scan.json (16098B)
1 { 2 "paper": { 3 "title": "Advancing large-molecule discovery with a unified digital platform for data analysis and workflow management", 4 "authors": ["Eriberto Natali", "Jana Hersch", "Christoph Freiberg", "Stephan Steigele"], 5 "year": 2025, 6 "venue": "mAbs", 7 "doi": "10.1080/19420862.2025.2555346" 8 }, 9 "checklist": { 10 "artifacts": { 11 "code_released": { 12 "applies": false, 13 "answer": false, 14 "justification": "This is a narrative review paper with no original code or software artifact to release." 15 }, 16 "data_released": { 17 "applies": false, 18 "answer": false, 19 "justification": "The paper states 'There are no new data associated with this article.' This is a conceptual review with no dataset." 20 }, 21 "environment_specified": { 22 "applies": false, 23 "answer": false, 24 "justification": "No computational experiments were conducted; this is a narrative review of platform concepts." 25 }, 26 "reproduction_instructions": { 27 "applies": false, 28 "answer": false, 29 "justification": "No experiments to reproduce; this is a review/perspective paper." 30 } 31 }, 32 "statistical_methodology": { 33 "confidence_intervals_or_error_bars": { 34 "applies": false, 35 "answer": false, 36 "justification": "No experiments or quantitative analyses are presented; this is a narrative review." 37 }, 38 "significance_tests": { 39 "applies": false, 40 "answer": false, 41 "justification": "No comparative claims backed by data are made; purely a conceptual review." 42 }, 43 "effect_sizes_reported": { 44 "applies": false, 45 "answer": false, 46 "justification": "No quantitative results are reported in this review." 47 }, 48 "sample_size_justified": { 49 "applies": false, 50 "answer": false, 51 "justification": "No empirical study with samples; narrative review only." 52 }, 53 "variance_reported": { 54 "applies": false, 55 "answer": false, 56 "justification": "No experiments conducted; no variance to report." 57 } 58 }, 59 "evaluation_design": { 60 "baselines_included": { 61 "applies": false, 62 "answer": false, 63 "justification": "No system evaluation is performed. The paper describes platform concepts but does not benchmark them." 64 }, 65 "baselines_contemporary": { 66 "applies": false, 67 "answer": false, 68 "justification": "No evaluation or comparison is conducted." 69 }, 70 "ablation_study": { 71 "applies": false, 72 "answer": false, 73 "justification": "No system or method is evaluated; no ablation possible." 74 }, 75 "multiple_metrics": { 76 "applies": false, 77 "answer": false, 78 "justification": "No evaluation metrics are used; this is a conceptual review." 79 }, 80 "human_evaluation": { 81 "applies": false, 82 "answer": false, 83 "justification": "No system outputs are evaluated by humans; this is a review paper." 84 }, 85 "held_out_test_set": { 86 "applies": false, 87 "answer": false, 88 "justification": "No datasets or test sets involved." 89 }, 90 "per_category_breakdown": { 91 "applies": true, 92 "answer": true, 93 "justification": "The paper organizes its review by platform capability categories (molecule registration, production, characterization, AI/ML) and compares three commercial platforms (Dotmatics, Genedata, Schrödinger) across these dimensions." 94 }, 95 "failure_cases_discussed": { 96 "applies": true, 97 "answer": true, 98 "justification": "The paper discusses limitations and gaps in existing platforms, e.g., Dotmatics initially lacking multi-specific support, Schrödinger lacking end-to-end registration, and general challenges with data silos and training data availability." 99 }, 100 "negative_results_reported": { 101 "applies": false, 102 "answer": false, 103 "justification": "No experiments are conducted; negative results are not applicable to this narrative review." 104 } 105 }, 106 "claims_and_evidence": { 107 "abstract_claims_supported": { 108 "applies": true, 109 "answer": true, 110 "justification": "The abstract claims the paper 'outlines state-of-the-art concepts behind a digital platform for automating and streamlining the discovery of new large-molecule treatments,' which is what the body delivers — a descriptive review of platform concepts and examples." 111 }, 112 "causal_claims_justified": { 113 "applies": false, 114 "answer": false, 115 "justification": "The paper makes no testable causal claims. It describes platform concepts and future directions without claiming one approach causes better outcomes based on data." 116 }, 117 "generalization_bounded": { 118 "applies": true, 119 "answer": false, 120 "justification": "The paper makes broad claims about what unified platforms 'must' support and how AI 'promises to open a new avenue' without bounding these to specific evidence or tested settings. Claims like 'AI's biggest impact is likely in the de-novo design of antibodies' are speculative and unbounded." 121 }, 122 "alternative_explanations_discussed": { 123 "applies": false, 124 "answer": false, 125 "justification": "No empirical results are presented, so alternative explanations are not applicable." 126 } 127 }, 128 "setup_transparency": { 129 "model_versions_specified": { 130 "applies": false, 131 "answer": false, 132 "justification": "No models are used or evaluated in this review paper." 133 }, 134 "prompts_provided": { 135 "applies": false, 136 "answer": false, 137 "justification": "No prompting is used; this is a review paper." 138 }, 139 "hyperparameters_reported": { 140 "applies": false, 141 "answer": false, 142 "justification": "No experiments conducted; no hyperparameters relevant." 143 }, 144 "scaffolding_described": { 145 "applies": false, 146 "answer": false, 147 "justification": "No agentic scaffolding is used." 148 }, 149 "data_preprocessing_documented": { 150 "applies": false, 151 "answer": false, 152 "justification": "This is a narrative review, not a systematic review with a documented search/filtering pipeline." 153 } 154 }, 155 "limitations_and_scope": { 156 "limitations_section_present": { 157 "applies": true, 158 "answer": false, 159 "justification": "There is no dedicated limitations section. The 'Future challenges' section discusses open problems but does not discuss limitations of the review itself." 160 }, 161 "threats_to_validity_specific": { 162 "applies": true, 163 "answer": false, 164 "justification": "No threats to validity are discussed. The paper does not acknowledge potential biases in its coverage or limitations of its analysis." 165 }, 166 "scope_boundaries_stated": { 167 "applies": true, 168 "answer": false, 169 "justification": "The paper does not explicitly state what it does NOT cover. It mentions not discussing ELNs but does not bound its claims about AI or platform capabilities to specific evidence." 170 } 171 }, 172 "data_integrity": { 173 "raw_data_available": { 174 "applies": false, 175 "answer": false, 176 "justification": "No data collected; the paper states 'There are no new data associated with this article.'" 177 }, 178 "data_collection_described": { 179 "applies": true, 180 "answer": false, 181 "justification": "The paper does not describe how the reviewed literature or platform examples were selected. No search methodology is documented." 182 }, 183 "recruitment_methods_described": { 184 "applies": false, 185 "answer": false, 186 "justification": "No human participants; no recruitment applicable." 187 }, 188 "data_pipeline_documented": { 189 "applies": true, 190 "answer": false, 191 "justification": "No systematic review methodology is described. The selection of platforms (Dotmatics, Genedata, Schrödinger) appears ad hoc with no documented criteria beyond 'broadest available coverage' and 'reported implementations in the scientific literature.'" 192 } 193 }, 194 "conflicts_of_interest": { 195 "funding_disclosed": { 196 "applies": true, 197 "answer": true, 198 "justification": "The funding section states: 'The author(s) reported there is no funding associated with the work featured in this article.'" 199 }, 200 "affiliations_disclosed": { 201 "applies": true, 202 "answer": true, 203 "justification": "All four authors are disclosed as employees of Genedata AG, a company whose platform (Genedata Biologics, Genedata Biopharma Platform) is prominently featured in the review." 204 }, 205 "funder_independent_of_outcome": { 206 "applies": false, 207 "answer": false, 208 "justification": "No external funding reported; the work is unfunded per the authors' statement." 209 }, 210 "financial_interests_declared": { 211 "applies": true, 212 "answer": true, 213 "justification": "The disclosure statement reads: 'Eriberto Natali, Jana Hersch, Christoph Freiberg, and Stephan Steigele report a relationship with Genedata AG that includes employment.'" 214 } 215 }, 216 "contamination": { 217 "training_cutoff_stated": { 218 "applies": false, 219 "answer": false, 220 "justification": "No pre-trained model is evaluated on any benchmark." 221 }, 222 "train_test_overlap_discussed": { 223 "applies": false, 224 "answer": false, 225 "justification": "No model evaluation is conducted." 226 }, 227 "benchmark_contamination_addressed": { 228 "applies": false, 229 "answer": false, 230 "justification": "No benchmark evaluation is performed." 231 } 232 }, 233 "human_studies": { 234 "pre_registered": { 235 "applies": false, 236 "answer": false, 237 "justification": "No human participants in this review paper." 238 }, 239 "irb_or_ethics_approval": { 240 "applies": false, 241 "answer": false, 242 "justification": "No human participants." 243 }, 244 "demographics_reported": { 245 "applies": false, 246 "answer": false, 247 "justification": "No human participants." 248 }, 249 "inclusion_exclusion_criteria": { 250 "applies": false, 251 "answer": false, 252 "justification": "No human participants." 253 }, 254 "randomization_described": { 255 "applies": false, 256 "answer": false, 257 "justification": "No human participants." 258 }, 259 "blinding_described": { 260 "applies": false, 261 "answer": false, 262 "justification": "No human participants." 263 }, 264 "attrition_reported": { 265 "applies": false, 266 "answer": false, 267 "justification": "No human participants." 268 } 269 }, 270 "cost_and_practicality": { 271 "inference_cost_reported": { 272 "applies": false, 273 "answer": false, 274 "justification": "This is a review/perspective paper with no method of its own to cost." 275 }, 276 "compute_budget_stated": { 277 "applies": false, 278 "answer": false, 279 "justification": "No computation performed; narrative review only." 280 } 281 } 282 }, 283 "claims": [ 284 { 285 "claim": "A unified digital platform covering molecule registration, production, characterization, and analysis is needed to replace the current fragmented approach of multiple software tools and manual processes in large-molecule discovery.", 286 "evidence": "The paper describes the proliferation of disconnected software (LIMS, ELNs, Excel, PowerPoint, email) and outlines four platform requirements in the 'Building blocks' section. Examples of implementations at Sanofi, AstraZeneca, and others are cited.", 287 "supported": "moderate" 288 }, 289 { 290 "claim": "AI and foundation models will enable de-novo antibody design and end-to-end discovery workflows.", 291 "evidence": "The 'Rise of AI and machine-learning' section cites examples from Eli Lilly (mAb solubility prediction), Sanofi (solution behavior prediction), Merck (BioPhi humanization), and references to AlphaFold. However, these are citations of others' work, not original evidence.", 292 "supported": "weak" 293 }, 294 { 295 "claim": "Genedata, Dotmatics, and Schrödinger represent the platforms with the broadest coverage of antibody discovery workflows.", 296 "evidence": "The 'Current platforms' section describes these three, stating the selection criteria as 'broadest available coverage of the antibody discovery process across multiple systems in a single portfolio and with reported implementations in the scientific literature.' No systematic comparison methodology is provided.", 297 "supported": "weak" 298 } 299 ], 300 "methodology_tags": ["qualitative"], 301 "key_findings": "This narrative review describes the concept of a unified biopharma digital platform for large-molecule (antibody) discovery, covering molecule registration, production, characterization, and analysis. It surveys three commercial platforms (Dotmatics, Genedata, Schrödinger) and discusses AI/ML applications in antibody design. The paper identifies future challenges including training data availability, federated learning, CRO integration, and regulatory compliance. No original empirical data or experiments are presented.", 302 "red_flags": [ 303 { 304 "flag": "Severe conflict of interest", 305 "detail": "All four authors are Genedata AG employees. Genedata's platform is described most extensively and favorably among the three reviewed platforms. Competitors' limitations are highlighted (e.g., Dotmatics' initially limited registration, Schrödinger's lack of end-to-end registration) while Genedata's limitations are not discussed. The paper reads in part as a product positioning document." 306 }, 307 { 308 "flag": "No systematic review methodology", 309 "detail": "The paper presents itself as a 'review' but provides no search strategy, inclusion/exclusion criteria, or systematic methodology for selecting the literature or platforms discussed. The selection of three platforms appears to favor the authors' employer." 310 }, 311 { 312 "flag": "Unbounded speculative claims", 313 "detail": "Claims about AI's future impact (e.g., 'AI's biggest impact is likely in the de-novo design of antibodies') are presented without evidence or qualification. The paper freely mixes demonstrated capabilities with speculative future projections." 314 } 315 ], 316 "cited_papers": [ 317 { 318 "title": "Attention is All You Need", 319 "authors": ["Vaswani, A."], 320 "year": 2017, 321 "relevance": "Foundational transformer architecture paper cited in the context of AI applications in biopharma." 322 }, 323 { 324 "title": "Highly accurate protein structure prediction with AlphaFold", 325 "authors": ["Jumper, J."], 326 "year": 2021, 327 "relevance": "Key AI/ML breakthrough in protein structure prediction, cited as transformative for antibody discovery." 328 }, 329 { 330 "title": "Antibody design using deep learning: from sequence and structure design to affinity maturation", 331 "authors": ["Joubbi, S."], 332 "year": 2024, 333 "relevance": "Review of deep learning methods for antibody design, relevant to AI-driven code/model generation in bioinformatics." 334 }, 335 { 336 "title": "BioPhi: A platform for antibody design, humanization, and humanness evaluation based on natural antibody repertoires and deep learning", 337 "authors": ["Prihoda, D."], 338 "year": 2022, 339 "relevance": "Deep learning platform for antibody humanization, example of AI-assisted molecular design tool." 340 }, 341 { 342 "title": "Towards an AI co-scientist", 343 "authors": ["Google"], 344 "year": 2025, 345 "relevance": "Referenced as an emerging reasoning model that could enhance drug target identification, relevant to AI agent capabilities." 346 } 347 ] 348 }