UPA Perpustakaan Universitas Jember

Can human experts predict solubility better than computers?

Samuel Boobier - Personal Name
Anne Osbourn - Personal Name
John B. O. Mitchell - Personal Name

In this study, we design and carry out a survey, asking human experts to predict the aqueous solubility of druglike
organic compounds. We investigate whether these experts, drawn largely from the pharmaceutical industry and
academia, can match or exceed the predictive power of algorithms. Alongside this, we implement 10 typical machine
learning algorithms on the same dataset. The best algorithm, a variety of neural network known as a multi-layer
perceptron, gave an RMSE of 0.985 log S units and an R2 of 0.706. We would not have predicted the relative success of
this particular algorithm in advance. We found that the best individual human predictor generated an almost identical prediction quality with an RMSE of 0.942 log S units and an R2 of 0.723. The collection of algorithms contained
a higher proportion of reasonably good predictors, nine out of ten compared with around half of the humans. We
found that, for either humans or algorithms, combining individual predictions into a consensus predictor by taking
their median generated excellent predictivity. While our consensus human predictor achieved very slightly better
headline fgures on various statistical measures, the diference between it and the consensus machine learning predictor was both small and statistically insignifcant. We conclude that human experts can predict the aqueous solubility of druglike molecules essentially equally well as machine learning algorithms. We fnd that, for either humans or
algorithms, combining individual predictions into a consensus predictor by taking their median is a powerful way of
beneftting from the wisdom of crowds.

No copy data

Detail Information

Series Title

Call Number

Publisher

: ,

Collation

Language

ISBN/ISSN

Classification

NONE

Detail Information

Content Type

Media Type

Carrier Type

Edition

Subject(s)

Specific Detail Info

Statement of Responsibility

No other version available

Can human experts predict solubility better than computers?

UPA Perpustakaan

Merupakan Unit Pendukung Akademis (UPA) yang bersama-sama dengan unit lain melaksanakan Tri Dharma Perguruan Tinggi (PT) melalui menghimpun, memilih, mengolah, merawat serta melayankan sumber informasi kepada civitas akademika Universitas Jember khususnya dan masyarakat akademis pada umumnya.

VISI

UPA Perpustakaan Universitas Jember sebagai perpustakaan modern dengan layanan prima yang mampu menunjang visi Universitas Jember.

MISI

Menyelenggarakan pembinaan dan pengembangan ketersediaan bahan pustaka dan informasi ilmiah sesuai dengan kebutuhan pemustaka secara berkelanjutan

Meningkatkan kualitas dan sistem manajemen layanan perpustakaan secara professional dengan memanfaatkan teknologi informasi

Membina dan mengembangkan jaringan kerjasama dengan pusat-pusat informasi dan lembaga terkait dalam dan luar negeri

UPA Perpustakaan Universitas Jember

NPP. 3509212D1000001

Can human experts predict solubility better than computers?

Samuel Boobier - Personal NameAnne Osbourn - Personal NameJohn B. O. Mitchell - Personal Name

Series Title

Call Number

Publisher

Collation

Language

ISBN/ISSN

Classification

Content Type

Media Type

Carrier Type

Edition

Subject(s)

Specific Detail Info

Statement of Responsibility

About Us

UPA Perpustakaan

Total Koleksi

Total Item

Total Member

Total Pustakawan

Total Terpinjam

Peminjaman Tahun 2025

Peminjaman 5 Tahun

Peminjaman Bulan June 2025

Total Pengunjung

Pengunjung Tahun 2025

Pengunjung 5 Tahun Terakhir

Pengunjung Bulan June 2025

New collection + Update

mode interaksi protein koro komak dengan gum xathan

strategi pengembangan produk unggulan umbi umbian inferior di kabupaten jember

prosedur akuntansi deposito berjangka pada pt bank tabungan pensiunan nasional btpn caang jember

efektivitas saluran distribusi bahan bangunan pada ud karya prima sidoarjo

analisis kualitas pelayanan dalam membangun kepuasan anggota pada kpri bina karya kecamatan gambiran banyuwangi

pengaruh komunikasi pemasaran tabungan britama terhadap pengambilan keputusan pada mahasiswa fakultas ilmu sosial dan ilmu politik universitas jember

Aplikasi Android

Our Services

Help Desk and Service Support UPA Perpustakaan

Tautan Pintas :

Jam Layanan :

Senin - Kamis:

Jum'at:

Sabtu dan Minggu:

Alamat & Kontak Info :

Jalan Kalimantan No. 37 - Kampus Bumi Tegalboto Kotak POS 159 Jember, Jawa Timur, 68121, Indonesia

library@unej.ac.id

(+62) 331 333860

Samuel Boobier - Personal Name
Anne Osbourn - Personal Name
John B. O. Mitchell - Personal Name