Liang Huang

US Patent:

20220269951, Aug 25, 2022

Filed:

Feb 24, 2021

Appl. No.:

17/184505

Inventors:

- Sunnyvale CA, US
Liang ZHANG - Fremont CA, US
Ziyu LI - South San Francisco CA, US
Kaibo LIU - Sunnyvale CA, US
Boxiang LIU - Sunnyvale CA, US
Liang HUANG - Mountain View CA, US

Assignee:

Baidu USA LLC - Sunnyvale CA

International Classification:

G06N 3/12
A61K 39/215

Abstract:

A messenger RNA (mRNA) vaccine has emerged as a promising direction to combat the COVID-19 pandemic. This requires an mRNA sequence that is stable and highly productive in protein expression, features to benefit from greater mRNA secondary structure folding stability and optimal codon usage. Sequence design remains challenging due to the exponentially many synonymous mRNA sequences encoding the same protein. The present disclosure presents embodiments of a linear-time approximation (LinearDesign) reducing the design to an intersection between a Stochastic Context Free Grammar (SCFG) and a Deterministic Finite Automaton (DFA). Embodiments of the LinearDesign may implement an mRNA sequence design using much reduced time with very limited loss. Various methodologies, e.g., finding alternative sequences based on k-best parsing or directly incorporating codon optimality, are presented for incorporating the codon optimality into the design. Embodiments of the LinearDesign may provide efficient computational tools to speed up and improve mRNA vaccine development.

US Patent:

20200104371, Apr 2, 2020

Filed:

May 10, 2019

Appl. No.:

16/409503

Inventors:

- Sunnyvale CA, US
Liang HUANG - Mountain View CA, US
Hao XIONG - Beijing, CN
Kaibo LIU - Sunnyvale CA, US
Chuanqiang ZHANG - Beijing, CN
Renjie ZHENG - Corvallis OR, US
Zhongjun HE - Beijing, CN
Hairong LIU - San Jose CA, US
Xing LI - Santa Clara CA, US
Hua Wu - Beijing, CN
Haifeng WANG - Beijing, CN

Assignee:

Baidu USA LLC - Sunnyvale CA

International Classification:

G06F 17/28
G06F 17/27
G06N 3/08

Abstract:

Presented herein are embodiments of a prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipates in a single translation. Within these frameworks are effective “wait-k” policy model embodiments that may be trained to generate a target sentence concurrently with a source sentence but lag behind by a predefined number of words. Embodiments of the prefix-to-prefix framework achieve low latency and better quality when compared to full-sentence translation in four directions: Chinese↔English and German↔English. Also presented herein is a novel latency metric that addresses deficiencies of previous latency metrics.