Prof. Dr. Alexander Schliep is the new FGW Professor for Medical Bioinformatics with a focus on patient-oriented data acquisition at the Brandenburg University of Technology Cottbus-Senftenberg (BTU) since October 01, 2022.
Large amounts of data are collected in many disciplines, often with highly diverse formats that need to be processed bioinformatically. For this purpose, it is usually necessary to develop new tools that provide the best possible answer for the data set and the specific question.
Furthermore, one focus of this professorship will be the development of new techniques such as mobile diagnostics or networked care of chronically ill people as well as the bias-free evaluation of these new techniques.
The SchliepLAB is part of the Brandenburg Faculty of Health Sciences and is located at the Brandenburg University of Technology Cottbus-Senftenberg. Part of the group is based at the Faculty of Computer Science and Engineering, which is a joint faculty of the University of Gothenburg and Chalmers University of Technology.
A list of current and completed research projects can be found at https://schlieplab.org/Research/, a list of publications at https://schlieplab.org/Publications/ and a list of software packages at https://schlieplab.org/Software/.
In particular, for antisense oligonucleotides (ASO) that act by RNAse H1-mediated knockdown, binding energies and kinetics of ASO mRNA duplexes are critical for predicting efficacy and safety. We predict binding energies from sequences, study the kinetics of ASO action to make the ASO drug design process more predictable, and combine molecular dynamics and artificial intelligence in collaborative projects to extend predictive models to a wider range of nucleotide modifications. Our federated, privacy-preserving learning approach enables competitors to pool data for training predictors of binding energies.
Pan-genomic graphs provide a principled approach for dealing with structural variants and the high degree of diversity between genomes. ML on pan-genomic graphs will allow to tackle prediction and regression tasks for different populations, including quantities relevant for oligonucleotide therapeutics, such as transcription rate or accessibility, as well as clinically relevant variables.
Data generated by high-throughput experimental platforms such as high-throughput sequencing (HTS) pose computational challenges, in particular when advanced statistical approaches such as Bayesian methods are used for analysis. In the past, we have developed a compressive genomics approach funded by the NIH Big Data to Knowledge Program (BD2K), used wavelet compression in Bayesian HMMs for copy number variant detection, and significantly improved the utility of statistical ML models representing genomes – variable length Markov chains – through faster learning algorithms. This enables, for example, alignment-free genome comparisons from raw data.
Computational thinking is a basic requirement for all disciplines. The teaching of computational and algorithmic ideas can benefit greatly from software tools. We develop animation systems for graph algorithms that are available on desktop, as a web app, and soon as an iOS app; CATBox is a Springer textbook that uses Gato. With our Hidden Markov Model library, learners can focus on solving exciting bioinformatics problems.
Learning Outcome
After successfully completing the module, students will have acquired an introduction to modern bioinformatics and to selected applications from biology and medicine. They understand the methodology through presentation of the central computational problems and an introduction of solutions based on classical algorithms and statistical machine learning, as well as modern deep learning approaches.
Contents
The focus will be on four fundamental problem areas:
Recommended Prerequisites
| Lecture | Exercise |
|---|---|
| Friday | Friday |
| 9:15 – 10:45 (Block 2) | 11:30 – 13:00 (Block 3) |
| Campus Sachsendorf, building 9, room 9.122 | Campus Sachsendorf, building 9, room 9.122 |
Detailed information for participants is available at
https://www.b-tu.de/elearning/btu/course/view.php?id=12912
Learning Outcome
After successfully completing the module, students have insight into this exciting field of application for Artificial Intelligence (AI). They are able to acquire research literature and to present the topic orally as well as in a written report.
Contents
AI is revolutionizing drug design both for small molecule drugs – the prevalent drug modality – and novel modalities such as oligonucleotide therapeutics. Some of the progress has been achieved by transferring methods from established AI areas such as NLP. For other areas novel methodological developments were instrumental, with very exciting developments on the intersection between molecular dynamics and AI. The focus of the seminar will be on state-of-the-art methods and applications of AI in drug design for small molecule drugs and oligonucleotide therapeutics.
Recommended Prerequisites
Working knowledge of probability/statistics and modern machine learning methods.
| Seminar |
|---|
| Friday |
| 13:45 – 15:15 (Block 4) |
| Campus Sachsendorf, building 9, room 9.122 |
Detailed information available for participants at
https://www.b-tu.de/elearning/btu/course/view.php?id=12913
After successfully completing the module, students have an overview on how to solve large-scale computational problems in data science and machine learning. They know parallel approaches from multi-threaded computation on individual machines to implicit parallelism frameworks on compute clusters. They are familiar with algorithms and data structures supporting efficient exact or approximate (e.g. sketching) computation with massive data sets in and out of core. They are able to implement the algorithms. They can assess which methods can be used in a given situation.
The focus will be on the following areas: A review of memory-compute co-location and its impact on big data computations; Solving Machine Learning (ML) work loads using explicit parallelism, specifically multi-threaded computation on an individual machine; Introduction of implicit parallelism programming models as implemented for example in MapReduce, Spark and Ray and their application in ML; Sketching algorithms (e.g. CountMinSketch, HyperLogLog) or Bloom filters; Implementing ML methods using index data structures such as suffix or kd-trees.
Detailed information for participants is available at
https://www.b-tu.de/elearning/btu/course/view.php?id=12914
A list of current and prior offered courses and seminars can be found at https://schlieplab.org/Teaching/
