Papers for

biotech bioinformatics groups

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Inferred microRNAs improve drug action modeling from gene data

MIRCID: Inferred Hub-miRNAs Drive Cross-Task Improvements in Drug Mechanistic Modeling

Abstract: Drug mechanism-of-action (MoA) modeling commonly relies on perturbational transcriptomes, but matched microRNA (miRNA) measurements are often unavailable. Inferred regulatory features offer a scalable way to reuse these data. Here, we present MIRCID, a framework comparing gene expression with inferred transcription factor (TF) activity and miRNA expression across pathway classification and similarity-based MoA retrieval. HubmiRNet infers 414 pan-cancer hub miRNAs (HubmiRs) from 977 L1000 landmark genes, achieving a Pearson correlation coefficient of 87.72\%; its 1,298-output variant also outperformed SiCmiR on the full-miRNA task (71.21\% versus 67.30\%). In the evaluated comparisons, miRNA augmentation provided more consistent gains than TF activity. Generic embedding controls showed model-dependent utility, while complementarity analyses identified a distinct, partially linearly recoverable representation that retained gene-derived structure. Illustrative rescue cases linked improved classification to biologically plausible miRNA patterns in samples with weak transcriptional signatures. These findings support inferred HubmiRs as a biologically informed recoding of transcriptomic data for perturbational drug modeling, while leaving recovery of measured perturbational miRNA responses to further validation.

Fri 18 SeptMachine Learning
The gist
Scientists often study how drugs work by looking at changes in gene activity, but measurements of small molecules called microRNAs, which also affect cells, are usually missing. The authors created a new method called MIRCID that guesses these important microRNAs from gene data, helping to better classify drug effects and find similar drug actions. Their method showed stronger and more consistent improvements than existing approaches that guess other regulators. This suggests that inferred microRNAs can be a useful way to understand drug effects when direct microRNA data is unavailable, although future work is needed to confirm these guesses with actual measurements.
Open → 2609.21280v1