Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
MoReL: Multi-omics Relational Learning
Authors: Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield, Xiaoning Qian
ICLR 2022 | Venue PDF | LLM Run Details | Input Tokens: 20,146 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,182 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experiments on several real-world datasets demonstrate the enhanced performance of Mo Re L in inferring meaningful interactions compared to existing baselines. |
| Researcher Affiliation | Academia | Department of Electrical and Computer Engineering, Texas A&M University |
| Pseudocode | Yes | The pseudo-code in Algorithm 1 (Appendix A.1) provides the details of the FGW distance calculation procedure. |
| Open Source Code | No | The paper does not contain an explicit statement about the availability of source code or a link to a code repository. |
| Open Datasets | Yes | We use the same datasets as Bay Re L (Hajiramezanali et al., 2020), i.e. microbiomemetabolite interactions in cystic fibrosis (CF) and gene-drug interactions in precision medicine. Dataset description and graph construction procedure are detailed in Appendix A.2. (Morton et al., 2019; Quinn et al., 2015; Lee et al., 2018; Wagner et al., 2016) |
| Dataset Splits | Yes | The remaining 20% of the reported molecules are considered as a validation set and are only used for the early stopping purpose. |
| Hardware Specification | Yes | All the experiments are performed on a workstation with a single NVIDIA P100 GPU. |
| Software Dependencies | No | The paper states, "We have implemented Mo Re L and all the competing methods in Tensorflow (Abadi et al., 2015)," but it does not specify a version number for TensorFlow or any other software dependencies. |
| Experiment Setup | Yes | The temperature for relaxed Bernoulli distribution is set to 0.3. The normalizing parameter γ in equation 6 is 0.9 while α and β in DFGW are set to 1 and 0.5, respectively. We used the exponential decaying learning rate with the decay rate of 0.01 and initial learning rate of 0.01. |