AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

MoReL: Multi-omics Relational Learning

Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield, Xiaoning Qian

ICLR 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein representation learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the MoReL FGW-based relational model instead of BCCACF microbiome-metabolite interaction inference · CF, negative accuracy >97%positive accuracy (%): 28.30\pm3.21 -> 56.16\pm1.85Improved
Add the microbiome graph as structured side information (ablation)MoReL on CF · CF, negative accuracy >97%positive accuracy (%): 56.16\pm1.85 -> 63.77\pm1.11Improved
Use MoReL rather than BCCAPrecision medicine interaction inference · Precision medicine, avg. degree 0.50prediction sensitivity (%): 46.88 \pm1.88 -> 53.16\pm0.96Improved
Use both view-specific graphs rather than only the microbiome graph (ablation)MoReL on CF · CFpositive accuracy (%): 82.70\pm4.70 -> 89.50\pm3.29Improved
Use MoReL_ss instead of BayReL with both views structuredCF interaction inference · CF, all views structuredpositive accuracy (%): 82.70\pm4.70 -> 89.50\pm3.29Improved
Use MoReL_ss instead of BayReL with both views structuredPrecision medicine interaction inference · Precision medicine, avg. degree 0.4prediction sensitivity (%): 47.90\pm0.43 -> 49.24\pm1.64Improved
Use MoReL_ss instead of BayReL with both views structuredPrecision medicine interaction inference · Precision medicine, avg. degree 0.5prediction sensitivity (%): 56.76\pm0.50 -> 58.92\pm0.40Improved
Use FGW-based MoReL instead of BayReL when samples are unpairedCF interaction inference · CF, unpaired samplespositive accuracy (%): 31.56 -> 63.24\pm2.13Improved
Randomly remove 10% of metabolite-view samples (ablation)MoReL_us on CF · CF, missing samplespositive accuracy (%): 63.77\pm1.11 -> 61.36\pm3.74No clear effect
Use MoReL instead of BayReLCF interaction inference with unpaired samples · CF, unpaired samplesnegative accuracy (%): 72 -> 97Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy