Minmeng Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Minmeng Tang has a total of 82 co-authors. Here are the top co-authors by number of shared publications:
- Anil Vachani
University of Pennsylvania, Philadelphia, PA
15 shared publications - Christine Ann Garcia
Division of Hematology and Oncology, Department of Medicine Weill Cornell Medicine New York New York USA
15 shared publications - Eunji Choi
Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, USA
15 shared publications - Evan Sholle
Weill Cornell Medicine, New York Presbyterian Hospital , New York, NY 10065
15 shared publications - Huaizhu Oliver Gao
School of Civil and Environmental Engineering, Cornell University, Ithaca, NY, USA
15 shared publications - James Patrick Solomon
Department of Pathology and Laboratory Medicine, Weill Cornell Medicine, New York, New York
15 shared publications
Latest Publications
- 2 November 2026
- Published by Wiley in Advanced Materials
Attribution Fingerprinting by Interpretable Machine Learning Reveals Category‐Specific Additive Design Rules for Zinc Anodes
Electrolyte additives are one of the most direct remedy for interfacial instability in aqueous zinc‐ion batteries, yet their development remains empirical. Existing machine‐learning (ML) screening strategies presume a single global structure‐property relationship shared by all additives. Here, an interpretable ML framework predicts cycle life from molecular descriptors and test conditions, and molecule‐specific SHapley Additive exPlanations (SHAP) profiles serve as attribution fingerprints. Unsupervised clustering resolves the additives into three attribution‐based categories, governed respectively by adsorption energetics, charge‐transfer gap and hydrogen‐bond‐network regulation, indicating that one universal descriptor set may not hold across chemically distinct additives. Representative additives from each category, none present in the training set, agree with experiment to within 11%. Category I screening identifies 2‐fluoropyridine‐5‐carbaldehyde (2FPD), predicted at 3218 h, and Zn//Zn cells deliver 3010 h at 1 mA cm −2 and 1 mAh cm −2 , within 6.5% of prediction. Structural controls trace the improvement to the aldehyde: retaining it alone gives 900 h against an 89 h baseline, whereas fluorine alone gives 90 h. 2FPD constructs a graded organic‐inorganic interphase that limits water access to the zinc surface and accelerates Zn 2+ desolvation, and Zn//MnO 2 full cells retain 96% capacity over 4000 cycles. This workflow offers a route towards interpretability‐guided additive design.
- 2 November 2026
- Published by Wiley in Advanced Materials
Attribution Fingerprinting by Interpretable Machine Learning Reveals Category‐Specific Additive Design Rules for Zinc Anodes
Electrolyte additives are one of the most direct remedy for interfacial instability in aqueous zinc‐ion batteries, yet their development remains empirical. Existing machine‐learning (ML) screening strategies presume a single global structure‐property relationship shared by all additives. Here, an interpretable ML framework predicts cycle life from molecular descriptors and test conditions, and molecule‐specific SHapley Additive exPlanations (SHAP) profiles serve as attribution fingerprints. Unsupervised clustering resolves the additives into three attribution‐based categories, governed respectively by adsorption energetics, charge‐transfer gap and hydrogen‐bond‐network regulation, indicating that one universal descriptor set may not hold across chemically distinct additives. Representative additives from each category, none present in the training set, agree with experiment to within 11%. Category I screening identifies 2‐fluoropyridine‐5‐carbaldehyde (2FPD), predicted at 3218 h, and Zn//Zn cells deliver 3010 h at 1 mA cm −2 and 1 mAh cm −2 , within 6.5% of prediction. Structural controls trace the improvement to the aldehyde: retaining it alone gives 900 h against an 89 h baseline, whereas fluorine alone gives 90 h. 2FPD constructs a graded organic‐inorganic interphase that limits water access to the zinc surface and accelerates Zn 2+ desolvation, and Zn//MnO 2 full cells retain 96% capacity over 4000 cycles. This workflow offers a route towards interpretability‐guided additive design.
Selective Interfacial Regulation of LiMn 2 O 4 for Flow Electrochemical Lithium Extraction
Gas‐produced water (GPW) is increasingly recognized as an important low‐quality aqueous lithium resource. Electrochemical lithium extraction using LiMn 2 O 4 (LMO) offers a promising strategy for lithium extraction from aqueous resources. However, its application to GPW is hindered by competing‐ion co‐intercalation and Mn dissolution, which compromise extraction selectivity and stability. Inspired by selective ion transport in biological ion pumps, a Li 0.33 La 0.56 TiO 3 (LLTO)‐engineered LMO interface is developed to integrate Li + ‐sieving nanochannels with interfacial stabilization. Experimental and mechanistic analyses demonstrate that the LLTO‐engineered interface promotes local Li + enrichment, while its Li + ‐sieving nanochannels restrict competing‐cation access, thereby accelerating selective Li + transport and optimizing Li + storage. Concurrently, the LLTO suppresses Mn dissolution, thereby preserving interfacial stability during repeated Li + extraction and release. Furthermore, the cyclic flow 3LLTO‐LMO//3LLTO‐λ‐MnO 2 system delivers 16.6 mg·g −1 lithium release capacity after 10 cycles and achieves an 87.5% Li + recovery rate while retaining 60.7% Li + purity from simulated GPW after 20 cycles, and further demonstrates applicability to real GPW. This work establishes a Li + ‐selective interfacial regulation strategy for efficient and stable lithium extraction and provides a material‐to‐process framework for sustainable lithium extraction from low‐quality aqueous lithium resources.
Selective Interfacial Regulation of LiMn 2 O 4 for Flow Electrochemical Lithium Extraction
Gas‐produced water (GPW) is increasingly recognized as an important low‐quality aqueous lithium resource. Electrochemical lithium extraction using LiMn 2 O 4 (LMO) offers a promising strategy for lithium extraction from aqueous resources. However, its application to GPW is hindered by competing‐ion co‐intercalation and Mn dissolution, which compromise extraction selectivity and stability. Inspired by selective ion transport in biological ion pumps, a Li 0.33 La 0.56 TiO 3 (LLTO)‐engineered LMO interface is developed to integrate Li + ‐sieving nanochannels with interfacial stabilization. Experimental and mechanistic analyses demonstrate that the LLTO‐engineered interface promotes local Li + enrichment, while its Li + ‐sieving nanochannels restrict competing‐cation access, thereby accelerating selective Li + transport and optimizing Li + storage. Concurrently, the LLTO suppresses Mn dissolution, thereby preserving interfacial stability during repeated Li + extraction and release. Furthermore, the cyclic flow 3LLTO‐LMO//3LLTO‐λ‐MnO 2 system delivers 16.6 mg·g −1 lithium release capacity after 10 cycles and achieves an 87.5% Li + recovery rate while retaining 60.7% Li + purity from simulated GPW after 20 cycles, and further demonstrates applicability to real GPW. This work establishes a Li + ‐selective interfacial regulation strategy for efficient and stable lithium extraction and provides a material‐to‐process framework for sustainable lithium extraction from low‐quality aqueous lithium resources.
- Open Access
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Method 1 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Method 1. Final version of the EGFR NLP prompt.
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Method 1 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Method 1. Final version of the EGFR NLP prompt.
- Open Access
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table 5 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Table 5. Natural language processing (NLP) Model Performance for Smoking Status Classification in Training and Testing Datasets, Stratified by Subgroup.
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 5 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Table 5. Natural language processing (NLP) Model Performance for Smoking Status Classification in Training and Testing Datasets, Stratified by Subgroup.
- Open Access
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table 1 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Table 1. Personnel and effort involved in establishing MCC-MELD.
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 1 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Table 1. Personnel and effort involved in establishing MCC-MELD.
- Open Access
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Figure 2 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Figure 2. Note selection for smoking NLP model development and annotators’ agreement.
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure 2 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Figure 2. Note selection for smoking NLP model development and annotators’ agreement.
- Open Access
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Table 3 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Table 3. Distribution of development and test sets by smoking natural language processing (NLP) by calendar year.
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table 3 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Table 3. Distribution of development and test sets by smoking natural language processing (NLP) by calendar year.
- Open Access
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Materials and Methods from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Materials and Methods: Proposal
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Materials and Methods from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Materials and Methods: Proposal
- Open Access
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Data from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Background:The proportion of lung cancers affecting individuals who have never smoked is growing, with these cancers being prone to harbor mutations in the EGFR gene. Little is known about risk factors and prognostic indicators for EGFR-mutant cancers, with current research limited by the scarcity of datasets integrating genomic, clinical, and environmental data.Methods:We created the Meyer Cancer Center Molecularly Enhanced Lung Cancer Database (MCC-MELD), including lung cancer cases from a large catchment area in New York City. We identified cases through linkage to our institution’s cancer registry and a clinician-initiated, manually curated database. We linked all cases to the electronic health record and in-house tumor genomic testing results. We used natural language processing (NLP) to extract unstructured genomic testing results and detailed smoking history. We linked geocoded addresses to detailed area-level measures.Results:MCC-MELD contains 9,573 patients with lung cancer diagnosed from 1988 to 2024, of whom 20% were non-Hispanic Asian, 14% were non-Hispanic Black, and 8% were Hispanic. We identified 1,092 (11.4%) EGFR-mutant cancers, with NLP identifying 397 cases not identified by structured data. NLP showed high accuracy in ascertaining EGFR status (97%) and quantitative smoking history variables (90%–98%). Never smokers made up 16% of the cases in MCC-MELD.Conclusions:MCC-MELD is an NLP-enhanced database containing clinical information, genomic testing results, and linkages to area-level data for patients with lung cancer from a diverse urban setting.Impact:This resource can facilitate studies on lung cancer risk factors, treatment patterns, and outcomes by EGFR and other driver mutation status.
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Open AccessData from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Background:The proportion of lung cancers affecting individuals who have never smoked is growing, with these cancers being prone to harbor mutations in the EGFR gene. Little is known about risk factors and prognostic indicators for EGFR-mutant cancers, with current research limited by the scarcity of datasets integrating genomic, clinical, and environmental data.Methods:We created the Meyer Cancer Center Molecularly Enhanced Lung Cancer Database (MCC-MELD), including lung cancer cases from a large catchment area in New York City. We identified cases through linkage to our institution’s cancer registry and a clinician-initiated, manually curated database. We linked all cases to the electronic health record and in-house tumor genomic testing results. We used natural language processing (NLP) to extract unstructured genomic testing results and detailed smoking history. We linked geocoded addresses to detailed area-level measures.Results:MCC-MELD contains 9,573 patients with lung cancer diagnosed from 1988 to 2024, of whom 20% were non-Hispanic Asian, 14% were non-Hispanic Black, and 8% were Hispanic. We identified 1,092 (11.4%) EGFR-mutant cancers, with NLP identifying 397 cases not identified by structured data. NLP showed high accuracy in ascertaining EGFR status (97%) and quantitative smoking history variables (90%–98%). Never smokers made up 16% of the cases in MCC-MELD.Conclusions:MCC-MELD is an NLP-enhanced database containing clinical information, genomic testing results, and linkages to area-level data for patients with lung cancer from a diverse urban setting.Impact:This resource can facilitate studies on lung cancer risk factors, treatment patterns, and outcomes by EGFR and other driver mutation status.
- Open Access
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Supplementary Method 2 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Method 2. Final version of the quantitative smoking NLP prompt.
- 19 June 2026
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Method 2 from Design and Creation of a Racially Diverse Lung Cancer Registry with Detailed Genomic and Environmental Annotation
Supplementary Method 2. Final version of the quantitative smoking NLP prompt.