Optimizing thrombolytic activity of staphylokinase using machine learning-guided directed evolution - Supervisor’s statement and evaluation

Aug 5, 2026

Upload by Skyler

Supervisor and reviewer evaluation for a final thesis on optimizing the thrombolytic activity of staphylokinase using machine learning-guided directed evolution. The assessment confirms fulfillment of objectives, including preprocessing two staphylokinase datasets, training and applying a selected ML model, and analyzing results in detail. The thesis is rated highly for correctness, clarity, writing quality, adequate breadth, and proper sourcing. Experimental work is documented as repeatable and calculations are executed on an HPC cluster. Results show limited generalization likely due to dataset imbalance, and the work is planned to extend toward journal publication.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages4

Reading Time10 min

AccessFree to download

Evaluation criteria

Fulfillment of the assignment

Main written part

Non-written part, attachments

Evaluation of results, publication outputs and awards

Activity and self-reliance of the student

Instructions for the evaluator

Supervisor’s statement of a final thesis Reviewer: Mgr. Jiří Sedlář , Ph. D. and Ing. Anton Bushuiev Student: MUDr. Elisabet Maňásková Thesis title: Optimizing thrombolytic activity of staphylokinase using machine learning-guided directed evolution Branch / specialization: Informatics / Artificial Intelligence Created on: 10.6.2025 Evaluation criteria 1. Fulfillment of the assignment 1. assignment fulfilled ~~2. assignment fulfilled with minor objections~~ ~~3. assignment fulfilled with major objections~~ ~~4. assignment not fulfilled~~ The main objectives of the thesis were fulfilled: the student explored state-of-the-art approaches to machine learning-guided evolution, diligently preprocessed the two available staphylokinase datasets, applied the selected machine learning model to the prepared data, and in detail analyzed the results. Based on literature review and consultations with experts, the student proposed a set of mutants for the first round of directed evolution; we are now waiting for results from wet-lab experiments, which are being performed by our colleagues at Loschmidt Laboratories ( Masaryk University, Brno) . 2. Main written part 100/100 (A) The thesis is factually correct and logical, the formulations are clear, and the level of English is very good. The thesis provides an adequate overview of related work and the sources are properly cited. The extent is fully adequate, including a clear introduction into the multidisciplinary research area. 3. Non-written part, attachments 100/100 (A) The research experiments are well-documented and repeatable. The student managed to run the calculations on the HPC cluster. 4. Evaluation of results, publication outputs and awards 90/100 (A-) The thesis first validates EVOLVEpro on benchmark data and then uses it to learn the activity of SAK variants from the Laroche dataset. The analysis shows that the trained model has limited generalization capability, probably due to the high imbalance of the Laroche dataset. The plan is to extend the thesis to a journal publication. 5. Activity of the student 1. excellent activity ~~2. very good activity~~ ~~3. average activity~~ ~~4. weaker~~,~~ but still suficient activity~~ ~~5. insufficient activity~~ The student was active, punctual, well-prepared for consultations with supervisors as well as with external experts, and participated in a two-day research workshop between CIIRC and Loschmidt Laboratories that included talks and discussions on staphylokinase research. 6. Self-reliance of the student 1. excellent self-reliance ~~2. very good self-reliance~~ ~~3. average self-reliance~~ ~~4. weaker~~,~~ but still suficient self-reliance~~ ~~5. insufficient self-reliance~~ During the work on the thesis, the student exhibited strong ability for independent and creative research. The overall evaluation 95/100 (A) The main objectives of the thesis were fulfilled and the thesis has the potential to be extended to a journal publication. The student employed her knowledge of machine learning in a dynamic, multidisciplinary field. Overall, the thesis is very nicely written. The grade that I recommend for the thesis is A-excellent. Instructions Fulfillment of the assignment Assess whether the submitted FT defines the objectives sufficiently and in line with the assignment; whether the objectives are formulated correctly and fulfilled sufficiently. In the comment, specify thepoints of the assignment that have not been met, assess the severity, impact, and, if appropriate, also the cause of the deficiencies. If the assignment differs substantially from the standards for the FT or if the student has developed the FT beyond the assignment, describe the way it got reflected on the quality of the assignment’s fulfilment and the way it affected your final evaluation. Main written part Evaluate whether the extent of the FT is adequate to its content and scope: are all th

FAQs

What were the main objectives of the thesis, and were they fulfilled?

The objectives were fulfilled: the student reviewed state-of-the-art ML-guided evolution approaches, preprocessed two staphylokinase datasets, applied a selected ML model, and analyzed results in detail.

How was the thesis assessed in terms of written content and correctness?

The written part was evaluated as factually correct and logical, with clear formulations, very good English level, adequate overview of related work, and properly cited sources.

What does the evaluation indicate about the model’s performance and next steps?

The trained model showed limited generalization, likely due to the high imbalance of the Laroche dataset. The plan is to extend the thesis toward a journal publication.

Aug 5, 2026

Upload by Skyler