AUC 0.9. Prediction of LN invasion on CAMELYON16 dataset yielded AUC 0.85. Prediction of pCR on the Tryphaena cohort yielded an AUC of 0.8. Conclusions: We present a new approach to generate predictive signatures based on conventional diagnostic H&E images and a novel machine learning framework. The CRC80 and CAMELYON16 cohorts served as a confidence building experiments with predictive features well known by clinicians and visually confirmed. The predictive algorithm for pCR in the Tryphaena cohort yielded both response prediction and the high predictive value FOVs. These included tissue patterns which have not until now been considered to influence on the prediction of pCR.

Sign in / Sign up

Export Citation Format

Share Document