D4 · 变异效应与进化

RNA 深度突变扫描效应预测

Predict mutation effects across RNA deep-mutational-scanning assays.

RNA DMS effect prediction

T38RNAregression/ranking

任务定义

输入粒度
mutant sequence or mutation
生物学目标
experimental RNA fitness/function
输出表示
continuous assay score
ML formulation
regression/ranking
计数说明
NR

Benchmark coverage

3 个 benchmark 覆盖该任务

B10有公开数值结果

RNA-Scope

Board is public; DeepASmRNA and DeeReCT-PolyA/PAS are exposed as distinct tracks; verify exact release and frozen splits before comparative claims.

79 个 benchmark 数值协议 · 2,093 条 benchmark 全局结果(非 task 小计)
B11有公开数值结果

RNAGym

Three core tasks plus a task-family view of the ribozyme-assay subset; the subset track is separated from the aggregate DMS-effect track.

2 个 benchmark 数值协议 · 7 条 benchmark 全局结果(非 task 小计)
B29无公开数值结果

NABench

Large-scale nucleotide fitness benchmark; verify repository release before production adoption.

0 个 benchmark 数值协议 · 0 条 benchmark 全局结果(非 task 小计)

评测协议

2 个口径单元

ProtocolTrackSplit / subset可比状态
PROT-SUPP-B11-RNAGYM-T2fitness overall | RNAGym original benchmark table
B11-TR01
full RNAGym fitness benchmark aggregate
fitness overall across the source-defined assay collection
insufficient_protocol_detail
assay-level aggregation details;external_data_policy;inference_budget
PROT-SUPP-B11-BASEPROMPT-T2fitness overall | BasePrompt same-source table
B11-TR01
full RNAGym fitness benchmark aggregate
fitness overall across the source-defined assay collection
insufficient_protocol_detail
assay-level aggregation details;external_data_policy;inference_budget