Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAnalysis of training and seed bias in small molecules generated with a conditional graph-based variational autoencoder -- Insights for practical AI-driven molecule generation
158
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
The application of deep learning to generative molecule design has shown early promise for accelerating lead series development. However, questions remain concerning how factors like training, dataset, and seed bias impact the technologys utility to medicine and computational chemists. In this work, we analyze the impact of seed and training bias on the output of an activity-conditioned graph-based variational autoencoder (VAE). Leveraging a massive, labeled dataset corresponding to the dopamine D2 receptor, our graph-based generative model is shown to excel in producing desired conditioned activities and favorable unconditioned physical properties in generated molecules. We implement an activity swapping method that allows for the activation, deactivation, or retention of activity of molecular seeds, and we apply independent deep learning classifiers to verify the generative results. Overall, we uncover relationships between noise, molecular seeds, and training set selection across a range of latent-space sampling procedures, providing important insights for practical AI-driven molecule generation.
rate research
Read More
We investigate large-scale latent variable models (LVMs) for neural story generation -- an under-explored application for open-domain long text -- with objectives in two threads: generation effectiveness and controllability. LVMs, especially the variational autoencoder (VAE), have achieved both effective and controllable generation through exploiting flexible distributional latent representations. Recently, Transformers and its variants have achieved remarkable effectiveness without explicit latent representation learning, thus lack satisfying controllability in generation. In this paper, we advocate to revive latent variable modeling, essentially the power of representation learning, in the era of Transformers to enhance controllability without hurting state-of-the-art generation effectiveness. Specifically, we integrate latent representation vectors with a Transformer-based pre-trained architecture to build conditional variational autoencoder (CVAE). Model components such as encoder, decoder and the variational posterior are all built on top of pre-trained language models -- GPT2 specifically in this paper. Experiments demonstrate state-of-the-art conditional generation ability of our model, as well as its excellent representation learning capability and controllability.
As camera pixel arrays have grown larger and faster, and optical microscopy techniques ever more refined, there has been an explosion in the quantity of data acquired during routine light microcopy. At the single-molecule level, analysis involves multiple steps and can rapidly become computationally expensive, in some cases intractable on office workstations. Complex bespoke software can present high activation barriers to entry for new users. Here, we redevelop our quantitative single-molecule analysis routines into an optimized and extensible Python program, with GUI and command-line implementations to facilitate use on local machines and remote clusters, by beginners and advanced users alike. We demonstrate that its performance is on par with previous MATLAB implementations but runs an order of magnitude faster. We tested it against challenge data and demonstrate its performance is comparable to state-of-the-art analysis platforms. We show the code can extract fluorescence intensity values for single reporter dye molecules and, using these, estimate molecular stoichiometries and cellular copy numbers of fluorescently-labeled biomolecules. It can evaluate 2D diffusion coefficients for the characteristically short single-particle tracking data. To facilitate benchmarking we include data simulation routines to compare different analysis programs. Finally, we show that it works with 2-color data and enables colocalization analysis based on overlap integration, to infer interactions between differently labelled biomolecules. By making this freely available we aim to make complex light microscopy single-molecule analysis more democratized.
Researchers across the globe are seeking to rapidly repurpose existing drugs or discover new drugs to counter the the novel coronavirus disease (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). One promising approach is to train machine learning (ML) and artificial intelligence (AI) tools to screen large numbers of small molecules. As a contribution to that effort, we are aggregating numerous small molecules from a variety of sources, using high-performance computing (HPC) to computer diverse properties of those molecules, using the computed properties to train ML/AI models, and then using the resulting models for screening. In this first data release, we make available 23 datasets collected from community sources representing over 4.2 B molecules enriched with pre-computed: 1) molecular fingerprints to aid similarity searches, 2) 2D images of molecules to enable exploration and application of image-based deep learning methods, and 3) 2D and 3D molecular descriptors to speed development of machine learning models. This data release encompasses structural information on the 4.2 B molecules and 60 TB of pre-computed data. Future releases will expand the data to include more detailed molecular simulations, computed models, and other products.
Molecule generation is to design new molecules with specific chemical properties and further to optimize the desired chemical properties. Following previous work, we encode molecules into continuous vectors in the latent space and then decode the vectors into molecules under the variational autoencoder (VAE) framework. We investigate the posterior collapse problem of current RNN-based VAEs for molecule sequence generation. For the first time, we find that underestimated reconstruction loss leads to posterior collapse, and provide both theoretical and experimental evidence. We propose an effective and efficient solution to fix the problem and avoid posterior collapse. Without bells and whistles, our method achieves SOTA reconstruction accuracy and competitive validity on the ZINC 250K dataset. When generating 10,000 unique valid SMILES from random prior sampling, it costs JT-VAE1450s while our method only needs 9s. Our implementation is at https://github.com/chaoyan1037/Re-balanced-VAE.
This paper presents an emotion-regularized conditional variational autoencoder (Emo-CVAE) model for generating emotional conversation responses. In conventional CVAE-based emotional response generation, emotion labels are simply used as additional conditions in prior, posterior and decoder networks. Considering that emotion styles are naturally entangled with semantic contents in the language space, the Emo-CVAE model utilizes emotion labels to regularize the CVAE latent space by introducing an extra emotion prediction network. In the training stage, the estimated latent variables are required to predict the emotion labels and token sequences of the input responses simultaneously. Experimental results show that our Emo-CVAE model can learn a more informative and structured latent space than a conventional CVAE model and output responses with better content and emotion performance than baseline CVAE and sequence-to-sequence (Seq2Seq) models.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
