Tapio Pahikkala
YOU?
Author Swipe
View article: Towards practical federated learning and evaluation for medical prediction models
Towards practical federated learning and evaluation for medical prediction models Open
Federated learning shows potential in scenarios with limited data availability. However, its practical applicability is highly context-dependent, influenced by factors such as data availability and specific task requirements.
View article: Improved diagnostic performance of a phage display antibody-assisted intact free PSA assay as used in the four kallikrein concept applied to the IMPROD/multi-IMPROD study
Improved diagnostic performance of a phage display antibody-assisted intact free PSA assay as used in the four kallikrein concept applied to the IMPROD/multi-IMPROD study Open
The I-MC assay demonstrates modest but clear improvement in differentiating benign and low-grade prostate cancer from clinically significant cancers, particularly in patients with less than median gland volume. This is an effect of the mut…
View article: Stochastic limited memory bundle algorithm for clustering in big data
Stochastic limited memory bundle algorithm for clustering in big data Open
Clustering is a crucial task in data mining and machine learning. In this paper, we propose an efficient algorithm, BIG-CLuST, for solving minimum sum-of-squares clustering problems in large and big datasets. We first develop a novel stoch…
View article: Limited memory bundle DC algorithm for sparse pairwise kernel learning
Limited memory bundle DC algorithm for sparse pairwise kernel learning Open
Pairwise learning is a specialized form of supervised learning that focuses on predicting outcomes for pairs of objects. In this paper, we formulate the pairwise learning problem as a difference of convex (DC) optimization problem using th…
View article: Targeted and Untargeted Amine Metabolite Quantitation in Single Cells with Isobaric Multiplexing
Targeted and Untargeted Amine Metabolite Quantitation in Single Cells with Isobaric Multiplexing Open
We developed a single cell amine analysis approach utilizing isobarically multiplexed samples of 6 individual cells along with analyte abundant carrier. This methodology was applied for absolute quantitation of amino acids and untargeted r…
View article: Targeted and Untargeted Amine Metabolite Quantitation in Single Cells with Isobaric Multiplexing
Targeted and Untargeted Amine Metabolite Quantitation in Single Cells with Isobaric Multiplexing Open
We developed a single cell amine analysis approach utilizing isobarically multiplexed samples of 6 individual cells along with analyte abundant carrier. This methodology was applied for absolute quantitation of amino acids and untargeted r…
View article: Does Differentially Private Synthetic Data Lead to Synthetic Discoveries?
Does Differentially Private Synthetic Data Lead to Synthetic Discoveries? Open
Background Synthetic data have been proposed as a solution for sharing anonymized versions of sensitive biomedical datasets. Ideally, synthetic data should preserve the structure and statistical properties of the original data, while prote…
View article: Predicting pairwise interaction affinities with ℓ <sub>0</sub> -penalized least squares–a nonsmooth bi-objective optimization based approach*
Predicting pairwise interaction affinities with ℓ <sub>0</sub> -penalized least squares–a nonsmooth bi-objective optimization based approach* Open
In this paper, we introduce a novel nonsmooth optimization-based method LMBM-Kron & ell;(0) LS for solving large-scale pairwise interaction affinity prediction problems. The aim of LMBM-Kron & ell;0LS is to produce accurate predictions usi…
View article: Finnish perspective on using synthetic health data to protect privacy: the PRIVASA project
Finnish perspective on using synthetic health data to protect privacy: the PRIVASA project Open
The use of synthetic data could facilitate data-driven innovation across industries and applications. Synthetic data can be generated using a range of methods, from statistical modeling to machine learning and generative AI, resulting in d…
View article: Benchmarking Evaluation Protocols for Classifiers Trained on Differentially Private Synthetic Data
Benchmarking Evaluation Protocols for Classifiers Trained on Differentially Private Synthetic Data Open
<div>\n<div>\n<div>\n<div>Differentially private (DP) synthetic data has emerged as a potential solution for sharing sensitive individual-level biomedical data. DP generative models offer a promising approach for ge…
View article: A Comparison of Embedding Aggregation Strategies in Drug-Target Interaction Prediction
A Comparison of Embedding Aggregation Strategies in Drug-Target Interaction Prediction Open
The prediction of interactions between novel drugs and biological targets is a vital step in the early stage of the drug discovery pipeline. Many deep learning approaches have been proposed over the last decade, with a substantial fraction…
View article: A Comparison of Embedding Aggregation Strategies in Drug-Target Interaction Prediction
A Comparison of Embedding Aggregation Strategies in Drug-Target Interaction Prediction Open
The prediction of interactions between novel drugs and biological targets is a vital step in the early stage of the drug discovery pipeline. Many deep learning approaches have been proposed over the last decade, with a substantial fraction…
View article: Budget-Based Classification of Parkinson's Disease From Resting State EEG
Budget-Based Classification of Parkinson's Disease From Resting State EEG Open
Early detection is vital for future neuroprotective treatments of Parkinson's disease (PD). Resting state electroencephalographic (EEG) recording has shown potential as a cost-effective means to aid in detection of neurological disorders s…
View article: Quicksort leave-pair-out cross-validation for ROC curve analysis
Quicksort leave-pair-out cross-validation for ROC curve analysis Open
Receiver Operating Characteristic (ROC) curve analysis and area under the ROC curve (AUC) are commonly used performance measures in diagnostic systems. In this work, we assume a setting, where a classifier is inferred from multivariate dat…
View article: Generalized vec trick for fast learning of pairwise kernel models
Generalized vec trick for fast learning of pairwise kernel models Open
Pairwise learning corresponds to the supervised learning setting where the goal is to make predictions for pairs of objects. Prominent applications include predicting drug-target or protein-protein interactions, or customer-product prefere…
View article: Adaptive risk prediction system with incremental and transfer learning
Adaptive risk prediction system with incremental and transfer learning Open
Currently, popular methods for prenatal risk assessment of fetal aneuploidies are based on multivariate probabilistic modelling, that are built on decades of scientific research and large-scale multi-center clinical studies. These static m…
View article: Detection of Prostate Cancer Using Biparametric Prostate <scp>MRI</scp>, Radiomics, and Kallikreins: A Retrospective Multicenter Study of Men With a Clinical Suspicion of Prostate Cancer
Detection of Prostate Cancer Using Biparametric Prostate <span>MRI</span>, Radiomics, and Kallikreins: A Retrospective Multicenter Study of Men With a Clinical Suspicion of Prostate Cancer Open
Background Accurate detection of clinically significant prostate cancer (csPCa), Gleason Grade Group ≥ 2, remains a challenge. Prostate MRI radiomics and blood kallikreins have been proposed as tools to improve the performance of biparamet…
View article: Modeling drug combination effects via latent tensor reconstruction
Modeling drug combination effects via latent tensor reconstruction Open
Motivation Combination therapies have emerged as a powerful treatment modality to overcome drug resistance and improve treatment efficacy. However, the number of possible drug combinations increases very rapidly with the number of individu…
View article: Modeling drug combination effects via latent tensor reconstruction
Modeling drug combination effects via latent tensor reconstruction Open
A bstract Motivation Combination therapies have emerged as a powerful treatment modality to overcome drug resistance and improve treatment efficacy. However, the number of possible drug combinations increases very rapidly with the number o…
View article: A Link between Coding Theory and Cross-Validation with Applications
A Link between Coding Theory and Cross-Validation with Applications Open
How many different binary classification problems a single learning algorithm can solve on a fixed data with exactly zero or at most a given number of cross-validation errors? While the number in the former case is known to be limited by t…
View article: Drug combination data used for comboLTR in "Modeling drug combination effects via latent tensor reconstruction"
Drug combination data used for comboLTR in "Modeling drug combination effects via latent tensor reconstruction" Open
DrugCombo.db : it contains all the drug combination data used for the cross validation for comboLTR, as well as drugs' fingerprints and cells multi-omics data. CV_Folds_S(1, 2, 3, 4)_Full.List.Pickle : These Python pickled list objects con…
View article: Drug combination data used for comboLTR in "Modeling drug combination effects via latent tensor reconstruction"
Drug combination data used for comboLTR in "Modeling drug combination effects via latent tensor reconstruction" Open
DrugCombo.db : it contains all the drug combination data used for the cross validation for comboLTR, as well as drugs' fingerprints and cells multi-omics data. CV_Folds_S(1, 2, 3, 4)_Full.List.Pickle : These Python pickled list objects con…
View article: A Resource Management Model for Distributed Multi-Task Applications in Fog Computing Networks
A Resource Management Model for Distributed Multi-Task Applications in Fog Computing Networks Open
While the effectiveness of fog computing in Internet of Things (IoT) applications has been widely investigated in various studies, there is still a lack of techniques to efficiently utilize the computing resources in a fog platform to maxi…
View article: New Recommendation Algorithm for Implicit Data Motivated by the Multivariate Normal Distribution
New Recommendation Algorithm for Implicit Data Motivated by the Multivariate Normal Distribution Open
The goal of recommender systems is to help users find useful items from a large catalog of items by producing a list of item recommendations for every user. Data sets based on implicit data collection have a number of special characteristi…