Towards Precision Medicine in Psychosis: Benefits and Challenges of Multimodal Multicenter Studies—PSYSCAN: Translating Neuroimaging Findings From Research into Clinical Practice

Abstract In the last 2 decades, several neuroimaging studies investigated brain abnormalities associated with the early stages of psychosis in the hope that these could aid the prediction of onset and clinical outcome. Despite advancements in the field, neuroimaging has yet to deliver. This is in part explained by the use of univariate analytical techniques, small samples and lack of statistical power, lack of external validation of potential biomarkers, and lack of integration of nonimaging measures (eg, genetic, clinical, cognitive data). PSYSCAN is an international, longitudinal, multicenter study on the early stages of psychosis which uses machine learning techniques to analyze imaging, clinical, cognitive, and biological data with the aim of facilitating the prediction of psychosis onset and outcome. In this article, we provide an overview of the PSYSCAN protocol and we discuss benefits and methodological challenges of large multicenter studies that employ neuroimaging measures.

Download Full-text

The rise and fall of machine learning methods in biomedical research

F1000Research ◽

10.12688/f1000research.13016.1 ◽

2017 ◽

Vol 6 ◽

pp. 2012 ◽

Cited By ~ 6

Author(s):

Hashem Koohy

Keyword(s):

Machine Learning ◽

Biomedical Research ◽

Life Sciences ◽

Biological Data ◽

Research Note ◽

Machine Learning Techniques ◽

Learning Methods ◽

The Past ◽

Machine Learning Methods ◽

Learning Techniques

In the era of explosion in biological data, machine learning techniques are becoming more popular in life sciences, including biology and medicine. This research note examines the rise and fall of the most commonly used machine learning techniques in life sciences over the past three decades.

Download Full-text

Predicting Alzheimer’s disease progression trajectory and clinical subtypes using machine learning

10.1101/792432 ◽

2019 ◽

Author(s):

Vipul K. Satone ◽

Rachneet Kaur ◽

Anant Dadu ◽

Hampton Leonard ◽

Hirotaka Iwaki ◽

...

Keyword(s):

Machine Learning ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Disease Progression ◽

Disease Onset ◽

Machine Learning Techniques ◽

Progression Rate ◽

Early Stages ◽

Age Related ◽

Learning Techniques

AbstractBackgroundAlzheimer’s disease (AD) is a common, age-related, neurodegenerative disease that impairs a person’s ability to perform day-to-day activities. Diagnosing AD is challenging, especially in the early stages. Many patients still go undiagnosed, partly due to the complex heterogeneity in disease progression. This highlights a need for early prediction of the disease course to assist its treatment and tailor therapy options to the disease progression rate. Recent developments in machine learning techniques provide the potential to not only predict disease progression and trajectory of AD but also to classify the disease into different etiological subtypes.Methods and findingsThe work shown here clusters participants in distinct and multifaceted progression subgroups of AD and discusses an approach to predict the progression rate from baseline diagnosis. We observed that the myriad of clinically reported symptoms summarized in the proposed AD progression space corresponds directly with memory and cognitive measures, which are routinely used to monitor disease onset and progression. Our analysis demonstrated accurate prediction of disease progression after four years from the first 12 months of post-diagnosis clinical data (Area Under the Curve of 0.96 (95% confidence interval (CI), 0.92-1.0), 0.81 (95% CI, 0.74-0.88) and 0.98 (95% CI, 0.96-1.0) for slow, moderate and fast progression rate patients respectively). Further, we explored the long short-term memory (LSTM) neural networks to predict the trajectory of an individual patient’s progression.ConclusionThe machine learning techniques presented in this study may assist providers in identifying different progression rates and trajectories in the early stages of the disease, hence allowing for more efficient and personalized healthcare deliveries. With additional information about the progression rate of AD at hand, providers may further individualize the treatment plans. The predictive tests discussed in this study not only allow for early AD diagnosis but also facilitate the characterization of distinct AD subtypes relating to trajectories of disease progression. These findings are a crucial step forward for early disease detection. These models can be used to design improved clinical trials for AD research.

Download Full-text

Current Developments in Machine Learning Techniques in Biological Data Mining

Bioinformatics and Biology Insights ◽

10.1177/1177932216687545 ◽

2017 ◽

Vol 11 ◽

pp. 117793221668754 ◽

Cited By ~ 4

Author(s):

Gerard G Dumancas ◽

Indra Adrianto ◽

Ghalib Bello ◽

Mikhail Dozmorov

Keyword(s):

Machine Learning ◽

Biomarker Discovery ◽

Wide Spectrum ◽

Specific Area ◽

Biological Data ◽

Machine Learning Techniques ◽

Learning Techniques ◽

Indispensable Tool ◽

Underlying Mechanisms ◽

Applications Of Machine Learning

This supplement is intended to focus on the use of machine learning techniques to generate meaningful information on biological data. This supplement under Bioinformatics and Biology Insights aims to provide scientists and researchers working in this rapid and evolving field with online, open-access articles authored by leading international experts in this field. Advances in the field of biology have generated massive opportunities to allow the implementation of modern computational and statistical techniques. Machine learning methods in particular, a subfield of computer science, have evolved as an indispensable tool applied to a wide spectrum of bioinformatics applications. Thus, it is broadly used to investigate the underlying mechanisms leading to a specific disease, as well as the biomarker discovery process. With a growth in this specific area of science comes the need to access up-to-date, high-quality scholarly articles that will leverage the knowledge of scientists and researchers in the various applications of machine learning techniques in mining biological data.

Download Full-text

Prediction of protein-protein interactions using one-class classification methods and integrating diverse biological data

Journal of Integrative Bioinformatics ◽

10.1515/jib-2007-77 ◽

2007 ◽

Vol 4 (3) ◽

pp. 208-223 ◽

Cited By ~ 5

Author(s):

José A. Reyes ◽

David Gilbert

Keyword(s):

Performance Evaluation ◽

Protein Interactions ◽

Biological Data ◽

Biological Information ◽

Machine Learning Techniques ◽

Protein Protein Interactions ◽

Comparative Performance ◽

Learning Techniques ◽

Imbalanced Class ◽

One Class Classification

Summary This research addresses the problem of prediction of protein-protein interactions (PPI) when integrating diverse kinds of biological information. This task has been commonly viewed as a binary classification problem (whether any two proteins do or do not interact) and several different machine learning techniques have been employed to solve this task. However the nature of the data creates two major problems which can affect results. These are firstly imbalanced class problems due to the number of positive examples (pairs of proteins which really interact) being much smaller than the number of negative ones. Secondly the selection of negative examples can be based on some unreliable assumptions which could introduce some bias in the classification results.Here we propose the use of one-class classification (OCC) methods to deal with the task of prediction of PPI. OCC methods utilise examples of just one class to generate a predictive model which consequently is independent of the kind of negative examples selected; additionally these approaches are known to cope with imbalanced class problems. We have designed and carried out a performance evaluation study of several OCC methods for this task, and have found that the Parzen density estimation approach outperforms the rest. We also undertook a comparative performance evaluation between the Parzen OCC method and several conventional learning techniques, considering different scenarios, for example varying the number of negative examples used for training purposes. We found that the Parzen OCC method in general performs competitively with traditional approaches and in many situations outperforms them. Finally we evaluated the ability of the Parzen OCC approach to predict new potential PPI targets, and validated these results by searching for biological evidence in the literature.

Download Full-text

Machine Learning-Based Analysis of Sperm Videos and Participant Data for Male Fertility Prediction

Scientific Reports ◽

10.1038/s41598-019-53217-y ◽

2019 ◽

Vol 9 (1) ◽

Cited By ~ 5

Author(s):

Steven A. Hicks ◽

Jorunn M. Andersen ◽

Oliwia Witczak ◽

Vajira Thambawita ◽

Pål Halvorsen ◽

...

Keyword(s):

Machine Learning ◽

Sperm Motility ◽

Semen Analysis ◽

Biological Data ◽

Automatic Analysis ◽

Semen Sample ◽

Human Reproduction ◽

Machine Learning Techniques ◽

Simple Linear Regression ◽

Learning Techniques

AbstractMethods for automatic analysis of clinical data are usually targeted towards a specific modality and do not make use of all relevant data available. In the field of male human reproduction, clinical and biological data are not used to its fullest potential. Manual evaluation of a semen sample using a microscope is time-consuming and requires extensive training. Furthermore, the validity of manual semen analysis has been questioned due to limited reproducibility, and often high inter-personnel variation. The existing computer-aided sperm analyzer systems are not recommended for routine clinical use due to methodological challenges caused by the consistency of the semen sample. Thus, there is a need for an improved methodology. We use modern and classical machine learning techniques together with a dataset consisting of 85 videos of human semen samples and related participant data to automatically predict sperm motility. Used techniques include simple linear regression and more sophisticated methods using convolutional neural networks. Our results indicate that sperm motility prediction based on deep learning using sperm motility videos is rapid to perform and consistent. Adding participant data did not improve the algorithms performance. In conclusion, machine learning-based automatic analysis may become a valuable tool in male infertility investigation and research.

Download Full-text

Deep Learning in Mining Biological Data

Cognitive Computation ◽

10.1007/s12559-020-09773-x ◽

2021 ◽

Author(s):

Mufti Mahmud ◽

M. Shamim Kaiser ◽

T. Martin McGinnity ◽

Amir Hussain

Keyword(s):

Pattern Recognition ◽

Deep Learning ◽

Meta Analysis ◽

Biological Data ◽

Machine Learning Techniques ◽

Data Types ◽

Multimodal Data ◽

Data Intensive ◽

Learning Techniques ◽

Access Data

AbstractRecent technological advancements in data acquisition tools allowed life scientists to acquire multimodal data from different biological application domains. Categorized in three broad types (i.e. images, signals, and sequences), these data are huge in amount and complex in nature. Mining such enormous amount of data for pattern recognition is a big challenge and requires sophisticated data-intensive machine learning techniques. Artificial neural network-based learning systems are well known for their pattern recognition capabilities, and lately their deep architectures—known as deep learning (DL)—have been successfully applied to solve many complex pattern recognition problems. To investigate how DL—especially its different architectures—has contributed and been utilized in the mining of biological data pertaining to those three types, a meta-analysis has been performed and the resulting resources have been critically analysed. Focusing on the use of DL to analyse patterns in data from diverse biological domains, this work investigates different DL architectures’ applications to these data. This is followed by an exploration of available open access data sources pertaining to the three data types along with popular open-source DL tools applicable to these data. Also, comparative investigations of these tools from qualitative, quantitative, and benchmarking perspectives are provided. Finally, some open research challenges in using DL to mine biological data are outlined and a number of possible future perspectives are put forward.

Download Full-text

Early Detection of Alzheimer’s Disease Using Patient Neuropsychological and Cognitive Data and Machine Learning Techniques

2019 IEEE International Conference on Big Data (Big Data) ◽

10.1109/bigdata47090.2019.9006583 ◽

2019 ◽

Cited By ~ 2

Author(s):

Ibrahim Almubark ◽

Lin-Ching Chang ◽

Thanh Nguyen ◽

Raymond Scott Turner ◽

Xiong Jiang

Keyword(s):

Machine Learning ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Early Detection ◽

Machine Learning Techniques ◽

Learning Techniques ◽

Cognitive Data

Download Full-text

KymoButler, a deep learning software for automated kymograph analysis

eLife ◽

10.7554/elife.42288 ◽

2019 ◽

Vol 8 ◽

Cited By ~ 7

Author(s):

Maximilian AH Jakobs ◽

Andrea Dimitracopoulos ◽

Kristian Franze

Keyword(s):

Deep Learning ◽

Data Analysis ◽

Biological Data ◽

Machine Learning Techniques ◽

Unconscious Bias ◽

Web Based ◽

Complex Particle ◽

Learning Techniques ◽

Biological Data Analysis ◽

Learning Software

Kymographs are graphical representations of spatial position over time, which are often used in biology to visualise the motion of fluorescent particles, molecules, vesicles, or organelles moving along a predictable path. Although in kymographs tracks of individual particles are qualitatively easily distinguished, their automated quantitative analysis is much more challenging. Kymographs often exhibit low signal-to-noise-ratios (SNRs), and available tools that automate their analysis usually require manual supervision. Here we developed KymoButler, a Deep Learning-based software to automatically track dynamic processes in kymographs. We demonstrate that KymoButler performs as well as expert manual data analysis on kymographs with complex particle trajectories from a variety of different biological systems. The software was packaged in a web-based ‘one-click’ application for use by the wider scientific community (http://kymobutler.deepmirror.ai). Our approach significantly speeds up data analysis, avoids unconscious bias, and represents another step towards the widespread adaptation of Machine Learning techniques in biological data analysis.

Download Full-text

A graph neural network approach to molecule carcinogenicity prediction

10.1101/2021.11.10.468094 ◽

2021 ◽

Author(s):

Philip Fradkin ◽

Adamo Young ◽

Lazar Atanackovic ◽

Brendan J Frey ◽

Leo J Lee ◽

...

Keyword(s):

Experimental Testing ◽

External Validation ◽

Machine Learning Techniques ◽

Training Dataset ◽

Validation Dataset ◽

Molecular Fingerprint ◽

Neural Network Approach ◽

Learning Techniques ◽

Substantial Progress ◽

Experimental Approaches

Molecular carcinogenicity is a preventable cause of cancer, however, most experimental testing of molecular compounds is an expensive and time consuming process, making high throughput experimental approaches infeasible. In recent years, there has been substantial progress in machine learning techniques for molecular property prediction. In this work, we propose a model for carcinogenicity prediction, CONCERTO, which uses a graph transformer in conjunction with a molecular fingerprint representation, trained on multi-round mutagenicity and carcinogenicity objectives. To train and validate CONCERTO, we augment the training dataset with more informative labels and utilize a larger external validation dataset. Extensive experiments demonstrate that our model yields results superior to alternate approaches for molecular carcinogenicity prediction.

Download Full-text