Experiments

Searchable full-text extractions: founding hypothesis, core claims, experimental setups, key results and statistics — pulled out of each paper as structure. Search a cell line, an assay or an entity (e.g. HUH7) and find every paper that worked with it. This corpus stands on its own: most entries carry no reproduction assessment (yet).

• maxATAC: Genome-scale transcription-factor binding prediction from ATAC-seq with deep neural networks.

  PMID 36719906 · PMC9917285 · PLoS computational biology · 2023 · 8 claims · 6 setups

  Has reproduction · 98

  maxATAC is a suite of deep neural network models enabling state-of-the-art, genome-scale TFBS prediction from ATAC-seq, with models for 127 human transcription factors

  lines hepg2 types single chip-seq omni-atac-seq atac-seq

• SurvConvMixer: robust and interpretable cancer survival prediction based on ConvMixer using pathway-level gene expression images.

  PMID 38539106 · PMC10967213 · BMC bioinformatics · 2024 · 7 claims · 6 setups

  Has reproduction · 77

  SurvConvMixer reformats KEGG Pathways-in-Cancer gene expression values into pathway-level 2D gene expression images and applies a ConvMixer-based model for overall survival prediction

  luad lung bulk gene machine

• CONTRAST: a discriminative, phylogeny-free approach to multiple informant de novo gene prediction.

  PMID 18096039 · PMC2246271 · Genome biology · 2007 · 8 claims · 5 setups

  Full-text index only

  CONTRAST predicts exact coding region structures for 65% more human genes than the previous state-of-the-art de novo predictor (N-SCAN)

  genome sequence drosophila novo gene coding

• Accurate splice site prediction using support vector machines.

  PMID 18269701 · PMC2230508 · BMC bioinformatics · 2007 · 8 claims · 5 setups

  Full-text index only

  Weighted degree (WD) kernel SVMs outperform Markov Chains, GeneSplicer and SpliceMachine for genome-wide splice site recognition

  nn269 dgsplicer caenorhabditis arabidopsis svm genome-wide

• Comprehensive benchmarking of large language models for RNA secondary structure prediction.

  PMID 40205851 · PMC11982019 · Briefings in bioinformatics · 2025 · 7 claims · 4 setups

  Has reproduction · 88

  Existing RNA-LLMs had not previously been evaluated for secondary structure prediction in a unified, fair experimental setup with the same datasets and prediction model.

  archiveii bprna large-scale secondary cross-family self-supervised

• Prediction by graph theoretic measures of structural effects in proteins arising from non-synonymous single nucleotide polymorphisms.

  PMID 18654622 · PMC2447880 · PLoS computational biology · 2008 · 8 claims · 5 setups

  Full-text index only

  Bongo identifies mutations causing local and global structural effects with a remarkably low false positive rate

  p53 1bpi mutations disease-associated graph correlation structural

• Enhanced Generalizability of RNA Secondary Structure Prediction via Convolutional Block Attention Network and Ensemble Learning.

  PMID 40871599 · PMC12388828 · Molecules (Basel, Switzerland) · 2025 · 8 claims · 8 setups

  Has reproduction · 87

  TrioFold integrates base-pairing clues from thermodynamic- and DL-based methods via ensemble learning and a convolutional block attention mechanism to enhance RSS prediction generalizability.

  testseta bprna-new ts-inter individual jaccard pca ensemble

• Evaluating native-like structures of RNA-protein complexes through the deep learning method.

  PMID 36828844 · PMC9958188 · Nature communications · 2023 · 8 claims · 7 setups

  Has reproduction · 67

  DRPScore identifies native-like RNA-protein structures with higher success rates than ITScore-PR, DARS-RNP, and 3dRPC across bound and unbound testing sets.

  bound-bound unbound-bound unbound-unbound bacillus structure interface secondary

• Integrating alternative splicing detection into gene prediction.

  PMID 15705189 · PMC550657 · BMC bioinformatics · 2005 · 8 claims · 4 setups

  Full-text index only

  An integrative intrinsic/extrinsic method was implemented in the gene finder EuGÈNE (as EuGÈNE-M) to detect AS evidence from aligned transcripts and generate alternative optimal gene predictions consistent with each detected AS event.

  arabidopsis araset thaliana transcript-to-genome initio comparative

• Update of the G2D tool for prioritization of gene candidates to inherited diseases.

  PMID 17478516 · PMC1933178 · Nucleic acids research · 2007 · 8 claims · 4 setups

  Full-text index only

  G2D is a web server that prioritizes candidate genes for inherited diseases using three distinct algorithms based on different input information.

  genome genomic etrb computational literature go-similarity

• A space-efficient and accurate method for mapping and aligning cDNA sequences onto genomic sequence.

  PMID 18344523 · PMC2377433 · Nucleic acids research · 2008 · 7 claims · 6 setups

  Full-text index only

  Spaln maps and aligns large cDNA sequence sets onto whole mammalian genomes using substantially less memory than comparable existing tools

  unigene shuffled real genomes genome-wide alignment gene

• Functional analysis of novel SNPs and mutations in human and mouse genomes.

  PMID 19091009 · PMC2638150 · BMC bioinformatics · 2008 · 8 claims · 7 setups

  Full-text index only

  FANS streamlines functional analysis of novel SNPs and mutations into a simplified, few-click, four-step procedure.

  apoe 11-nucleotide sequence genomic manual automated exonic

• Analysis of protein sequence and interaction data for candidate disease gene prediction.

  PMID 17020920 · PMC1636487 · Nucleic acids research · 2006 · 8 claims · 7 setups

  Full-text index only

  Combining CPS and CMP using known disease genes as input achieves sensitivity 0.52 and specificity 0.97, reducing candidate lists 13-fold

  ophid biocarta kegg pfam-annotated common benchmarking multiple-interval

• SNAP: predict effect of non-synonymous polymorphisms on function.

  PMID 17526529 · PMC1920242 · Nucleic acids research · 2007 · 7 claims · 8 setups

  Full-text index only

  SNAP, a neural network-based method using sequence-derived information, predicts whether a non-synonymous SNP is neutral or non-neutral for protein function

  combined escherichia bacteriophage hiv-1 neural benchmark comparative

• Macrel: antimicrobial peptide screening in genomes and metagenomes.

  PMID 33384902 · PMC7751412 · PeerJ · 2020 · 8 claims · 8 setups

  Has reproduction · 83

  Macrel is an end-to-end pipeline that predicts high-quality AMP candidates from peptides, contigs, or reads of (meta)genomes

  curated hemopi-1 xiao cd-hit random amp homology-aware

• miRGen: a database for the study of animal microRNA genomic organization and function.

  PMID 17108354 · PMC1669779 · Nucleic acids research · 2007 · 8 claims · 6 setups

  Full-text index only

  miRGen is an integrated database combining Genomics, Targets, and Clusters interfaces to study miRNA genomic organization and function across 11 animal genomes

  animal genome mouse-human mirna genomic mirna cross-species

• MACSIMS: multiple alignment of complete sequences information management system.

  PMID 16792820 · PMC1539025 · BMC bioinformatics · 2006 · 8 claims · 5 setups

  Full-text index only

  MACSIMS is a multiple alignment-based information management system combining knowledge-based database mining with ab initio sequence predictions

  balibase-derived sequences same query automatic database initio

• Predicting the phenotypic effects of non-synonymous single nucleotide polymorphisms based on support vector machines.

  PMID 18005451 · PMC2216041 · BMC bioinformatics · 2007 · 8 claims · 5 setups

  Full-text index only

  Parepro, an SVM-based method integrating three attribute sets (RD, MI, IE) derived from evolutionary and residue-property information, predicts whether an nsSNP is deleterious or neutral.

  sequences target svm benchmark homology

• fREDUCE: detection of degenerate regulatory elements using correlation with expression.

  PMID 17941998 · PMC2174516 · BMC bioinformatics · 2007 · 6 claims · 5 setups

  Full-text index only

  fREDUCE is a computational method that detects weak or degenerate binding motifs from gene expression or ChIP-chip data by exhaustive search of degenerate IUPAC oligonucleotides

  saccharomyces cerevisiae hepatocytes chip-chip motif-finding gene

• Adaptive learning embedding features to improve the predictive performance of SARS-CoV-2 phosphorylation sites.

  PMID 37847658 · PMC10628388 · Bioinformatics (Oxford, England) · 2023 · 7 claims · 3 setups

  Has reproduction · 67

  PSPred-ALE, a deep learning predictor using a self-adaptive learning embedding algorithm, automatically extracts contextual sequence features and identifies SARS-CoV-2 phosphorylation sites without feature engineering.

  lung peptide same bulk deep traditional