#29 · Genomics
Deep learning refines variant, splicing and RNA modification calls from sequencing reads
The dominant thread is learned models applied directly to sequencing-derived data, with fusion of heterogeneous inputs as a recurring design choice. Dual-SVF fuses sequence content with alignment topology to filter long-read structural variant calls, and VCboost applies a deep learning post-calling filter to reduce false-positive SNP and indel calls in challenging genomic regions. WattmaMod uses self-supervised pretraining for multi-modification RNA detection from nanopore direct RNA sequencing. MycoCirc is a pan-fungal multimodal pretrained model that predicts circRNAs from genome sequence, reporting AUROC of 0.69 to 0.70, and is accompanied by a database resource. IRCAS addresses alternative splicing detection, rectification and classification without a genome reference. Two of the five items are preprints, and the circRNA model's reported AUROC indicates modest discrimination.
Published papers
IRCAS: a novel end-to-end approach to identify, rectify, and classify comprehensive alternative splicing events in a transcriptome without genome reference.
IRCAS is an end-to-end reference-free framework for alternative splicing detection, rectification, and classification in transcriptomes, using colored de…
VCboost: reducing false positives in long-read variant calling for single-nucleotide polymorphism and indel detection in challenging genomic regions.
VCboost, a deep learning post-calling filter, reduces false-positive SNP and indel calls from long-read sequencing, improving precision and F1 in challenging…
Dual-SVF: a robust knowledge-guided multimodal method for structural variant filtering in long-read sequencing.
Dual-SVF is an open-source, VCF-compatible multimodal method that filters long-read structural variant calls by fusing sequence content with alignment topology…
Preprints
MycoCirc: A Pan-Fungal Multi-Modal Pretrained Model for Fungal circRNA Prediction from Genome Sequence
mycoCirc is a pan-fungal multi-modal pretrained model predicting circRNAs from genome sequence (AUROC 0.69-0.70), plus mycoCircAtlas, a database of 319,860…
WattmaMod enables high-resolution and extensible RNA modification profiling for nanopore direct RNA sequencing
WattmaMod is a deep learning framework for multi-modification RNA detection from nanopore direct RNA sequencing, using self-supervised pretraining and…
Topic history
| Date | Rank |
|---|---|
| #29 | |
| #6 | |
| #6 | |
| #16 | |
| #2 | |
| #1 | |
| #2 | |
| #14 | |
| #22 | |
| #7 | |
| #18 | |
| #33 | |
| #24 | |
| #27 | |
| #26 | |
| #33 | |
| #39 | |
| #35 | |
| #38 | |
| #12 | |
| #21 | |
| #29 | |
| #38 | |
| #9 | |
| #26 | |
| #20 | |
| #26 | |
| #23 | |
| #21 | |
| #7 | |
| #19 | |
| #18 | |
| #22 | |
| #34 | |
| #32 | |
| #17 | |
| #33 | |
| #18 | |
| #23 | |
| #29 | |
| #20 | |
| #34 | |
| #29 | |
| #34 | |
| #9 | |
| #26 | |
| #27 | |
| #27 | |
| #30 | |
| #30 | |
| #33 | |
| #2 | |
| #4 | |
| #6 | |
| #5 | |
| #19 | |
| #1 | |
| #10 | |
| #33 | |
| #38 | |
| #38 | |
| #23 | |
| #40 |