Jiaqi Guan

Advances in biomolecular modeling have broadened the range of problems addressable by structure prediction and design models. Here, we present results from Protenix-v2 , a system spanning high-accuracy structure prediction and biomolecular design. On the structure prediction side, Protenix-v2 achieves antibody-antigen success rates with up to 13-point gains over Protenix-v1, while 5-seed performance surpasses previous 1000-seed results . On the design side, Protenix-v2 demonstrates a 100% target-level success rate in novelty-controlled VHH-Fc campaigns, reaching hit rates up to 48%. Crucially, the model enables hit discovery on difficult GPCR targets with hit rates of 16%–88% (VHH-Fc) and up to 50% (mAb) under 16–30 testing budgets per target. Resulting hits show high developability and diversity . Beyond antibody tasks, we report improved ligand-related plausibility and successful cross-variant SARS-CoV-2 spike RBD mini-binder design. These results establish Protenix-v2 as a robust and powerful model for accelerated drug discovery.

The omnidirectional wireless power transmission (WPT) technology have higher degree of freedom and less limitation in direction and space than the traditional WPT technology. This paper proposes a novel three-dimensional transmitter for omnidirectional wireless power transmission technology research. First, the magnetic field intensity distribution generated when three Tx coils are fed with different current phases is evaluated and analyzed. Then, the circuit topology of the system was analyzed and the mutual inductance between the transmitter (Tx) and receiver (Rx) coils was derived. Finally, an omnidirectional WPT experimental system was set up to validate all theoretical analyses.

Automatically reasoning about future human behaviors is a difficult problem but has significant practical applications to assistive systems. Part of this difficulty stems from learning systems' inability to represent all kinds of behaviors. Some behaviors, such as motion, are best described with continuous representations, whereas others, such as picking up a cup, are best described with discrete representations. Furthermore, human behavior is generally not fixed: people can change their habits and routines. This suggests these systems must be able to learn and adapt continuously. In this work, we develop an efficient deep generative model to jointly forecast a person's future discrete actions and continuous motions. On a large-scale egocentric dataset, EPIC-KITCHENS, we observe our method generates high-quality and diverse samples while exhibiting better generalization than related generative models. Finally, we propose a variant to continually learn our model from streaming data, observe its practical effectiveness, and theoretically justify its learning efficiency.

Machine learning (ML) and Natural Language Processing (NLP) have achieved remarkable success in many fields and have brought new opportunities and high expectation in the analyses of medical data, of which the most common type is the massive free-text electronic medical records (EMR). However, the free EMR texts are lacking consistent standards, rich of private information, and limited in availability. Also, it is often hard to have a balanced number of samples for the types of diseases under study. These problems hinder the development of ML and NLP methods for EMR data analysis. To tackle these problems, we developed a model called Medical Text Generative Adversarial Network or mtGAN, to generate synthetic EMR text. It is based on the GAN framework and is trained by the REINFORCE algorithm. It takes disease features as inputs and generates synthetic texts as EMRs for the corresponding diseases. We evaluate the model from micro-level, macro-level and application-level on a Chinese EMR text dataset. The results show that the method has a good capacity to fit real data and can generate realistic and diverse EMR samples. This provides a novel way to avoid potential leakage of patient privacy while still supply sufficient well-controlled cohort data for developing downstream ML and NLP methods.