Best Finnish bioinformatics PhD thesis award winners

Winner of the best Finnish bioinformatics PhD thesis done in 2020-2021

At this year’s Bioinformatics Day organized by the Finnish Society for Bioinformatics held on June 2nd in CSC, Espoo. Dr. Kimmo Kartasalo and Dr. Tomi Suomi were awarded for the best Finnish Bioinformatics PhD thesis done in 2020-2021. In total, there were 4 high-level nominees, and Dr. Kimmo Kartasalo and Tomi Suomi were selected. Dr. Kimmo Kartasalo’s thesis is titled “Machine Learning and 3D Reconstruction Methods for Computational Pathology” and it was accepted at the Faculty of Medicine and Health Technology, Tampere University in 2021. Dr. Tomi Suomi’s thesis is titled “Data analysis tools for mass spectrometry proteomics” and it was accepted at the Faculty of Technology, the University of Turku in 2021. Below, you can find the review board’s statement:

The Finnish Society for Bioinformatics received this year 4 nominations for the best bioinformatics thesis in Finland for the years 2020-2021. We found them all to be of high quality, bringing significant contributions to the bioinformatics field. We found two of them to be of exceptional quality and we unanimously selected them as the recipients of the award: Dr. Kimmo Kartasalo and Dr. Tomi Suomi.

In his thesis, Dr. Kimmo Kartasalo developed very timely and modern machine learning methods for digital pathology, and successfully applied the methods in cancer research studies. He has authored and co-authored several articles in high-ranked journals, combining computational, biological and clinical aspects of life sciences. Such multi-disciplinary collaboration is often required to make a real impact to the life sciences field. His papers describing original research have been highly cited in such short time, e.g., his shared first author paper in The Lancet Oncology has already been cited 183 times (Google Scholar). The multidisciplinary work of Dr. Kartasalo has a great potential to advance the field of image analysis and cancer research, which is of high importance in precision medicine and medical bioinformatics in Finland.

In his thesis Tomi Suomi studied complex high-throughput data from mass spectronomy experiments.The performance of existing label-free proteomics methods were systemtically evaluated and new statistical data analysis methods were proposed, e.g., for a differential expression analysis. Due to rapidly evolving technologies in Omics, such comparisons provide an invaluable service to the community by establishing reliable benchmarks, setting analysis guidelines and providing open-access software. These results have the potential to enhance a systems biology understanding of proteomics data. Overall, the output of the thesis consists of five publications in top bioinformatics and proteomics journals (Briefings in Bioinformatics, PLOS Computational Biology, Journal of Proteome Research, and Scientific Reports) which have accumulated so far 300 citations.

Winner of the best Finnish bioinformatics PhD thesis done in 2018-2019

At this year’s Bioinformatics Day organized by the Finnish Society for Bioinformatics held on May 29th online, Dr. Anna Cichońska was awarded for the best Finnish Bioinformatics PhD thesis done in 2018-2019. In total, there were 10 high-level nominees and Dr. Anna Cichońska was selected because of the high impact of her work in terms of developing computational methods including advanced data modeling in the field of systems pharmacology. The thesis is titled “Machine Learning for Systems Pharmacology” and it was accepted at the Department of Computer Science, Aalto University in 2018. Below, you can find the review board’s statement:

The Finnish Society for Bioinformatics invited us to review the PhD theses that were nominated for “the best bioinformatics thesis in Finland award for the years 2018-2019” and to select one for the award.

We received 10 nominated theses of high quality, significantly contributing to the bioinformatics field. Among the top candidates, we paid special attention to the contribution of the nominee as well as to the amount and quality of bioinformatics approaches developed in the work. After consideration of the overall quality and impact of the work, we unanimously selected Dr. Anna Cichońska as the recipient of the best thesis award.

In her thesis, Dr. Cichońska developed computational methods including advanced data modeling in the field of systems pharmacology. The thesis includes five publications in highly relevant journals in the bioinformatics area. Her publications have been highly cited (ranging between 14 and 60).  The work of Dr. Cichońska has the potential to advance the field of drug discovery and repositioning, which is of high importance in precision medicine and pharmacology.


Winner of the best Finnish bioinformatics PhD thesis done in 2016-2017

At this year’s Bioinformatics Day organized by the Finnish Society for Bioinformatics held on May 11th at Turku, Dr. Huibin Shen was awarded for the best Finnish Bioinformatics Ph.D. thesis done in 2016-2017. In total, there were 6 high-level nominees and Dr. Huibin Shen was selected because of the high impact of his work in terms of identification of small molecules through MS/MS mass spectrometer data analysis. The thesis is titled “Machine Learning for Small Molecule Identification” and it was accepted at the School of Science, Aalto University in 2017. Below, you can find the review board’s statement:

The Finnish Society for Bioinformatics invited us to review the PhD theses that were nominated for “the best bioinformatics thesis in Finland award for the years 2016-2017” and to select one for the award.

After the review, we conclude that all nominated theses were of high quality and each made significant contributions to advance the bioinformatics and the selection of the best one was tough. After consideration of the overall quality and impact of the work, we unanimously selected Dr. Huibin Shen as the recipient of the best thesis award.

In his thesis, Dr. Shen proposes a pipeline based on machine learning algorithms for the identification of small molecules through MS/MS mass spectrometer data analysis. This is a very difficult and important problem, that have applications in many health science fields. Key methodology that the work is based on is multiple kernel learning methods that are applied elegantly.

Thesis includes six publications and many of these have been published in top journals, including Bioinformatics (2 papers) and PNAS. These papers have collected high number of citations in relatively short time, for example PNAS paper published in 2015 has been cited 116 times according to Google Scholar demonstrating the impact of the work.

We wish to congratulate Dr. Shen on the work well done and are happy to nominate him as the recipient of the best thesis award.