A logbook to explore basic medicine in molecules & cells from laboratory to clinic

Dr. Anne Remes' speach in Julie Luo gratulation ceremony, 02.06.2022 Helsinki university Main bulding hall

Dr. Cheng Luo (born October 26, 1958), Porvoo, Finland, Professor in Food Science (Zhejiang Ocean University, Tianjin University of Science and Technology, Senior Research Scientist in virology and medical science (Turku University and Tartu University), Ph. D, Helsinki University, 1993, | World Biographical Encyclopedia (prabook.com)

A Chinese/Finnish scientist, Sichuan University (1978-1982, Chengdu, China), resaech assistant in baceriophages (Vienna University,1988-1989), virus structure (Helsinki U 1989-1993), plant physiology (Umeå U 1996-1998), medicine (Turku U 1998-2003) COX-2 in pancreatic beta-cells. Recipient for traveling support to Hawaii, USA for COX-2 (inhibitor) workshop, Pfizer, 1999, Wang K. Edu. Foundation, Hong Kong, China, 2000. OMRF, USA 2003-04, HKU 2005-2007, Biotechnology: Senior Scientist Tartu U. 2008-2015, Food Sci. Professor Tianjin U 2010-2014, Zhejiang Ocean U 2016-2020.

Current interests:

1, GDNF gene network to artificial neural network

GDNF (Glial cell line-derived neurotrophic factor), a member of the transforming growth factor-beta superfamily, was first identified from glial cells and has the ability to protect midbrain dopaminergic neurons (Engele et al.). ., 1991; Lin et al., 1993), GDNF also applies to the ENS (enteric nervous system). Overexpression or abnormal expression of GDNF is currently known to cause brain tumors, Hirschsprung's disease, especially with neurocognitive function (schizophrenia) and habituation tendencies, such as GDNF has been identified as a potential common addiction-related gene ( For example, drug, alcohol, etc.). This may be because GDNF is expressed in the brain and other neuronal cells.

The main idea is to make a model, or through some ready-made models, to quickly transform the GDNF, or GDNF/PTGS2 gene network into the currently widely recognized neural network, which can be further developed into psychiatry by analyzing certain target genes from individual blood samples. or other clinical applications (APP).

RNN: Recurrent Neural Networks (RNNs) are a class of neural networks that help model sequence data. RNNs are derived from feedforward networks and exhibit behavior similar to how the human brain functions. In short: Recurrent Neural Networks produce predictions in sequential data that other algorithms cannot.

CNN: is a "feedforward neural network" that uses filter and pooling layers, while RNN feeds the results back into the network. In CNN, the size of the input and the resulting output are fixed.

Transformer: Models have been one of the main highlights of the advancement of deep learning and deep neural networks. Transformer neural networks are acyclic models for processing sequential data such as text.

Build neural networks in Python using packages like Keras and TensorFlow.

https://genemania.org/search/homo-sapiens/gdnf/ptgs2

2, Near-Infrared Database System for food safety in real time analysis: The food safety was a big problem in the beginning of 2000, typically melamine in milk powder was caught in media worldwide. And we learn that the NIR spectrometer is becoming smaller and smaller thanks to the linear variable filter (LVF) as modern spectroscopic element replacing the traditional prism, which make it possible to produce pocketable NIR spectrometer. And 5G telecommunication make is possible to do food safety check in real time because the spectra can be locally and remotely analyzed against different molecule database.