LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 28

Search options

  1. Book ; Online: Learn the Force We Can

    Davtyan, Aram / Favaro, Paolo

    Enabling Sparse Motion Control in Multi-Object Video Generation

    2023  

    Abstract: We propose a novel unsupervised method to autoregressively generate videos from a single frame and a sparse motion input. Our trained model can generate unseen realistic object-to-object interactions. Although our model has never been given the explicit ... ...

    Abstract We propose a novel unsupervised method to autoregressively generate videos from a single frame and a sparse motion input. Our trained model can generate unseen realistic object-to-object interactions. Although our model has never been given the explicit segmentation and motion of each object in the scene during training, it is able to implicitly separate their dynamics and extents. Key components in our method are the randomized conditioning scheme, the encoding of the input motion control, and the randomized and sparse sampling to enable generalization to out of distribution but realistic correlations. Our model, which we call YODA, has therefore the ability to move objects without physically touching them. Through extensive qualitative and quantitative evaluations on several datasets, we show that YODA is on par with or better than state of the art video generation prior work in terms of both controllability and video quality.

    Comment: Accepted to AAAI 2024. Project website: https://araachie.github.io/yoda
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Artificial Intelligence
    Subject code 004
    Publishing date 2023-06-06
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Book ; Online: Controllable Video Generation through Global and Local Motion Dynamics

    Davtyan, Aram / Favaro, Paolo

    2022  

    Abstract: We present GLASS, a method for Global and Local Action-driven Sequence Synthesis. GLASS is a generative model that is trained on video sequences in an unsupervised manner and that can animate an input image at test time. The method learns to segment ... ...

    Abstract We present GLASS, a method for Global and Local Action-driven Sequence Synthesis. GLASS is a generative model that is trained on video sequences in an unsupervised manner and that can animate an input image at test time. The method learns to segment frames into foreground-background layers and to generate transitions of the foregrounds over time through a global and local action representation. Global actions are explicitly related to 2D shifts, while local actions are instead related to (both geometric and photometric) local deformations. GLASS uses a recurrent neural network to transition between frames and is trained through a reconstruction loss. We also introduce W-Sprites (Walking Sprites), a novel synthetic dataset with a predefined action space. We evaluate our method on both W-Sprites and real datasets, and find that GLASS is able to generate realistic video sequences from a single input image and to successfully learn a more advanced action space than in prior work.
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Artificial Intelligence
    Subject code 006
    Publishing date 2022-04-13
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Book ; Online: Multi-View Unsupervised Image Generation with Cross Attention Guidance

    Cerkezi, Llukman / Davtyan, Aram / Sameni, Sepehr / Favaro, Paolo

    2023  

    Abstract: The growing interest in novel view synthesis, driven by Neural Radiance Field (NeRF) models, is hindered by scalability issues due to their reliance on precisely annotated multi-view images. Recent models address this by fine-tuning large text2image ... ...

    Abstract The growing interest in novel view synthesis, driven by Neural Radiance Field (NeRF) models, is hindered by scalability issues due to their reliance on precisely annotated multi-view images. Recent models address this by fine-tuning large text2image diffusion models on synthetic multi-view data. Despite robust zero-shot generalization, they may need post-processing and can face quality issues due to the synthetic-real domain gap. This paper introduces a novel pipeline for unsupervised training of a pose-conditioned diffusion model on single-category datasets. With the help of pretrained self-supervised Vision Transformers (DINOv2), we identify object poses by clustering the dataset through comparing visibility and locations of specific object parts. The pose-conditioned diffusion model, trained on pose labels, and equipped with cross-frame attention at inference time ensures cross-view consistency, that is further aided by our novel hard-attention guidance. Our model, MIRAGE, surpasses prior work in novel view synthesis on real images. Furthermore, MIRAGE is robust to diverse textures and geometries, as demonstrated with our experiments on synthetic images generated with pretrained Stable Diffusion.
    Keywords Computer Science - Computer Vision and Pattern Recognition
    Subject code 006 ; 004
    Publishing date 2023-12-07
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Article ; Online: Theoretical insights into mechanisms of channel-facilitated molecular transport in the presence of stochastic gating.

    Davtyan, Aram / Kolomeisky, Anatoly B

    The Journal of chemical physics

    2019  Volume 150, Issue 12, Page(s) 124111

    Abstract: Molecular motion through pores plays a crucial role in various natural and industrial processes. One of the most fascinating features of biological channel-facilitated transport is a stochastic gating process, when the channels dynamically fluctuate ... ...

    Abstract Molecular motion through pores plays a crucial role in various natural and industrial processes. One of the most fascinating features of biological channel-facilitated transport is a stochastic gating process, when the channels dynamically fluctuate between several conformations during the translocation. Although this phenomenon has been intensively investigated, many properties of translocation in a dynamically changing environment remain not well understood microscopically. We developed a discrete-state stochastic framework to analyze the molecular mechanisms of transport processes with stochastic gating by explicitly calculating molecular fluxes through the pores. Two scenarios are specifically investigated: (1) symmetry preserving stochastic gating with free-energy changes and (2) stochastic gating with symmetry changes but without modifications in the overall particle-pore interactions. It is found that stochastic gating can either accelerate or slow down the molecular translocation depending on the specific parameters of the system. We argue that biological systems might optimize their performance by utilizing conformational fluctuations of channels. Our theoretical analysis clarifies physical-chemical aspects of the molecular mechanisms of transport with stochastic gating.
    MeSH term(s) Kinetics ; Membrane Transport Proteins/chemistry ; Models, Chemical ; Stochastic Processes ; Thermodynamics
    Chemical Substances Membrane Transport Proteins
    Language English
    Publishing date 2019-03-23
    Publishing country United States
    Document type Journal Article
    ZDB-ID 3113-6
    ISSN 1089-7690 ; 0021-9606
    ISSN (online) 1089-7690
    ISSN 0021-9606
    DOI 10.1063/1.5086224
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    In stock of ZB MED Bonn / Germany

    Z 4' 49/16: Show issues

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Book ; Online: Efficient Video Prediction via Sparsely Conditioned Flow Matching

    Davtyan, Aram / Sameni, Sepehr / Favaro, Paolo

    2022  

    Abstract: We introduce a novel generative model for video prediction based on latent flow matching, an efficient alternative to diffusion-based models. In contrast to prior work, we keep the high costs of modeling the past during training and inference at bay by ... ...

    Abstract We introduce a novel generative model for video prediction based on latent flow matching, an efficient alternative to diffusion-based models. In contrast to prior work, we keep the high costs of modeling the past during training and inference at bay by conditioning only on a small random set of past frames at each integration step of the image generation process. Moreover, to enable the generation of high-resolution videos and to speed up the training, we work in the latent space of a pretrained VQGAN. Finally, we propose to approximate the initial condition of the flow ODE with the previous noisy frame. This allows to reduce the number of integration steps and hence, speed up the sampling at inference time. We call our model Random frame conditioned flow Integration for VidEo pRediction, or, in short, RIVER. We show that RIVER achieves superior or on par performance compared to prior work on common video prediction benchmarks, while requiring an order of magnitude fewer computational resources.

    Comment: Accepted to ICCV 2023. Project page: https://araachie.github.io/river
    Keywords Computer Science - Computer Vision and Pattern Recognition
    Subject code 004
    Publishing date 2022-11-26
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Article: Discovery of a cryptic pocket in the AI-predicted structure of PPM1D phosphatase explains the binding site and potency of its allosteric inhibitors.

    Meller, Artur / de Oliveira, Saulo / Davtyan, Aram / Abramyan, Tigran / Bowman, Gregory R / van den Bedem, Henry

    bioRxiv : the preprint server for biology

    2023  

    Abstract: Virtual screening is a widely used tool for drug discovery, but its predictive power can vary dramatically depending on how much structural data is available. In the best case, crystal structures of a ligand-bound protein can help find more potent ... ...

    Abstract Virtual screening is a widely used tool for drug discovery, but its predictive power can vary dramatically depending on how much structural data is available. In the best case, crystal structures of a ligand-bound protein can help find more potent ligands. However, virtual screens tend to be less predictive when only ligand-free crystal structures are available, and even less predictive if a homology model or other predicted structure must be used. Here, we explore the possibility that this situation can be improved by better accounting for protein dynamics, as simulations started from a single structure have a reasonable chance of sampling nearby structures that are more compatible with ligand binding. As a specific example, we consider the cancer drug target PPM1D/Wip1 phosphatase, a protein that lacks crystal structures. High-throughput screens have led to the discovery of several allosteric inhibitors of PPM1D, but their binding mode remains unknown. To enable further drug discovery efforts, we assessed the predictive power of an AlphaFold-predicted structure of PPM1D and a Markov state model (MSM) built from molecular dynamics simulations initiated from that structure. Our simulations reveal a cryptic pocket at the interface between two important structural elements, the flap and hinge regions. Using deep learning to predict the pose quality of each docked compound for the active site and cryptic pocket suggests that the inhibitors strongly prefer binding to the cryptic pocket, consistent with their allosteric effect. The predicted affinities for the dynamically uncovered cryptic pocket also recapitulate the relative potencies of the compounds (τ
    Language English
    Publishing date 2023-03-24
    Publishing country United States
    Document type Preprint
    DOI 10.1101/2023.03.22.533829
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  7. Article: AI-powered discovery of a novel p53-Y220C reactivator.

    Zhou, Shan / Chai, Dafei / Wang, Xu / Neeli, Praveen / Yu, Xinfang / Davtyan, Aram / Young, Ken / Li, Yong

    Frontiers in oncology

    2023  Volume 13, Page(s) 1229696

    Abstract: Introduction: The : Methods: In this study, we applied artificial intelligence (AI)-powered virtual screening to identify small-molecule compounds that specifically restore the wild-type p53 conformation from p53-Y220C. From 10 million compounds, the ...

    Abstract Introduction: The
    Methods: In this study, we applied artificial intelligence (AI)-powered virtual screening to identify small-molecule compounds that specifically restore the wild-type p53 conformation from p53-Y220C. From 10 million compounds, the AI algorithm selected a chemically diverse set of 83 high-scoring hits, which were subjected to several experimental assays using cell lines with different p53 mutations.
    Results: We identified one compound, H3, that preferentially killed cells with the
    Conclusion: AI enabled the discovery of the H3 compound that selectively reactivates the p53-Y220C mutant and inhibits tumor development in mice.
    Language English
    Publishing date 2023-08-01
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2649216-7
    ISSN 2234-943X
    ISSN 2234-943X
    DOI 10.3389/fonc.2023.1229696
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  8. Article: Discovery of a cryptic pocket in the AI-predicted structure of PPM1D phosphatase explains the binding site and potency of its allosteric inhibitors.

    Meller, Artur / De Oliveira, Saulo / Davtyan, Aram / Abramyan, Tigran / Bowman, Gregory R / van den Bedem, Henry

    Frontiers in molecular biosciences

    2023  Volume 10, Page(s) 1171143

    Abstract: Virtual screening is a widely used tool for drug discovery, but its predictive power can vary dramatically depending on how much structural data is available. In the best case, crystal structures of a ligand-bound protein can help find more potent ... ...

    Abstract Virtual screening is a widely used tool for drug discovery, but its predictive power can vary dramatically depending on how much structural data is available. In the best case, crystal structures of a ligand-bound protein can help find more potent ligands. However, virtual screens tend to be less predictive when only ligand-free crystal structures are available, and even less predictive if a homology model or other predicted structure must be used. Here, we explore the possibility that this situation can be improved by better accounting for protein dynamics, as simulations started from a single structure have a reasonable chance of sampling nearby structures that are more compatible with ligand binding. As a specific example, we consider the cancer drug target PPM1D/Wip1 phosphatase, a protein that lacks crystal structures. High-throughput screens have led to the discovery of several allosteric inhibitors of PPM1D, but their binding mode remains unknown. To enable further drug discovery efforts, we assessed the predictive power of an AlphaFold-predicted structure of PPM1D and a Markov state model (MSM) built from molecular dynamics simulations initiated from that structure. Our simulations reveal a cryptic pocket at the interface between two important structural elements, the flap and hinge regions. Using deep learning to predict the pose quality of each docked compound for the active site and cryptic pocket suggests that the inhibitors strongly prefer binding to the cryptic pocket, consistent with their allosteric effect. The predicted affinities for the dynamically uncovered cryptic pocket also recapitulate the relative potencies of the compounds (τ
    Language English
    Publishing date 2023-04-18
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2814330-9
    ISSN 2296-889X
    ISSN 2296-889X
    DOI 10.3389/fmolb.2023.1171143
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  9. Article ; Online: Artificial intelligence-powered discovery of small molecules inhibiting CTLA-4 in cancer.

    Sobhani, Navid / Tardiel-Cyril, Dana Rae / Chai, Dafei / Generali, Daniele / Li, Jian-Rong / Vazquez-Perez, Jonathan / Lim, Jing Ming / Morris, Rachel / Bullock, Zaniqua N / Davtyan, Aram / Cheng, Chao / Decker, William K / Li, Yong

    BJC reports

    2024  Volume 2

    Abstract: Background/objectives: Checkpoint inhibitors, which generate durable responses in many cancer patients, have revolutionized cancer immunotherapy. However, their therapeutic efficacy is limited, and immune-related adverse events are severe, especially ... ...

    Abstract Background/objectives: Checkpoint inhibitors, which generate durable responses in many cancer patients, have revolutionized cancer immunotherapy. However, their therapeutic efficacy is limited, and immune-related adverse events are severe, especially for monoclonal antibody treatment directed against cytotoxic T-lymphocyte-associated protein 4 (CTLA-4), which plays a pivotal role in preventing autoimmunity and fostering anticancer immunity by interacting with the B7 proteins CD80 and CD86. Small molecules impairing the CTLA-4/CD80 interaction have been developed; however, they directly target CD80, not CTLA-4.
    Subjects/methods: In this study, we performed artificial intelligence (AI)-powered virtual screening of approximately ten million compounds to identify those targeting CTLA-4. We validated the hits molecules with biochemical, biophysical, immunological, and experimental animal assays.
    Results: The primary hits obtained from the virtual screening were successfully validated in vitro and in vivo. We then optimized lead compounds and obtained inhibitors (inhibitory concentration, 1 micromole) that disrupted the CTLA-4/CD80 interaction without degrading CTLA-4.
    Conclusions: Several compounds inhibited tumor development prophylactically and therapeutically in syngeneic and CTLA-4-humanized mice. Our findings support using AI-based frameworks to design small molecules targeting immune checkpoints for cancer therapy.
    Language English
    Publishing date 2024-01-23
    Publishing country England
    Document type Journal Article
    ISSN 2731-9377
    ISSN (online) 2731-9377
    DOI 10.1038/s44276-023-00035-5
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  10. Article: CTLA-4 in Regulatory T Cells for Cancer Immunotherapy.

    Sobhani, Navid / Tardiel-Cyril, Dana Rae / Davtyan, Aram / Generali, Daniele / Roudi, Raheleh / Li, Yong

    Cancers

    2021  Volume 13, Issue 6

    Abstract: Immune checkpoint inhibitors (ICIs) have obtained durable responses in many cancers, making it possible to foresee their potential in improving the health of cancer patients. However, immunotherapies are currently limited to a minority of patients and ... ...

    Abstract Immune checkpoint inhibitors (ICIs) have obtained durable responses in many cancers, making it possible to foresee their potential in improving the health of cancer patients. However, immunotherapies are currently limited to a minority of patients and there is a need to develop a better understanding of the basic molecular mechanisms and functions of pivotal immune regulatory molecules. Immune checkpoint cytotoxic T-lymphocyte-associated protein 4 (CTLA-4) and regulatory T (T
    Language English
    Publishing date 2021-03-22
    Publishing country Switzerland
    Document type Journal Article ; Review
    ZDB-ID 2527080-1
    ISSN 2072-6694
    ISSN 2072-6694
    DOI 10.3390/cancers13061440
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

To top