Feiyang Ma1, Matteo Pellegrini1,2. 1. Molecular Biology Institute, University of California, Los Angeles, CA, USA. 2. Institute of Genomics and Proteomics, University of California, Los Angeles, CA, USA.
Abstract
MOTIVATION: Cell type identification is one of the major goals in single cell RNA sequencing (scRNA-seq). Current methods for assigning cell types typically involve the use of unsupervised clustering, the identification of signature genes in each cluster, followed by a manual lookup of these genes in the literature and databases to assign cell types. However, there are several limitations associated with these approaches, such as unwanted sources of variation that influence clustering and a lack of canonical markers for certain cell types. Here, we present ACTINN (Automated Cell Type Identification using Neural Networks), which employs a neural network with three hidden layers, trains on datasets with predefined cell types and predicts cell types for other datasets based on the trained parameters. RESULTS: We trained the neural network on a mouse cell type atlas (Tabula Muris Atlas) and a human immune cell dataset, and used it to predict cell types for mouse leukocytes, human PBMCs and human T cell sub types. The results showed that our neural network is fast and accurate, and should therefore be a useful tool to complement existing scRNA-seq pipelines. AVAILABILITY AND IMPLEMENTATION: The codes and datasets are available at https://figshare.com/articles/ACTINN/8967116. Tutorial is available at https://github.com/mafeiyang/ACTINN. All codes are implemented in python. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
MOTIVATION: Cell type identification is one of the major goals in single cell RNA sequencing (scRNA-seq). Current methods for assigning cell types typically involve the use of unsupervised clustering, the identification of signature genes in each cluster, followed by a manual lookup of these genes in the literature and databases to assign cell types. However, there are several limitations associated with these approaches, such as unwanted sources of variation that influence clustering and a lack of canonical markers for certain cell types. Here, we present ACTINN (Automated Cell Type Identification using Neural Networks), which employs a neural network with three hidden layers, trains on datasets with predefined cell types and predicts cell types for other datasets based on the trained parameters. RESULTS: We trained the neural network on a mouse cell type atlas (Tabula Muris Atlas) and a human immune cell dataset, and used it to predict cell types for mouse leukocytes, human PBMCs and human T cell sub types. The results showed that our neural network is fast and accurate, and should therefore be a useful tool to complement existing scRNA-seq pipelines. AVAILABILITY AND IMPLEMENTATION: The codes and datasets are available at https://figshare.com/articles/ACTINN/8967116. Tutorial is available at https://github.com/mafeiyang/ACTINN. All codes are implemented in python. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Authors: Carol C L Chen; Shriya Deshmukh; Selin Jessa; Djihad Hadjadj; Véronique Lisi; Augusto Faria Andrade; Damien Faury; Wajih Jawhar; Rola Dali; Hiromichi Suzuki; Manav Pathania; Deli A; Frank Dubois; Eleanor Woodward; Steven Hébert; Marie Coutelier; Jason Karamchandani; Steffen Albrecht; Sebastian Brandner; Nicolas De Jay; Tenzin Gayden; Andrea Bajic; Ashot S Harutyunyan; Dylan M Marchione; Leonie G Mikael; Nikoleta Juretic; Michele Zeinieh; Caterina Russo; Nicola Maestro; Angelia V Bassenden; Peter Hauser; József Virga; Laszlo Bognar; Almos Klekner; Michal Zapotocky; Ales Vicha; Lenka Krskova; Katerina Vanova; Josef Zamecnik; David Sumerauer; Paul G Ekert; David S Ziegler; Benjamin Ellezam; Mariella G Filbin; Mathieu Blanchette; Jordan R Hansford; Dong-Anh Khuong-Quang; Albert M Berghuis; Alexander G Weil; Benjamin A Garcia; Livia Garzia; Stephen C Mack; Rameen Beroukhim; Keith L Ligon; Michael D Taylor; Pratiti Bandopadhayay; Christoph Kramm; Stefan M Pfister; Andrey Korshunov; Dominik Sturm; David T W Jones; Paolo Salomoni; Claudia L Kleinman; Nada Jabado Journal: Cell Date: 2020-11-30 Impact factor: 41.582
Authors: Samantha A O'Connor; Heather M Feldman; Sonali Arora; Pia Hoellerbauer; Chad M Toledo; Philip Corrin; Lucas Carter; Megan Kufeld; Hamid Bolouri; Ryan Basom; Jeffrey Delrow; José L McFaline-Figueroa; Cole Trapnell; Steven M Pollard; Anoop Patel; Patrick J Paddison; Christopher L Plaisier Journal: Mol Syst Biol Date: 2021-06 Impact factor: 11.429