Yishai Shimoni

Yishai Shimoni

Auto-generated profile, based on publicly available information

Yishai Shimoni

IBM Research -Haifa

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 February 2018 in PLOS Computational Biology
Verified
Journal Article
Open access
PDF file
YSYishai Shimoni
Yishai Shimoni
One of the goals of cancer research is to identify a set of genes that cause or control disease progression. However, although multiple such gene sets were published, these are usually in very poor agreement with each other, and very few of the genes proved to be functional therapeutic targets. Furthermore, recent findings from a breast cancer gene-expression cohort showed that sets of genes selected randomly can be used to predict survival with a much higher probability than expected. These results imply that many of the genes identified in breast cancer gene expression analysis may not be causal of cancer progression, even though they can still be highly predictive of prognosis. We performed a similar analysis on all the cancer types available in the cancer genome atlas (TCGA), namely, estimating the predictive power of random gene sets for survival. Our work shows that most cancer types exhibit the property that random selections of genes are more predictive of survival than expected. In contrast to previous work, this property is not removed by using a proliferation signature, which implies that proliferation may not always be the confounder that drives this property. We suggest one possible solution in the form of data-driven sub-classification to reduce this property significantly. Our results suggest that the predictive power of random gene sets may be used to identify the existence of sub-classes in the data, and thus may allow better understanding of patient stratification. Furthermore, by reducing the observed bias this may allow more direct identification of biologically relevant, and potentially causal, genes. Multiple gene sets have been published as predictive of cancer progression and metastasis in several cancer types. Although many of these sets proved to be highly predictive of survival, even gene sets for the same cancer (but from different data-sets or different analyses) exhibit very little overlap and to date did not provide functional therapeutic targets. Recent studies found that in breast cancer, even random gene sets can predict survival much better than would be expected, and on average are better than many published gene sets. Together, these results undermine the causal role of the published gene sets and their potential clinical implications. We show that random gene sets predict survival in many cancer types, and that this property no longer exists after splitting the data into subclasses based on data-driven clusters. This suggests that such sub-classification could increase the likelihood to identify causal genes that are potential therapeutic targets, and that this property can be used as an indication that there may be subclasses within the dataset.

8 February 2007 in Physical Review A
Verified
Journal Article
Open access
YSYishai Shimoni
Yishai Shimoni
OBOfer Biham
Ofer Biham

15 April 2024 in Epidemiology
Verified
Journal Article
Open access
RGRom Gutman
Rom Gutman
EKEhud Karavani
Ehud Karavani
YSYishai Shimoni
Yishai Shimoni
Theoretical guarantees for causal inference using propensity scores are partially based on the scores behaving like conditional probabilities. However, prediction scores between zero and one do not necessarily behave like probabilities, especially when output by flexible statistical estimators. We perform a simulation study to assess the error in estimating the average treatment effect before and after applying a simple and well-established postprocessing method to calibrate the propensity scores. We observe that postcalibration reduces the error in effect estimation and that larger improvements in calibration result in larger improvements in effect estimation. Specifically, we find that expressive tree-based estimators, which are often less calibrated than logistic regression-based models initially, tend to show larger improvements relative to logistic regression-based models. Given the improvement in effect estimation and that postcalibration is computationally cheap, we recommend its adoption when modeling propensity scores with expressive models.

28 February 2025 in iScience
Verified
Journal Article
Open access
LSLiran Szlak
Liran Szlak
JSJingdi Shen
Jingdi Shen
EZEden Zohar
Eden Zohar
EKEhud Karavani
Ehud Karavani
DRDaniel Rotroff
Daniel Rotroff
LJLara Jehi
Lara Jehi
We conducted a retrospective observational study to examine whether anti-inflammatory medications prescribed peri-operatively of resective brain surgery can reduce long-term seizure recurrence for individuals with drug-resistant focal epilepsy. We used insurance-claims data from across the United States to screen medications prescribed to 1,993 individuals undergoing epilepsy. We then validated the results in a well-characterized cohort of 671 epilepsy patients from a major surgical center. Twelve medications met the screening criteria and were evaluated, identifying dexamethasone and zonisamide as potentially beneficial. Dexamethasone reduced seizure recurrence by 42% over 9 years of follow-up (hazard-ratio = 0.742; 95% CI = 0.662, 0.831), and zonisamide reduced recurrence by 33% (HR = 0.782; 95% CI = 0.667, 0.917). While dexamethasone could not be validated, analysis of zonisamide in the clinical cohort corroborated the beneficial effect (HR = 0.828; 95% CI = 0.706, 0.971). If prospectively validated, this study suggests surgeons could improve long-term outcomes of epilepsy surgery by medically reducing neuro-inflammation in the surgical bed.

5 December 2024 in arXiv
Verified
Preprint
Open access
PDF file
YKYoav Kan-Tor
Yoav Kan-Tor
MDMichael Morris Danziger
Michael Morris Danziger
EZEden Zohar
Eden Zohar
MNMatan Ninio
Matan Ninio
YSYishai Shimoni
Yishai Shimoni
The application of deep learning methods, particularly foundation models, in biological research has surged in recent years. These models can be text-based or trained on underlying biological data, especially omics data of various types. However, comparing the performance of these models consistently has proven to be a challenge due to differences in training data and downstream tasks. To tackle this problem, we developed an architecture-agnostic benchmarking approach that, instead of evaluating the models directly, leverages entity representation vectors from each model and trains simple predictive models for each benchmarking task. This ensures that all types of models are evaluated using the same input and output types. Here we focus on gene properties collected from professionally curated bioinformatics databases. These gene properties are categorized into five major groups: genomic properties, regulatory functions, localization, biological processes, and protein properties. Overall, we define hundreds of tasks based on these databases, which include binary, multi-label, and multi-class classification tasks. We apply these benchmark tasks to evaluate expression-based models, large language models, protein language models, DNA-based models, and traditional baselines. Our findings suggest that text-based models and protein language models generally outperform expression-based models in genomic properties and regulatory functions tasks, whereas expression-based models demonstrate superior performance in localization tasks. These results should aid in the development of more informed artificial intelligence strategies for biological understanding and therapeutic discovery. To ensure the reproducibility and transparency of our findings, we have made the source code and benchmark data publicly accessible for further investigation and expansion at github.com/BiomedSciAI/gene-benchmark.

20 March 2018 in arXiv
Verified
Preprint
Open access
PDF file
YSYishai Shimoni
Yishai Shimoni
CYChen Yanover
Chen Yanover
EKEhud Karavani
Ehud Karavani
YGYaara Goldschmnidt
Yaara Goldschmnidt
Causal inference analysis is the estimation of the effects of actions on outcomes. In the context of healthcare data this means estimating the outcome of counter-factual treatments (i.e. including treatments that were not observed) on a patient's outcome. Compared to classic machine learning methods, evaluation and validation of causal inference analysis is more challenging because ground truth data of counter-factual outcome can never be obtained in any real-world scenario. Here, we present a comprehensive framework for benchmarking algorithms that estimate causal effect. The framework includes unlabeled data for prediction, labeled data for validation, and code for automatic evaluation of algorithm predictions using both established and novel metrics. The data is based on real-world covariates, and the treatment assignments and outcomes are based on simulations, which provides the basis for validation. In this framework we address two questions: one of scaling, and the other of data-censoring. The framework is available as open source code at https://github.com/IBM-HRL-MLHLS/IBM-Causal-Inference-Benchmarking-Framework