中央研究院 資訊科學研究所

Increases in throughput and installed base ofbiomedical research equipment led to a massive accumulationof ‘omics’ data known to be highly variable, high-dimensional,and sourced from multiple often incompatible data platform. These kinds of ‘omics’ data, which include the genome sequencing data (genomics), microarray-based genome-wide expression profiles (transcriptomics), protein abundances data (proteomics), etc., provide unprecedented views of cellular components in the biological systems. We are now formally in the Million-Genome era. However, given this massive amount of data (Big Data), how do we know which information or feature is crucial towards certain diseases or behaviors? This is similar to finding a needle in a haystack. A systematic viewpoint and methodology to retrieve biological insights from these data is hence essential.

The field of artificial intelligence (AI) is a thriving field, in which intelligent agents perceive their environments (in the form of data) and take actions that maximize their chance of successfully achieving their goals. The age of “Big Data” and the rapid improvement of computational capability of hardware have made AI (deep learning) viable to handle many practical problems. Since 2006, major breakthroughs have been observed in many fields, including image and audio data processing, via applying deep learning to tackle the most challenging problems in these fields. We believe that the new wave of breakthroughs should lie in the areas of medicine and biology, in which enormous amount of data has been made available.

In this talk, I hope to provide a brief introduction to our recent results on this interdisciplinary and exciting field, in which AI (deep learning) and systems biology were integrated to provide precision medicine for cancers and to build predictive models for docking algorithms in drug discovery. I will provide two examples demonstrating how such integration can lead to a) accurate prediction of patient prognosis of NSCLC, and b) predictive models that effectively estimate the sizes of residue fluctuations in proteins. The aim of this talk is to provide a platform for researchers with biological or AI backgrounds to share ideas and collaborate. Researchers with either backgrounds are welcomed to join us!

Che Lin received the B.S. degree in Electrical Engineering from National Taiwan University, Taipei, Taiwan, in 1999. He received the M.S. degree in Electrical and Computer Engineering in 2003, the M.S. degree in Math in 2008, and the Ph.D. degree in Electrical and Computer Engineering in 2008, all from the University of Illinois at Urbana-Champaign, IL. In 2008, he joined the Department of Electrical Engineering at National Tsing Hua University as an assistant professor, and has been an associate professor since August 2014.

Dr. Lin received a two-year Vodafone graduate fellowship in 2006, the E. A. Reid fellowship award in 2008, and holds a U.S. patent, which has been included in the 3GPP LTE standard. In 2012, he received the Excellent Teaching Award for the college of EECS, NTHU. He won the best paper award for 2014 GIW-ISCB-ASIA conference. In 2015, he received the CIEE outstanding young electrical engineer Award. In 2017, he received the Young Scholar Innovation Award from Foundation For The Advancement Of Outstanding Scholarship. He is a senior member of IEEE.

His research interests include deep learning, data mining and analytic, signal processing in wireless communications, optimization theory, and systems biology.