Multi-objective Deep Data Generation with Correlated Property Control

Abstract

Developing deep generative models has been an emerging field due to the ability to model and generate complex data for various purposes, such as image synthesis and molecular design. However, the advancement of deep generative models is limited by challenges to generate objects that possess multiple desired properties: 1) the existence of complex correlation among real-world properties is common but hard to identify; 2) controlling individual property enforces an implicit partially control of its correlated properties, which is difficult to model; 3) controlling multiple properties under various manners simultaneously is hard and under-explored. We address these challenges by proposing a novel deep generative framework, CorrVAE, that recovers semantics and the correlation of properties through disentangled latent vectors. The correlation is handled via an explainable mask pooling layer, and properties are precisely retained by generated objects via the mutual dependence between latent vectors and properties. Our generative model preserves properties of interest while handling correlation and conflicts of properties under a multi-objective optimization framework. The experiments demonstrate our model's superior performance in generating data with desired properties. The code of CorrVAE is available at https://github.com/shi-yu-wang/CorrVAE.

Atom Economical QPCs: Phenyl-Free Biscationic Quaternary Phosphonium Compounds as Potent Disinfectants

“…Notable pathogens such as A. baumannii and P. aeruginosa have developed sufficient resistance mechanisms toward common disinfectants that they are renewing the problem of bacterial infections in hospital, domestic, and commercial settings. − In order to combat the growing problem of antimicrobial resistance (AMR), ongoing efforts toward the synthesis and antimicrobial evaluation of novel QACs are underway . Along these lines, our groups have systematically evaluated a variety of QAC structural motifs to identify molecular features that can inform the rational design of new classes of disinfectants; we have recently advanced to machine learning techniques to predict the bioactivity of proposed compounds . Despite the development of over 700 different compounds by our groups in the past decade, concerns remain about the cross-resistance in AMR mechanisms between established QACs such as BAC into any novel QAC. , Accordingly, exploration of molecules with markedly different cationic amphiphilic heads, such as quaternary phosphonium compounds (QPCs) − and trivalent sulfonium compounds (TSCs), − are being pursued.…”

“… 11 Along these lines, our groups have systematically evaluated a variety of QAC structural motifs to identify molecular features that can inform the rational design of new classes of disinfectants; we have recently advanced to machine learning techniques to predict the bioactivity of proposed compounds. 12 Despite the development of over 700 different compounds by our groups in the past decade, concerns remain about the cross-resistance in AMR mechanisms 13 between established QACs such as BAC into any novel QAC. 3 , 10 Accordingly, exploration of molecules with markedly different cationic amphiphilic heads, such as quaternary phosphonium compounds (QPCs) 14 − 19 and trivalent sulfonium compounds (TSCs), 20 − 22 are being pursued.…”