Tero A. Aittokallio

Paired activity learning supports systematic identification of mutant-selective EGFR inhibitors

The paper develops a computational-experimental framework to identify mutant-selective EGFR inhibitors by leveraging paired activity measurements and structural analysis.

Estimating the completeness of large-scale single-cell sequencing projects

This paper estimates the completeness of large-scale single-cell sequencing projects using ecological richness metrics applied to cellular diversity data.

Human-supervised Agentic AI for Hypothesis Generation and Experimental Assistance in Drug Repurposing

A human-supervised multi-agent LLM system covered drug repurposing from knowledge graph building to assay analysis in three case studies; retrospective COVID-19 screen AUC-ROC 0.986 without predefined thresholds.

Selective scoring of drug effects in multicellular co-culture systems

The paper introduces CES, a computational framework to score drug effects in multicellular co-culture systems, distinguishing between immunomodulatory effects and toxicity.

Domain-adversarial learning predicts clinically actionable drug combination synergy in leukemia patients using bulk transcriptomics data

This paper develops a domain-adversarial neural network to predict drug combination synergy in leukemia patients using bulk transcriptomics data, showing improved accuracy over existing methods.

TRAFIKK: systematic prediction and mechanistic interpretation of anticancer drug synergies

TRAFIKK predicts and explains anticancer drug synergies by simulating drug effects in cell-specific models, achieving high recall and revealing both conserved and context-dependent mechanisms.

Improving reproducibility in pharmacogenomic screens through cross-study benchmarking

This paper benchmarks pharmacogenomic studies to improve reproducibility by identifying key factors causing inconsistency and introducing a standardized Drug Response Score (DRS) and resource.

Multimodal immunopharmacologic screens identify drugs rewiring the cancer-immune interface

The paper identifies drugs that rewiring the cancer-immune interface by enhancing NK cell function and tumor susceptibility through multimodal screening approaches.

NFATC2 in pancreatic cancer-associated fibroblasts predicts treatment response and facilitates ERBB-targeted therapies

The paper identifies NFATC2-expressing cancer-associated fibroblasts in PDAC that improve treatment response and enhance ERBB-targeted therapies.

A STAT5B-driven mouse model of hepatosplenic γδ T-cell lymphoma reveals therapeutic efficacy of JAK inhibition

Breast Cancer Remodels Lymphatics in Sentinel Lymph Nodes

This study identifies changes in lymphatic endothelial cell subsets and increased MGP expression in metastatic sentinel lymph nodes from breast cancer patients.

Off-target mapping enhances selectivity of machine learning-predicted CK2 inhibitors

The paper develops an ML-powered drug discovery pipeline to design selective CK2 inhibitors with favorable off-target profiles, achieving a 90% hit-rate.

A statistical framework for defining synergistic anticancer drug interactions

The paper establishes a statistical framework to identify synergistic anticancer drug interactions using large-scale cell line data and reference null distributions.

Spatial artefact detection improves reproducibility of drug screening experiments

The paper introduces a control-independent QC method to detect spatial artefacts in drug screening experiments, improving reproducibility between technical replicates and cross-dataset correlation.

Morphological cell profiling for drug repurposing against SARS-CoV-2 infection

The paper identifies host-targeting antivirals against SARS-CoV-2 using morphological profiling, finding compounds that reverse infected cell phenotypes and validate host processes hijacked by viruses.

High-resolution integrative analysis allows characterization and spatial annotation of normal and cancer-associated colon fibroblasts

This study characterizes and spatially annotates normal and cancer-associated colon fibroblasts using single-cell RNA-sequencing and spatial transcriptomics.

Complex I Drives Glutamine-Dependent TCA Cycle to Support Viability of MYChigh Breast Cancer Cells

This study identifies enhanced mitochondrial respiration and glutamine-dependent TCA cycle as vulnerabilities in MYChigh breast cancer cells, showing synthetic lethality with complex I inhibitors.

BooLEVARD: Boolean Logical Evaluation of Activation and Repression in Directed pathways

BooLEVARD quantifies paths leading to node activation or repression in Boolean models, enhancing signal strength analysis in signaling networks.

Scaling up drug combination surface prediction

This paper develops an improved machine learning model for predicting drug combination dose-response surfaces, showing better performance than scalar-valued synergy score methods.

Predicting drug combination response surfaces

This paper introduces comboKR, a structured prediction method for drug combination response surfaces, showing improved performance in predicting responses for new drugs.

From Library to Landscape: Integrative Annotation Workflows for Compound Libraries in Drug Repurposing

The paper develops two annotation pipelines and dashboards to integrate chemical and bioactivity data for drug repurposing, validated on a compound library with over 5000 compounds.

Single-cell transcriptomes identify patient-tailored therapies for selective co-inhibition of cancer clones

The paper develops a machine learning model to identify patient-specific multi-targeting therapies using single-cell transcriptomic data for hematological cancers and solid tumors.

Attention-based approach to predict drug-target interactions across seven target superfamilies

This paper introduces an attention-based method to predict drug-target interactions across seven superfamilies, achieving high correlation and identifying missing activities in approved drugs.

Self-supervised learning for DNA sequences with circular dilated convolutional networks

The paper introduces a self-supervised deep learning framework for DNA sequence analysis that improves variant effect prediction and open chromatin region prediction across human and plant genomes.

OSCAR: Optimal subset cardinality regression using the L0-pseudonorm with applications to prognostic modelling of prostate cancer

OSCAR uses an L0-pseudonorm approach to select sparse prognostic features in prostate cancer, balancing model accuracy and clinical implementation costs.

Discovery of host-directed modulators of virus infection by probing the SARSCoV-2-host protein-protein interaction network

The paper identifies host proteins modulating SARS-CoV-2 infection by expanding the virus-host protein interaction network and testing chemical inhibitors of these targets.

Fully-automated and ultra-fast cell-type identification using specific marker combinations from single-cell transcriptomic data

ScType automates cell-type identification from scRNA-seq data using marker genes, achieving accurate and unbiased annotations across human and mouse tissues.

Modeling drug combination effects via latent tensor reconstruction

The paper introduces comboLTR, a method for predicting drug combination effects using latent tensor reconstruction, outperforming existing methods in speed and accuracy.

Patient-tailored design of AML cell subpopulation-selective drug combinations

This paper develops a computational-experimental approach to design patient-specific drug combinations for AML that are synergistic and minimally toxic.

Multiobjective optimization identifies cancer-selective combination therapies

This paper develops a multiobjective optimization method to identify cancer-selective drug combinations, validated in BRAF-V600E melanoma, showing improved selectivity through combinatorial targeting.