This record contains the source code supporting both the article (submitted to Bioinformatics, 2026) and the master's dissertation (PPGCC/UFMG, 2026) entitled "Virtual Immunohistochemical Staining for Pathological Complete Response Prediction in Triple-Negative Breast Cancer". The project predicts pathological complete response (pCR) in triple-negative breast cancer (TNBC) by combining H&E images with Ki-67 and PHH3 stains (real or virtually generated) through a biomarker-based spatial attention mechanism. Contents: bcs-kedro/ - Kedro project implementing the full pCR prediction pipeline: image preprocessing, generation of biomarker-based spa
Colonese, Henrique, Ayala, Daniel, Teodoro, George
Analysis code for the study 'Differentiating notified dengue from malaria in Kolkata from routine surveillance fields: a leakage-audited machine-learning study, 2014-2025'. Includes data preparation, the leakage-safe benchmark (seven classifiers, five class-imbalance strategies, five random splits and a temporal split), the leakage audit, field ablations, calibration and decision-curve analyses, figures, ward-level spatial statistics, a synthetic example dataset, and derived ward-level result tables without patient information. The Kolkata Municipal Corporation line-lists and the licensed ward boundaries are not included.
Biswas, Ankur, Das, Ayan, Mandal, Bithika, Das, Anirban, Chatterjee, Sankhadeep
Reproducibility package for the article "A Cognitive Digital Twin Framework (HYPRO) Integrating Ensemble Machine Learning and Physics-Based Modeling for Hybrid Rocket Motor Analysis and Diagnostics". The archive contains: hypro_core/ - computational core of HYPRO Pro v4.1.0: zero-dimensional internal-ballistics solver with Summerfield flow-separation limit, regression-rate model zoo (random forest, gradient boosting, AdaBoost, support-vector regression, elastic net, multilayer perceptron, voting and stacking ensembles), multi-channel signal tools (LabVIEW reader, joint pressure-thrust segmentation, magnitude-squared coherence, acquisition-fil
Elkhshen, Mohamed, Hashish, Anwer, Hassan, Ahmed Farid Ayad, Ahmed, Mahmoud Y. M.
The flowering phenology of many Tropical Mountain Forest tree species remains poorly understood, including flowering synchrony and its drivers across Neotropical ecosystems. We obtained herbarium records for 427 tree species from a long-term monitoring transect on the north-western Ecuadorian Andes, sourced from the Global Biodiversity Information Facility (GBIF) and the Herbario Nacional del Ecuador (QCNE). Using machine learning algorithms, we identified flowering phenophases from digitized specimen labels and applied circular statistics to build phenological calendars across six climatic regions within the Neotropics. We found 47,939 herba
Ordonez, Jenny Cristina, Tovar, Carolina, Walker, B.E., Wheeler, J., Ayala-Ruano, S., Aguirre-Carvajal, K., McMahon, Sean, Cuesta, F.
VesiclePy is a deep learning toolkit for vesicle analysis in serial electron microscopy data (with a special focus on large vesicles outside of synapse), providing tools for segmentation, classification, spatial and statistical analysis of vesicles, along with web-based proofreading tools and visualization capabilities, as well as neuron classification with vesicle and morphology information. see README.md files, both the main one and those in subfolders, for usage instructions. documentation also available in code itself.
Adhinarta, Jason, Fan, Yutian, Gohain, Adam, Lin, Michael, Nurkin, Paige, Ren, Richard, Roth, Micaela, Zhang, Shulin, Yakobe, Ayal, Yuste, Rafael, Wei, Donglai
Code and data for "A Machine Learning Approach for Detecting WPA3 Downgrade Attacks in Next-Generation Wi-Fi Systems", submitted to PLOS ONE. This repository includes preprocessing scripts, ML-based detection models, and evaluation metrics.
ayatareef
Code and data for "A Machine Learning Approach for Detecting WPA3 Downgrade Attacks in Next-Generation Wi-Fi Systems", submitted to PLOS ONE. This repository includes preprocessing scripts, ML-based detection models, and evaluation metrics.
ayatareef
The codes are used to generate the results and the figures associated with the following publication: M. Dora, S. Jaffard, D. Holcman. The WQN algorithm for EEG artifact removal in the absence of scale invariance, (to appear in) IEEE Transactions on Signal Processing 2024 EEG, EMG, and EOG data used in the present article can be obtained from publicly available in References: B. Blankertz, G. Dornhege, M. Krauledat, K.-R. M ̈uller, G. Curio, The non-invasive berlin brain–computer interface: fast acquisition of effective performance in untrained subjects, NeuroImage 37 (2) (2007) 539–550. K. T. Sweeney, H. Ayaz, T. E. Ward, M. Izzetoglu, S. F.
Dora, Matteo, Jaffard, Stéphane, Holcman, David
Long-term field monitoring of leaf pigment content is informative for understanding plant responses to environments distinct from regulated chambers but is impractical by conventional destructive measurements. We developed PlantServation, a method incorporating robust image-acquisition hardware and deep learning-based software that extracts leaf color by detecting plant individuals automatically. As a case study, we applied PlantServation to examine environmental and genotypic effects on the pigment anthocyanin content estimated from leaf color. We analyzed >4 million images of small individuals of four Arabidopsis species in the field, where
Akiyama, Reiko, Goto, Takao, Tameshige, Toshiaki, Sugisaka, Jiro, Kuroki, Ken, Sun, Jianqiang, Akita, Junichi, Hatakeyama, Masaomi, Kudoh, Hiroshi, Kenta, Tanaka, Tonouchi, Aya, Shimahara, Yuki, Sese, Jun, Kutsuna, Natsumaro, Shimizu-Inatsugi, Rie, Shimizu, Kentaro
This is the python code implementation of the experiments presented in the manuscript titled "Spectral imaging enables contrast agent-free real-time ischemia monitoring in laparoscopic surgery". It's main components are the definitions of the deep learning model utilized for ischemia detection, the implementation of the region of interest tracking, and the code used to analyze inter-patient variability with mixed models.
Leonardo Ayala, Tim Adler, Silvia Seidlitz, Sebastian Wirkert, Alexander Seitel, Jan Sellner, Anant Vemuri, Manuel Wiesenfarth, Nicholas Schreck, Sebastian Pirmann, Annette Kopp-Schneider, Lena Maier-Hein
Background: Gene-gene co-expression correlations measured by mRNA-sequencing (RNA-seq) can be used to predict gene annotations based on the co-variance structure within these data. In our prior work, we showed that uniformly aligned RNA-seq co-expression data from thousands of diverse studies is highly predictive of both gene annotations and protein-protein interactions. However, the performance of the predictions varies depending on whether the gene annotations and interactions are cell type and tissue specific or agnostic. Tissue and cell type specific gene-gene co-expression data can be useful for making more accurate predictions because m
Lachmann, Alexander, Rizzo, Kaeli, Bartal, Alon, Jeon, Minji, Clarke, Daniel J. B., Ma'ayan, Avi
General This is the 1.4.0 release for Coqui STT, the deep learning toolkit for speech-to-text. In accordance with semantic versioning , this version is backwards compatible with previous 1.x versions. The compatibility guarantees of our semantic versioning cover the deployment APIs: the C API and all the official language bindings: Python, Node.JS/ElectronJS and Java/Android. You can get started with Coqui STT 1.4.0 by following the steps in our documentation . Compatible pre-trained models are available in the Coqui Model Zoo . We also include example audio files: audio-1.4.0.tar.gz which can be used to test the engine, and checkpoint files
Reuben Morais, lissyx, Kelly Davis, Tilman Kamp, Josh Meyer, Chris Lord, Catalin Voss, Danny Waser, Carlos Fonseca, Alessio Placitelli, Anurag Dixit, kdavis-coqui, Yi-Hua Chiu, Aya-AlJafari, Rob, Mike C. Fletcher, Bernardo, Francis Tyers, Shubham Kumar, Erik Ziegler, Andre Natal, Daniel Souza, Richard Hamnett, Sebastian, bprfh, Nicolas Panel, aayagar001, Nanshu, Rahul Karmakar, Juan Díaz
