Predicting the Lineage Choice of Hematopoietic Stem Cells: A Novel Approach Using Deep Neural Networks

ISBN-13: 9783658128784 / Angielski / Miękka / 2016 / 68 str.

Manuel Kroiss

Opis

Manuel Kroiss examines the differentiation of hematopoietic stem cells using machine learning methods. This work is based on experiments focusing on the lineage choice of CMPs, the progenitors of HSCs, which either become MEP or GMP cells. The author presents a novel approach to distinguish MEP from GMP cells using machine learning on morphology features extracted from bright field images. He tests the performance of different models and focuses on Recurrent Neural Networks with the latest advances from the field of deep learning. Two different improvements to recurrent networks were tested: Long Short Term Memory (LSTM) cells that are able to remember information over long periods of time, and dropout regularization to prevent overfitting. With his method, Manuel Kroiss considerably outperforms standard machine learning methods without time information like Random Forests and Support Vector Machines.

Spis treści

Machine Learning – Deep Learning.- Training Neural Networks.- Recurrent Neural Networks.- Stem Cell Classification Using Microscopy Images.

O autorze

After finishing his MSc in Bioinformatics, Manuel Kroiss moved to London to work for a computer science company. In his work, the author is focusing on algorithmic problem solving while still remaining interested in applied machine learning.

Blurb

Manuel Kroiss examines the differentiation of hematopoietic stem cells using machine learning methods. This work is based on experiments focusing on the lineage choice of CMPs, the progenitors of HSCs, which either become MEP or GMP cells. The author presents a novel approach to distinguish MEP from GMP cells using machine learning on morphology features extracted from bright field images. He tests the performance of different models and focuses on Recurrent Neural Networks with the latest advances from the field of deep learning. Two different improvements to recurrent networks were tested: Long Short Term Memory (LSTM) cells that are able to remember information over long periods of time, and dropout regularization to prevent overfitting. With his method, Manuel Kroiss considerably outperforms standard machine learning methods without time information like Random Forests and Support Vector Machines.

Contents

• Machine Learning – Deep Learning 
• Training Neural Networks
• Recurrent Neural Networks
• Stem Cell Classification Using Microscopy Images

Target Groups 

• Teachers and students in the field of computer science and applied machine learning
• Executives and specialists in the field of neural networks and computational biology

About the Author

After finishing his MSc in Bioinformatics, Manuel Kroiss moved to London to work for a computer science company. In his work, the author is focusing on algorithmic problem solving while still remaining interested in applied machine learning.