285,488 Hits in 6.3 sec

Generative Models for Graph-Based Protein Design

John Ingraham, Vikas K. Garg, Regina Barzilay, Tommi S. Jaakkola
2019 International Conference on Learning Representations  
We develop generative models for protein sequences conditioned on a graph-structured specification of the design target.  ...  Our framework significantly improves upon prior parametric models of protein sequences given structure, and takes a step toward rapid and targeted biomolecular design with the aid of deep generative models  ...  ACKNOWLEDGMENTS We thank members of the MIT MLPDS consortium for helpful feedback and discussions.  ... 
dblp:conf/iclr/IngrahamGBJ19 fatcat:a7yeweu45reolcenvumsr4xvae

Exploration of the relationship between topology and designability of conformations

Sumudu P. Leelananda, Fadi Towfic, Robert L. Jernigan, Andrzej Kloczkowski
2011 Journal of Chemical Physics  
Complementary interaction graphs are then generated for each conformation and are described using a set of graph features.  ...  Lattice models have been utilized in numerous studies to model protein folds and predict the designability of certain folds.  ...  To address this issue, we utilize protein structure graphs to represent lattice models and investigate the relationship between various graph features based on the structure graphs and designable conformations  ... 
doi:10.1063/1.3596947 pmid:21702580 pmcid:PMC3133807 fatcat:odkmqseqnvfr3kqudtrpjyoblu

Dowker complex based machine learning (DCML) models for protein-ligand binding affinity prediction

Xiang Liu, Huitao Feng, Jie Wu, Kelin Xia, Joanna Slusky
2022 PLoS Computational Biology  
However, a major issue remains for all AI-based learning model that is efficient molecular representations.  ...  Our Dowker complex based machine learning models can be used in other tasks in AI-based drug design and molecular data analysis.  ...  Recently, bipartite-graph based interactive matrixes have been used for machine learning models in drug design and achieved great success [20, [30] [31] [32] [33] [34] 40] .  ... 
doi:10.1371/journal.pcbi.1009943 pmid:35385478 pmcid:PMC8985993 fatcat:m5vmvp6guvgnpidjrniegbu64q

Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design [article]

Wengong Jin, Jeremy Wohlwend, Regina Barzilay, Tommi Jaakkola
2022 arXiv   pre-print
Previous generative approaches formulate protein design as a structure-conditioned sequence generation task, assuming the desired 3D structure is given a priori.  ...  In contrast, we propose to co-design the sequence and 3D structure of CDRs as graphs. Our model unravels a sequence autoregressively while iteratively refining its predicted global structure.  ...  Generative models for graph- based protein design. Neural Information Processing Systems, 2019. Wengong Jin, Regina Barzilay, and Tommi Jaakkola.  ... 
arXiv:2110.04624v3 fatcat:7lm2oowyvbfnll253oagjsgzky

Neural networks to learn protein sequence–function relationships from deep mutational scanning data

Sam Gelman, Sarah A. Fahlberg, Pete Heinzelman, Philip A. Romero, Anthony Gitter
2021 Proceedings of the National Academy of Sciences of the United States of America  
Finally, we demonstrate the models' ability to navigate sequence space and design new proteins beyond the training set.  ...  We applied the protein G B1 domain (GB1) models to design a sequence that binds to immunoglobulin G with substantially higher affinity than wild-type GB1.  ...  (D) Process of generating the protein structure graph for Pab1.  ... 
doi:10.1073/pnas.2104878118 pmid:34815338 pmcid:PMC8640744 fatcat:s3zkimuxo5axlho2pnarxrq6fq

Design of structurally distinct proteins using strategies inspired by evolution

T. M. Jacobs, B. Williams, T. Williams, X. Xu, A. Eletsky, J. F. Federizon, T. Szyperski, B. Kuhlman
2016 Science  
High resolution structures of the designed proteins CA01 and DA05R1 were solved by X-ray crystallography (2.2 Å resolution) and NMR respectively, and there was excellent agreement with the design models  ...  Additionally, idealized structures may not always be the most effective starting points for engineering novel protein functions.  ...  The structural variety in the design models for the well-folded proteins is of particular note (Fig. 2) . The SEWING generated models include kinked and curved helices (Fig.  ... 
doi:10.1126/science.aad8036 pmid:27151863 pmcid:PMC4934125 fatcat:fnjfovfzkrcvhoh4p4t5khw6sy

Designing Graphical Data Storage Model for Gene-Protein and Gene-Gene Interaction Networks

Hina Farooq, Javed Ferzund, Azka Mahmood, Muhammad Atif
2017 International Journal of Advanced Computer Science and Applications  
This paper aims at designing a well suited graphical data storage model for biological information which is collected from major heterogeneous biological data repositories, by using graph database.  ...  The large volume of such data posses challenges for data acquisition, data integration, multiple data modalities (either data model of storage model, storage, processing and visualization.  ...  Graph Database Graph Storage Graph Processing Neo4j Native Native OrientDB Native Native Affinity Native Native Dex Native Native HypergraphDB Native Non-Native Allegrograph Native Non-Native FlockDB Non-Native  ... 
doi:10.14569/ijacsa.2017.080559 fatcat:b6wniqvl6zghhlzmhfif734aom

In-Pocket 3D Graphs Enhance Ligand-Target Compatibility in Generative Small-Molecule Creation [article]

Seung-gu Kang, Jeffrey K. Weber, Joseph A. Morrone, Leili Zhang, Tien Huynh, Wendy D. Cornell
2022 arXiv   pre-print
We here present a graph-based generative modeling technology that encodes explicit 3D protein-ligand contacts within a relational graph architecture.  ...  However, three-dimensional representations are absent from most deep-learning-based generative models.  ...  ACKNOWLEDGMENT We thank Sugato Bagchi for assistance in training dataset preparation.  ... 
arXiv:2204.02513v1 fatcat:vj4icboupncrljy7lm6zvdiure

Structure-aware generation of drug-like molecules [article]

Pavol Drotár, Arian Rokkum Jamasb, Ben Day, Cătălina Cangea, Pietro Liò
2021 arXiv   pre-print
Structure-based drug design involves finding ligand molecules that exhibit structural and chemical complementarity to protein pockets.  ...  We propose a novel supervised model that generates molecular graphs jointly with 3D pose in a discretised molecular space.  ...  tasks resembling the docking benchmark: • Multi-molecule design -the task is to generate/design a ligand based on a randomly chosen encoded protein-ligand pair.  ... 
arXiv:2111.04107v1 fatcat:k3riximgtzbxlcezt2iykpndee

Multi-Objective Drug Design Based on Graph-Fragment Molecular Representation and Deep Evolutionary Learning

Muhetaer Mukaidaisi, Andrew Vu, Karl Grantham, Alain Tchagang, Yifeng Li
2022 Frontiers in Pharmacology  
1) integrating a graph fragmentation-based deep generative model with a deep evolutionary learning process for large-scale multi-objective molecular optimization, and (2) applying protein-ligand binding  ...  Motivated by fragment-based drug search for a given protein target and the emergence of artificial intelligence (AI) approaches in this field, this work advances the field of in silico drug design by (  ...  fragment-based method, JTVAE, as the deep generative model for multi-objective molecular optimization.  ... 
doi:10.3389/fphar.2022.920747 pmid:35860028 pmcid:PMC9291509 fatcat:g6xq4hcw3jetvb43x2dtugvd6i

Ollivier persistent Ricci curvature (OPRC) based molecular representation for drug design [article]

JunJie Wee, Kelin Xia
2020 arXiv   pre-print
Efficient molecular featurization is one of the major issues for machine learning models in drug design.  ...  Our OPRC-GBT model is used in the prediction of protein-ligand binding affinity, which is one of key steps in drug design.  ...  Author contributions K.X. designed research; K.X. and J.J. performed research; K.X. and J.J. analyzed data; and K.X. and J.J. wrote the paper.  ... 
arXiv:2011.10281v1 fatcat:rpe6fndbg5hx5af2elkvhjs5ki

Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design [article]

Yue Cao and Payel Das and Vijil Chenthamarakshan and Pin-Yu Chen and Igor Melnyk and Yang Shen
2021 arXiv   pre-print
To overcome these challenges, we propose Fold2Seq, a novel transformer-based generative framework for designing protein sequences conditioned on a specific target fold.  ...  reliability for sequence design, when compared to existing state-of-the-art methods that include data-driven deep generative models and physics-based RosettaDesign.  ...  Fold2Seq for Protein Design Part of the computing resources was provided by the Texas A&M High Performance Research Computing (HPRC).  ... 
arXiv:2106.13058v1 fatcat:a2rpvt4gwvdahc2ghjbnmlsblm

Application advances of deep learning methods for de novo drug design and molecular dynamics simulation

Qifeng Bai, Shuo Liu, Yanan Tian, Tingyang Xu, Antonio Jesús Banegas‐Luna, Horacio Pérez‐Sánchez, Junzhou Huang, Huanxiang Liu, Xiaojun Yao
2021 Wiley Interdisciplinary Reviews. Computational Molecular Science  
The application progress of deep learning is also summarized for MD simulations. Furthermore, IML is introduced for the deep learning model interpretability of de novo drug design and MD simulations.  ...  De novo drug design and MD simulation are effective tools for novel drug discovery.  ...  JR202004)" who provided the grant for this manuscript.  ... 
doi:10.1002/wcms.1581 fatcat:lzwgw6oigbaspcvxuetancbthy

Neural Network-Derived Potts Models for Structure-Based Protein Design using Backbone Atomic Coordinates and Tertiary Motifs [article]

Alex J Li, Mindren Lu, Israel Tilahun Desta, Vikram Sundar, Gevorg Grigoryan, Amy E. Keating
2022 bioRxiv   pre-print
In this work, we combine the two methods to make neural structure-based models more suitable for protein design.  ...  A statistical energy-based framework for modeling protein sequence landscapes using Tertiary Motifs (TERMs) has also demonstrated performance on protein design tasks.  ...  The authors acknowledge Dartmouth Anthill, MGHPCC C3DDB, and MIT SuperCloud for providing high-performance computing resources used to generate research results for this paper. Alex J.  ... 
doi:10.1101/2022.08.02.501736 fatcat:7fqxvugcbrbfbmdhtg5vunii4i

Improved recognition of native-like protein structures using a family of designed sequences

P. Koehl, M. Levitt
2002 Proceedings of the National Academy of Sciences of the United States of America  
Methods Given a protein sequence and a collection of structural models, the aim of our method is to use the sequence information implicit This paper was submitted directly (Track II) to the PNAS office  ...  Abbreviations: RDA, reverse design approach; cRMS, coordinate root-mean-square distance; PDB, Protein Data Bank; RAPDF, residue-specific all-atom conditional probability discriminatory function.  ...  to generate a model for C.  ... 
doi:10.1073/pnas.022408799 pmid:11782533 pmcid:PMC117367 fatcat:5zoe36egd5hpteg6teqajvztxa
« Previous Showing results 1 — 15 out of 285,488 results