Dr. Thomas Martin Lange
Research Fields and Interests
Stability optimisation of non-deterministic prediction models
Quantification and reduction of variability of machine learning models that incorporate stochastic elements during model training. The aim is to develop a universal framework to define and optimise stability and computation time of different non-deterministic algorithms.
Published results:
1) Optimising Random Forest (optRF) by Determining the Optimal Number of Decision Trees
2) A General Framework for Stability Assessment of Non-Deterministic Prediction Models
Published results:
1) Optimising Random Forest (optRF) by Determining the Optimal Number of Decision Trees
- To the project website: optRF
2) A General Framework for Stability Assessment of Non-Deterministic Prediction Models
- To the R packaget: APS
Improving accuracy of genomic prediction models and evaluating new methods for quality assessment of prediction models for genomic selection.
Published results:
1) Development of a New Method to Classify Single Nucleotide Polymorphisms (SNPs)
2) Development of a New Method to Assess the Accuracy of Prediction Models for Genomic Selection
3) Evaluation of Incremental Feature Selection in Random Forest Prediction Models for Genomic Selection
Published results:
1) Development of a New Method to Classify Single Nucleotide Polymorphisms (SNPs)
2) Development of a New Method to Assess the Accuracy of Prediction Models for Genomic Selection
3) Evaluation of Incremental Feature Selection in Random Forest Prediction Models for Genomic Selection
Development of new methods to improve phenotyping of disease resistance in crops and improving genomic prediction of disease resistance as well as usage of prediction models to identify epistatic effects between genomic markers.
Published results:
1) Improving the Accuracy of Random Forest Prediction Models for Genomic Prediction of Rhizomania Resistance in Sugar Beet Through Variable Selection
2) Non-linear transformation of enzyme-linked immunosorbent assay (ELISA) Values to Optimise Data Analysis in Resistance Breeding
Published results:
1) Improving the Accuracy of Random Forest Prediction Models for Genomic Prediction of Rhizomania Resistance in Sugar Beet Through Variable Selection
2) Non-linear transformation of enzyme-linked immunosorbent assay (ELISA) Values to Optimise Data Analysis in Resistance Breeding
Memberships
- Member of the International Biometric Society
- Editorial Board Member at the Journals Bioinformatics Methods and Applications
Current Lectures
Winter semester
- Data Analysis with R (M.iPAB.0014, 3 Credits, 2 WLH)
- Scientific Project: scientific methods, procedures and practical skills in animal and plant breeding (M.iPAB.0019, 9 Credits, 6 WLH)
Summer semester
- Scientific Project: scientific methods, procedures and practical skills in animal and plant breeding (M.iPAB.0019, 9 Credits, 6 WLH)
Curriculum Vitae
Scientific qualifications
| Time period | Degree and Institution |
|---|---|
| 2019 - 2023 | Ph.D. (Dr. rer. nat.) in Breeding Informatics, Georg-August University of Göttingen |
| 2015 - 2018 | Master of Science in Agrarwissenschaften, Georg-August University of Göttingen |
| 2012 - 2015 | Bachelor of Science in Agrarwissenschaften, Georg-August University of Göttingen |
Professional Experience
| Time period | Position and Institution |
|---|---|
| Since 10/2023 | Postdoctoral researcher in the Breeding Informatics group, Georg-August University of Göttingen |
| 03/2019 - 09/2023 | Doctoral candidate in in the Breeding Informatics group, Georg-August University of Göttingen in cooperation with KWS Saat SE & Co. KGaA |
| 10/2018 - 12/2018 | Student research assistant in the Breeding Informatics group, Georg-August University of Göttingen |
| 10/2016 - 09/2018 | Student assistant for teaching in the Breeding Informatics group, Georg-August University of Göttingen |
| 02 - 04/2016 | Conducting a student project at SESVanderHave |
| 2015 - 2017 | Seasonal temporary worker in maize breeding at Euralis Saaten GmbH (nowadays Lidea Germany GmbH) |
Selected Publications
| Authors | Title | Journal |
|---|---|---|
| Heinrich, F., Lange, T. M., Ramzan, F., Gültas, M., Schmitt, A.O. | Normalized Cumulative Gain as an Alternative Evaluation Measure for Genomic Selection Models | Genetics Selection Evolution |
| Lange, T. M., Gültas, M., Schmitt, A.O., Heinrich, F. | optRF: Optimising random forest stability by determining the optimal number of trees | BMC Bioinformatics |
| Heinrich, F., Lange, T. M., Kircher, M., Ramzan, F., Schmitt, A. O., Gültas, M. | Exploring the potential of incremental feature selection to improve genomic prediction accuracy | Genetics Selection Evolution |
| Lange, T. M., Rotärmel, M., Müller, D., Mahone, G. S., Kopisch-Obuch, F., Keunecke, H., Schmitt, A. O. | Non-linear transformation of enzyme-linked immunosorbent assay (ELISA) measurements allows usage of linear models for data analysis | Virology Journal |
| Klees, S., Lange, T. M., Bertram, H., Rajavel, A., Schlüter, J.-S., Lu, K., Schmitt, A. O., Gültas, M. | In Silico Identification of the Complex Interplay between Regulatory SNPs, Transcription Factors, and Their Related Genes in Brassica napus L. Using Multi-Omics Data | International journal of molecular sciences |
| Lange, T. M., Heinrich, F., Enders, M., Wolf, M., Schmitt, A. O. | In silico quality assessment of SNPs — A case study on the Axiom Wheat genotyping arrays | Current Plant Biology |
For a full list of publication see ResearchGate or Google Scholar.